Compare commits
235 Commits
Author | SHA1 | Date |
---|---|---|
|
796aff4514 | 11 years ago |
|
2a2fe448e7 | 11 years ago |
|
23967d11dd | 11 years ago |
|
7a3251f649 | 11 years ago |
|
9ba8910281 | 11 years ago |
|
e83a3cf263 | 11 years ago |
|
b3c2945d9b | 12 years ago |
|
fc3cf08675 | 12 years ago |
|
8162cd31b7 | 11 years ago |
|
1ea6fdc9a7 | 12 years ago |
|
1b0c9f40cc | 12 years ago |
|
c0111a467b | 12 years ago |
|
64175151f8 | 12 years ago |
|
586957e840 | 12 years ago |
|
f2fc775963 | 12 years ago |
|
b8bce948c8 | 12 years ago |
|
0a996857dd | 12 years ago |
|
26509f614c | 12 years ago |
|
3e28d5a936 | 12 years ago |
|
95ff427873 | 12 years ago |
|
8ed10037df | 12 years ago |
|
7a090dd4a2 | 12 years ago |
|
49f34cb48d | 12 years ago |
|
2a76de50dd | 12 years ago |
|
8adf7fc600 | 12 years ago |
|
f4c053f56f | 12 years ago |
|
5cb5a1677d | 12 years ago |
|
9fb9f0ef5b | 12 years ago |
|
242d69a981 | 12 years ago |
|
eb151a4c5d | 12 years ago |
|
2520b19798 | 12 years ago |
|
319c9e979a | 12 years ago |
|
93aa5b1920 | 12 years ago |
|
f648af66a6 | 12 years ago |
|
7c4185e1fa | 12 years ago |
|
0fb06a3fd3 | 12 years ago |
|
1e39d643a8 | 12 years ago |
|
69d58663ef | 12 years ago |
|
e59b53fab2 | 12 years ago |
|
a66f6f0166 | 12 years ago |
|
1344f03b16 | 12 years ago |
|
a23c409939 | 12 years ago |
|
a6b1cc833f | 12 years ago |
|
d2c7e3ef56 | 12 years ago |
|
6c87008d7b | 12 years ago |
|
6b3af21e45 | 12 years ago |
|
5a5cc0005c | 12 years ago |
|
d65117c0e3 | 12 years ago |
|
d8884bb655 | 12 years ago |
|
afe9aed2eb | 12 years ago |
|
01e64e989e | 12 years ago |
|
9496df9e9d | 12 years ago |
|
8b4c67b977 | 12 years ago |
|
f77a8f5573 | 12 years ago |
|
de8aefebb7 | 12 years ago |
|
8f0d22a6f2 | 12 years ago |
|
721190028b | 12 years ago |
|
50e565142e | 12 years ago |
|
bead3e2b07 | 12 years ago |
|
71aa0cbb9a | 12 years ago |
|
8de19cbd52 | 12 years ago |
|
8573832ff7 | 12 years ago |
|
7c1d3f8762 | 12 years ago |
|
9cd1adcdee | 12 years ago |
|
f017ac9dca | 12 years ago |
|
907704e45f | 12 years ago |
|
b17f937389 | 12 years ago |
|
f591c56dd4 | 12 years ago |
|
2fd54901e7 | 12 years ago |
|
1bf6c5a82e | 12 years ago |
|
45484461b5 | 12 years ago |
|
aa394f59ae | 12 years ago |
|
717111f5d2 | 12 years ago |
|
e3461dc35f | 12 years ago |
|
9b834f62a9 | 12 years ago |
|
935938474c | 12 years ago |
|
6573196186 | 12 years ago |
|
9a07f2ed65 | 12 years ago |
|
613ff3b729 | 12 years ago |
|
def62fc865 | 12 years ago |
|
037c355836 | 12 years ago |
|
180b2bbffe | 12 years ago |
|
143dcad4f3 | 12 years ago |
|
b0e352ab6d | 12 years ago |
|
5ea7dc5920 | 12 years ago |
|
3c675b5b8a | 12 years ago |
|
11ea9b4e91 | 12 years ago |
|
e8a2139ecf | 12 years ago |
|
dc57d7b6d1 | 12 years ago |
|
0925f1312d | 12 years ago |
|
efc02f66f5 | 12 years ago |
|
9ce8ffc14b | 12 years ago |
|
bab07a05e7 | 12 years ago |
|
1df9f7c83f | 12 years ago |
|
efdf77ef6c | 12 years ago |
|
a989c93505 | 12 years ago |
|
d122bd1b43 | 12 years ago |
|
ab81824f4c | 12 years ago |
|
4eb73e3609 | 12 years ago |
|
6bcb279f0e | 12 years ago |
|
f446c8ed33 | 12 years ago |
|
10a34f2b69 | 12 years ago |
|
cc3ebd79e8 | 12 years ago |
|
3e035f84b1 | 12 years ago |
|
611c159373 | 12 years ago |
|
db65980ba4 | 12 years ago |
|
180576f2b7 | 12 years ago |
|
46d4d34da7 | 12 years ago |
|
3fa21560be | 12 years ago |
|
b902186389 | 12 years ago |
|
da87e68fad | 12 years ago |
|
f23412ea7e | 12 years ago |
|
07abf7c83d | 12 years ago |
|
6259684487 | 12 years ago |
|
0a0935d635 | 12 years ago |
|
fb5b17005f | 12 years ago |
|
e3745b5d74 | 12 years ago |
|
8d24d96804 | 12 years ago |
|
529b535d9f | 12 years ago |
|
0793668e5c | 12 years ago |
|
8d368ecf29 | 12 years ago |
|
2d2b0c9048 | 12 years ago |
|
fb0719d677 | 12 years ago |
|
7ffa5dc7b6 | 12 years ago |
|
32c289fd3d | 12 years ago |
|
ff63b8a1c5 | 12 years ago |
|
60d8934444 | 12 years ago |
|
e0aba01866 | 12 years ago |
|
1ae498e3c8 | 12 years ago |
|
d1db099f71 | 12 years ago |
|
f4ef64290d | 12 years ago |
|
026151d1a1 | 12 years ago |
|
70dada8ef6 | 12 years ago |
|
9ef752f8a3 | 12 years ago |
|
d265a5bddd | 12 years ago |
|
b2b6e3eb33 | 12 years ago |
|
2b6c7a8f94 | 12 years ago |
|
6070209d33 | 12 years ago |
|
fa78d18890 | 12 years ago |
|
40eaf2a96b | 12 years ago |
|
73dd0916c0 | 12 years ago |
|
77d32fe16b | 12 years ago |
|
7def0944a6 | 12 years ago |
|
8782cd77d5 | 12 years ago |
|
1b59fd9af0 | 12 years ago |
|
9dca8a03be | 12 years ago |
|
132f4882e5 | 12 years ago |
|
9e32a38288 | 12 years ago |
|
c1b13cd076 | 12 years ago |
|
820588aa5f | 12 years ago |
|
8fbf050510 | 12 years ago |
|
dd5ae3c4ee | 12 years ago |
|
ab51707607 | 12 years ago |
|
8acdc56df1 | 12 years ago |
|
d345a05b3c | 12 years ago |
|
5f427ec6ea | 12 years ago |
|
a95c030885 | 12 years ago |
|
bef6a74dfe | 12 years ago |
|
01da470c21 | 12 years ago |
|
5fdf4d9085 | 12 years ago |
|
bc51e263e1 | 12 years ago |
|
4c527f0931 | 12 years ago |
|
e9fc528a0f | 12 years ago |
|
c9ba3c804e | 12 years ago |
|
ee9fe347c7 | 12 years ago |
|
515aafe112 | 12 years ago |
|
314016e1fa | 12 years ago |
|
906a54ef09 | 12 years ago |
|
ec2facd056 | 12 years ago |
|
ddbfef575f | 12 years ago |
|
8dd7a4771c | 12 years ago |
|
49ba1f1acd | 12 years ago |
|
c4d661535c | 12 years ago |
|
bd52ab7ab1 | 12 years ago |
|
cce0a8ec62 | 12 years ago |
|
d02e62f89f | 12 years ago |
|
e180addc3c | 12 years ago |
|
a37a4a8cd4 | 12 years ago |
|
8328c18728 | 12 years ago |
|
7ae07d6c15 | 12 years ago |
|
770bcf5bc6 | 12 years ago |
|
7bd6a295d8 | 12 years ago |
|
4063761313 | 12 years ago |
|
d62b346a74 | 12 years ago |
|
155732ab1a | 12 years ago |
|
b3713b7ae5 | 12 years ago |
|
19d026756c | 12 years ago |
|
3cddd29425 | 12 years ago |
|
23bde0b866 | 12 years ago |
|
6f895c1805 | 12 years ago |
|
96089074ce | 12 years ago |
|
2ed53df008 | 12 years ago |
|
060859483a | 12 years ago |
|
eced476eaf | 12 years ago |
|
8d5b55a753 | 12 years ago |
|
7296dc54d0 | 12 years ago |
|
e5e9cf7d5f | 12 years ago |
|
b106229a78 | 12 years ago |
|
73efd5549f | 12 years ago |
|
8139016636 | 12 years ago |
|
59c0d0416e | 12 years ago |
|
cd559ece04 | 12 years ago |
|
120a4ad1ed | 12 years ago |
|
3363e164fd | 12 years ago |
|
6d6d5caeb6 | 12 years ago |
|
21030e7cb4 | 12 years ago |
|
9b238ba712 | 12 years ago |
|
b3d2d5349b | 12 years ago |
|
f9bad281de | 12 years ago |
|
72ce919989 | 12 years ago |
|
ff782669f6 | 12 years ago |
|
36950993f1 | 12 years ago |
|
7df93dc1b4 | 12 years ago |
|
a45913eee7 | 12 years ago |
|
a25eac6c4e | 12 years ago |
|
dd0fcf0bc1 | 12 years ago |
|
2267235eca | 12 years ago |
|
029cf9ecac | 12 years ago |
|
f4217ecd3d | 12 years ago |
|
31cd993506 | 12 years ago |
|
fb579561de | 12 years ago |
|
37eb424827 | 12 years ago |
|
4348451692 | 12 years ago |
|
e93e55a0f7 | 12 years ago |
|
bc11f90529 | 12 years ago |
|
8fcc246f25 | 12 years ago |
|
4d7c38d6db | 12 years ago |
|
c8d79cde21 | 12 years ago |
|
f4d792079b | 12 years ago |
|
78ab419cd8 | 12 years ago |
|
3e93983f6e | 12 years ago |
|
6a4822cc26 | 12 years ago |
|
92b08bb5d5 | 12 years ago |
|
e270e09969 | 12 years ago |
|
40cd5218db | 12 years ago |
102 changed files with 10237 additions and 339 deletions
@ -1,13 +1,6 @@ |
|||
from couchpotato.core.event import addEvent |
|||
from couchpotato.core.plugins.base import Plugin |
|||
from .main import Library |
|||
|
|||
def start(): |
|||
return Library() |
|||
|
|||
class LibraryBase(Plugin): |
|||
|
|||
_type = None |
|||
|
|||
def initType(self): |
|||
addEvent('library.types', self.getType) |
|||
|
|||
def getType(self): |
|||
return self._type |
|||
config = [] |
|||
|
@ -0,0 +1,13 @@ |
|||
from couchpotato.core.event import addEvent |
|||
from couchpotato.core.plugins.base import Plugin |
|||
|
|||
|
|||
class LibraryBase(Plugin): |
|||
|
|||
_type = None |
|||
|
|||
def initType(self): |
|||
addEvent('library.types', self.getType) |
|||
|
|||
def getType(self): |
|||
return self._type |
@ -0,0 +1,18 @@ |
|||
from couchpotato.core.event import addEvent, fireEvent |
|||
from couchpotato.core.media._base.library.base import LibraryBase |
|||
|
|||
|
|||
class Library(LibraryBase): |
|||
def __init__(self): |
|||
addEvent('library.title', self.title) |
|||
|
|||
def title(self, library): |
|||
return fireEvent( |
|||
'library.query', |
|||
library, |
|||
|
|||
condense = False, |
|||
include_year = False, |
|||
include_identifier = False, |
|||
single = True |
|||
) |
@ -0,0 +1,6 @@ |
|||
from .main import Matcher |
|||
|
|||
def start(): |
|||
return Matcher() |
|||
|
|||
config = [] |
@ -0,0 +1,84 @@ |
|||
from couchpotato.core.event import addEvent |
|||
from couchpotato.core.helpers.encoding import simplifyString |
|||
from couchpotato.core.logger import CPLog |
|||
from couchpotato.core.plugins.base import Plugin |
|||
|
|||
log = CPLog(__name__) |
|||
|
|||
|
|||
class MatcherBase(Plugin): |
|||
type = None |
|||
|
|||
def __init__(self): |
|||
if self.type: |
|||
addEvent('%s.matcher.correct' % self.type, self.correct) |
|||
|
|||
def correct(self, chain, release, media, quality): |
|||
raise NotImplementedError() |
|||
|
|||
def flattenInfo(self, info): |
|||
# Flatten dictionary of matches (chain info) |
|||
if isinstance(info, dict): |
|||
return dict([(key, self.flattenInfo(value)) for key, value in info.items()]) |
|||
|
|||
# Flatten matches |
|||
result = None |
|||
|
|||
for match in info: |
|||
if isinstance(match, dict): |
|||
if result is None: |
|||
result = {} |
|||
|
|||
for key, value in match.items(): |
|||
if key not in result: |
|||
result[key] = [] |
|||
|
|||
result[key].append(value) |
|||
else: |
|||
if result is None: |
|||
result = [] |
|||
|
|||
result.append(match) |
|||
|
|||
return result |
|||
|
|||
def constructFromRaw(self, match): |
|||
if not match: |
|||
return None |
|||
|
|||
parts = [ |
|||
''.join([ |
|||
y for y in x[1:] if y |
|||
]) for x in match |
|||
] |
|||
|
|||
return ''.join(parts)[:-1].strip() |
|||
|
|||
def simplifyValue(self, value): |
|||
if not value: |
|||
return value |
|||
|
|||
if isinstance(value, basestring): |
|||
return simplifyString(value) |
|||
|
|||
if isinstance(value, list): |
|||
return [self.simplifyValue(x) for x in value] |
|||
|
|||
raise ValueError("Unsupported value type") |
|||
|
|||
def chainMatch(self, chain, group, tags): |
|||
info = self.flattenInfo(chain.info[group]) |
|||
|
|||
found_tags = [] |
|||
for tag, accepted in tags.items(): |
|||
values = [self.simplifyValue(x) for x in info.get(tag, [None])] |
|||
|
|||
if any([val in accepted for val in values]): |
|||
found_tags.append(tag) |
|||
|
|||
log.debug('tags found: %s, required: %s' % (found_tags, tags.keys())) |
|||
|
|||
if set(tags.keys()) == set(found_tags): |
|||
return True |
|||
|
|||
return all([key in found_tags for key, value in tags.items()]) |
@ -0,0 +1,88 @@ |
|||
from couchpotato.core.event import addEvent, fireEvent |
|||
from couchpotato.core.helpers.variable import possibleTitles |
|||
from couchpotato.core.logger import CPLog |
|||
from couchpotato.core.media._base.matcher.base import MatcherBase |
|||
from caper import Caper |
|||
|
|||
log = CPLog(__name__) |
|||
|
|||
|
|||
class Matcher(MatcherBase): |
|||
def __init__(self): |
|||
super(Matcher, self).__init__() |
|||
|
|||
self.caper = Caper() |
|||
|
|||
addEvent('matcher.parse', self.parse) |
|||
addEvent('matcher.match', self.match) |
|||
|
|||
addEvent('matcher.flatten_info', self.flattenInfo) |
|||
addEvent('matcher.construct_from_raw', self.constructFromRaw) |
|||
|
|||
addEvent('matcher.correct_title', self.correctTitle) |
|||
addEvent('matcher.correct_quality', self.correctQuality) |
|||
|
|||
def parse(self, name, parser='scene'): |
|||
return self.caper.parse(name, parser) |
|||
|
|||
def match(self, release, media, quality): |
|||
match = fireEvent('matcher.parse', release['name'], single = True) |
|||
|
|||
if len(match.chains) < 1: |
|||
log.info2('Wrong: %s, unable to parse release name (no chains)', release['name']) |
|||
return False |
|||
|
|||
for chain in match.chains: |
|||
if fireEvent('%s.matcher.correct' % media['type'], chain, release, media, quality, single = True): |
|||
return chain |
|||
|
|||
return False |
|||
|
|||
def correctTitle(self, chain, media): |
|||
root_library = media['library']['root_library'] |
|||
|
|||
if 'show_name' not in chain.info or not len(chain.info['show_name']): |
|||
log.info('Wrong: missing show name in parsed result') |
|||
return False |
|||
|
|||
# Get the lower-case parsed show name from the chain |
|||
chain_words = [x.lower() for x in chain.info['show_name']] |
|||
|
|||
# Build a list of possible titles of the media we are searching for |
|||
titles = root_library['info']['titles'] |
|||
|
|||
# Add year suffix titles (will result in ['<name_one>', '<name_one> <suffix_one>', '<name_two>', ...]) |
|||
suffixes = [None, root_library['info']['year']] |
|||
|
|||
titles = [ |
|||
title + ((' %s' % suffix) if suffix else '') |
|||
for title in titles |
|||
for suffix in suffixes |
|||
] |
|||
|
|||
# Check show titles match |
|||
# TODO check xem names |
|||
for title in titles: |
|||
for valid_words in [x.split(' ') for x in possibleTitles(title)]: |
|||
|
|||
if valid_words == chain_words: |
|||
return True |
|||
|
|||
return False |
|||
|
|||
def correctQuality(self, chain, quality, quality_map): |
|||
if quality['identifier'] not in quality_map: |
|||
log.info2('Wrong: unknown preferred quality %s', quality['identifier']) |
|||
return False |
|||
|
|||
if 'video' not in chain.info: |
|||
log.info2('Wrong: no video tags found') |
|||
return False |
|||
|
|||
video_tags = quality_map[quality['identifier']] |
|||
|
|||
if not self.chainMatch(chain, 'video', video_tags): |
|||
log.info2('Wrong: %s tags not in chain', video_tags) |
|||
return False |
|||
|
|||
return True |
@ -0,0 +1,6 @@ |
|||
from .main import ShowBase |
|||
|
|||
def start(): |
|||
return ShowBase() |
|||
|
|||
config = [] |
@ -0,0 +1,239 @@ |
|||
from couchpotato import get_session |
|||
from couchpotato.api import addApiView |
|||
from couchpotato.core.event import fireEvent, fireEventAsync, addEvent |
|||
from couchpotato.core.helpers.variable import tryInt |
|||
from couchpotato.core.logger import CPLog |
|||
from couchpotato.core.media import MediaBase |
|||
from couchpotato.core.settings.model import Media |
|||
import time |
|||
|
|||
log = CPLog(__name__) |
|||
|
|||
|
|||
class ShowBase(MediaBase): |
|||
|
|||
_type = 'show' |
|||
|
|||
def __init__(self): |
|||
super(ShowBase, self).__init__() |
|||
|
|||
addApiView('show.add', self.addView, docs = { |
|||
'desc': 'Add new movie to the wanted list', |
|||
'params': { |
|||
'identifier': {'desc': 'IMDB id of the movie your want to add.'}, |
|||
'profile_id': {'desc': 'ID of quality profile you want the add the movie in. If empty will use the default profile.'}, |
|||
'title': {'desc': 'Movie title to use for searches. Has to be one of the titles returned by movie.search.'}, |
|||
} |
|||
}) |
|||
|
|||
addEvent('show.add', self.add) |
|||
|
|||
def addView(self, **kwargs): |
|||
add_dict = self.add(params = kwargs) |
|||
|
|||
return { |
|||
'success': True if add_dict else False, |
|||
'show': add_dict, |
|||
} |
|||
|
|||
def add(self, params = {}, force_readd = True, search_after = True, update_library = False, status_id = None): |
|||
""" |
|||
params |
|||
{'category_id': u'-1', |
|||
'identifier': u'tt1519931', |
|||
'profile_id': u'12', |
|||
'thetvdb_id': u'158661', |
|||
'title': u'Haven'} |
|||
""" |
|||
log.debug("show.add") |
|||
|
|||
# Add show parent to db first; need to update library so maps will be in place (if any) |
|||
parent = self.addToDatabase(params = params, update_library = True, type = 'show') |
|||
|
|||
# TODO: add by airdate |
|||
|
|||
# Add by Season/Episode numbers |
|||
self.addBySeasonEpisode(parent, |
|||
params = params, |
|||
force_readd = force_readd, |
|||
search_after = search_after, |
|||
update_library = update_library, |
|||
status_id = status_id |
|||
) |
|||
|
|||
def addBySeasonEpisode(self, parent, params = {}, force_readd = True, search_after = True, update_library = False, status_id = None): |
|||
identifier = params.get('id') |
|||
# 'tvdb' will always be the master for our purpose. All mapped data can be mapped |
|||
# to another source for downloading, but it will always be remapped back to tvdb numbering |
|||
# when renamed so media can be used in media players that use tvdb for info provider |
|||
# |
|||
# This currently means the episode must actually exist in tvdb in order to be found but |
|||
# the numbering can be different |
|||
|
|||
#master = 'tvdb' |
|||
#destination = 'scene' |
|||
#destination = 'anidb' |
|||
#destination = 'rage' |
|||
#destination = 'trakt' |
|||
# TODO: auto mode. if anime exists use it. if scene exists use it else use tvdb |
|||
|
|||
# XXX: We should abort adding show, etc if either tvdb or xem is down or we will have incorrent mappings |
|||
# I think if tvdb gets error we wont have anydata anyway, but we must make sure XEM returns!!!! |
|||
|
|||
# Only the master should return results here; all other info providers should just return False |
|||
# since we are just interested in the structure at this point. |
|||
seasons = fireEvent('season.info', merge = True, identifier = identifier) |
|||
if seasons is not None: |
|||
for season in seasons: |
|||
# Make sure we are only dealing with 'tvdb' responses at this point |
|||
if season.get('primary_provider', None) != 'thetvdb': |
|||
continue |
|||
season_id = season.get('id', None) |
|||
if season_id is None: continue |
|||
|
|||
season_params = {'season_identifier': season_id} |
|||
# Calling all info providers; merge your info now for individual season |
|||
single_season = fireEvent('season.info', merge = True, identifier = identifier, params = season_params) |
|||
single_season['category_id'] = params.get('category_id') |
|||
single_season['profile_id'] = params.get('profile_id') |
|||
single_season['title'] = single_season.get('original_title', None) |
|||
single_season['identifier'] = season_id |
|||
single_season['parent_identifier'] = identifier |
|||
log.info("Adding Season %s" % season_id) |
|||
s = self.addToDatabase(params = single_season, type = "season") |
|||
|
|||
episode_params = {'season_identifier': season_id} |
|||
episodes = fireEvent('episode.info', merge = True, identifier = identifier, params = episode_params) |
|||
if episodes is not None: |
|||
for episode in episodes: |
|||
# Make sure we are only dealing with 'tvdb' responses at this point |
|||
if episode.get('primary_provider', None) != 'thetvdb': |
|||
continue |
|||
episode_id = episode.get('id', None) |
|||
if episode_id is None: continue |
|||
try: |
|||
episode_number = int(episode.get('episodenumber', None)) |
|||
except (ValueError, TypeError): |
|||
continue |
|||
try: |
|||
absolute_number = int(episode.get('absolute_number', None)) |
|||
except (ValueError, TypeError): |
|||
absolute_number = None |
|||
|
|||
episode_params = {'season_identifier': season_id, |
|||
'episode_identifier': episode_id, |
|||
'episode': episode_number} |
|||
if absolute_number: |
|||
episode_params['absolute'] = absolute_number |
|||
# Calling all info providers; merge your info now for individual episode |
|||
single_episode = fireEvent('episode.info', merge = True, identifier = identifier, params = episode_params) |
|||
single_episode['category_id'] = params.get('category_id') |
|||
single_episode['profile_id'] = params.get('profile_id') |
|||
single_episode['title'] = single_episode.get('original_title', None) |
|||
single_episode['identifier'] = episode_id |
|||
single_episode['parent_identifier'] = single_season['identifier'] |
|||
log.info("Adding [%sx%s] %s - %s" % (season_id, |
|||
episode_number, |
|||
params['title'], |
|||
single_episode.get('original_title', ''))) |
|||
e = self.addToDatabase(params = single_episode, type = "episode") |
|||
|
|||
# Start searching now that all the media has been added |
|||
if search_after: |
|||
onComplete = self.createOnComplete(parent['id']) |
|||
onComplete() |
|||
|
|||
return parent |
|||
|
|||
def addToDatabase(self, params = {}, type = "show", force_readd = True, search_after = False, update_library = False, status_id = None): |
|||
log.debug("show.addToDatabase") |
|||
|
|||
if not params.get('identifier'): |
|||
msg = 'Can\'t add show without imdb identifier.' |
|||
log.error(msg) |
|||
fireEvent('notify.frontend', type = 'show.is_tvshow', message = msg) |
|||
return False |
|||
#else: |
|||
#try: |
|||
#is_show = fireEvent('movie.is_show', identifier = params.get('identifier'), single = True) |
|||
#if not is_show: |
|||
#msg = 'Can\'t add show, seems to be a TV show.' |
|||
#log.error(msg) |
|||
#fireEvent('notify.frontend', type = 'show.is_tvshow', message = msg) |
|||
#return False |
|||
#except: |
|||
#pass |
|||
|
|||
library = fireEvent('library.add.%s' % type, single = True, attrs = params, update_after = update_library) |
|||
if not library: |
|||
return False |
|||
|
|||
# Status |
|||
status_active, snatched_status, ignored_status, done_status, downloaded_status = \ |
|||
fireEvent('status.get', ['active', 'snatched', 'ignored', 'done', 'downloaded'], single = True) |
|||
|
|||
default_profile = fireEvent('profile.default', single = True) |
|||
cat_id = params.get('category_id', None) |
|||
|
|||
db = get_session() |
|||
m = db.query(Media).filter_by(library_id = library.get('id')).first() |
|||
added = True |
|||
do_search = False |
|||
if not m: |
|||
m = Media( |
|||
type = type, |
|||
library_id = library.get('id'), |
|||
profile_id = params.get('profile_id', default_profile.get('id')), |
|||
status_id = status_id if status_id else status_active.get('id'), |
|||
category_id = tryInt(cat_id) if cat_id is not None and tryInt(cat_id) > 0 else None, |
|||
) |
|||
db.add(m) |
|||
db.commit() |
|||
|
|||
onComplete = None |
|||
if search_after: |
|||
onComplete = self.createOnComplete(m.id) |
|||
|
|||
fireEventAsync('library.update.%s' % type, params.get('identifier'), default_title = params.get('title', ''), on_complete = onComplete) |
|||
search_after = False |
|||
elif force_readd: |
|||
|
|||
# Clean snatched history |
|||
for release in m.releases: |
|||
if release.status_id in [downloaded_status.get('id'), snatched_status.get('id'), done_status.get('id')]: |
|||
if params.get('ignore_previous', False): |
|||
release.status_id = ignored_status.get('id') |
|||
else: |
|||
fireEvent('release.delete', release.id, single = True) |
|||
|
|||
m.profile_id = params.get('profile_id', default_profile.get('id')) |
|||
m.category_id = tryInt(cat_id) if cat_id is not None and tryInt(cat_id) > 0 else None |
|||
else: |
|||
log.debug('Show already exists, not updating: %s', params) |
|||
added = False |
|||
|
|||
if force_readd: |
|||
m.status_id = status_id if status_id else status_active.get('id') |
|||
m.last_edit = int(time.time()) |
|||
do_search = True |
|||
|
|||
db.commit() |
|||
|
|||
# Remove releases |
|||
available_status = fireEvent('status.get', 'available', single = True) |
|||
for rel in m.releases: |
|||
if rel.status_id is available_status.get('id'): |
|||
db.delete(rel) |
|||
db.commit() |
|||
|
|||
show_dict = m.to_dict(self.default_dict) |
|||
|
|||
if do_search and search_after: |
|||
onComplete = self.createOnComplete(m.id) |
|||
onComplete() |
|||
|
|||
if added: |
|||
fireEvent('notify.frontend', type = 'show.added', data = show_dict, message = 'Successfully added "%s" to your wanted list.' % params.get('title', '')) |
|||
|
|||
db.expire_all() |
|||
return show_dict |
@ -0,0 +1,232 @@ |
|||
Block.Search.ShowItem = new Class({ |
|||
|
|||
Implements: [Options, Events], |
|||
|
|||
initialize: function(info, options){ |
|||
var self = this; |
|||
self.setOptions(options); |
|||
|
|||
self.info = info; |
|||
self.alternative_titles = []; |
|||
|
|||
self.create(); |
|||
}, |
|||
|
|||
create: function(){ |
|||
var self = this, |
|||
info = self.info; |
|||
|
|||
self.el = new Element('div.media_result', { |
|||
'id': info.id |
|||
}).adopt( |
|||
self.thumbnail = info.images && info.images.poster.length > 0 ? new Element('img.thumbnail', { |
|||
'src': info.images.poster[0], |
|||
'height': null, |
|||
'width': null |
|||
}) : null, |
|||
self.options_el = new Element('div.options.inlay'), |
|||
self.data_container = new Element('div.data', { |
|||
'events': { |
|||
'click': self.showOptions.bind(self) |
|||
} |
|||
}).adopt( |
|||
self.info_container = new Element('div.info').adopt( |
|||
new Element('h2').adopt( |
|||
self.title = new Element('span.title', { |
|||
'text': info.titles && info.titles.length > 0 ? info.titles[0] : 'Unknown' |
|||
}), |
|||
self.year = info.year ? new Element('span.year', { |
|||
'text': info.year |
|||
}) : null |
|||
) |
|||
) |
|||
) |
|||
) |
|||
|
|||
if(info.titles) |
|||
info.titles.each(function(title){ |
|||
self.alternativeTitle({ |
|||
'title': title |
|||
}); |
|||
}) |
|||
}, |
|||
|
|||
alternativeTitle: function(alternative){ |
|||
var self = this; |
|||
|
|||
self.alternative_titles.include(alternative); |
|||
}, |
|||
|
|||
getTitle: function(){ |
|||
var self = this; |
|||
try { |
|||
return self.info.original_title ? self.info.original_title : self.info.titles[0]; |
|||
} |
|||
catch(e){ |
|||
return 'Unknown'; |
|||
} |
|||
}, |
|||
|
|||
get: function(key){ |
|||
return this.info[key] |
|||
}, |
|||
|
|||
showOptions: function(){ |
|||
var self = this; |
|||
|
|||
self.createOptions(); |
|||
|
|||
self.data_container.addClass('open'); |
|||
self.el.addEvent('outerClick', self.closeOptions.bind(self)) |
|||
|
|||
}, |
|||
|
|||
closeOptions: function(){ |
|||
var self = this; |
|||
|
|||
self.data_container.removeClass('open'); |
|||
self.el.removeEvents('outerClick') |
|||
}, |
|||
|
|||
add: function(e){ |
|||
var self = this; |
|||
|
|||
if(e) |
|||
(e).preventDefault(); |
|||
|
|||
self.loadingMask(); |
|||
|
|||
Api.request('show.add', { |
|||
'data': { |
|||
'identifier': self.info.id, |
|||
'id': self.info.id, |
|||
'type': self.info.type, |
|||
'primary_provider': self.info.primary_provider, |
|||
'title': self.title_select.get('value'), |
|||
'profile_id': self.profile_select.get('value'), |
|||
'category_id': self.category_select.get('value') |
|||
}, |
|||
'onComplete': function(json){ |
|||
self.options_el.empty(); |
|||
self.options_el.adopt( |
|||
new Element('div.message', { |
|||
'text': json.added ? 'Show successfully added.' : 'Show didn\'t add properly. Check logs' |
|||
}) |
|||
); |
|||
self.mask.fade('out'); |
|||
|
|||
self.fireEvent('added'); |
|||
}, |
|||
'onFailure': function(){ |
|||
self.options_el.empty(); |
|||
self.options_el.adopt( |
|||
new Element('div.message', { |
|||
'text': 'Something went wrong, check the logs for more info.' |
|||
}) |
|||
); |
|||
self.mask.fade('out'); |
|||
} |
|||
}); |
|||
}, |
|||
|
|||
createOptions: function(){ |
|||
var self = this, |
|||
info = self.info; |
|||
|
|||
if(!self.options_el.hasClass('set')){ |
|||
|
|||
if(self.info.in_library){ |
|||
var in_library = []; |
|||
self.info.in_library.releases.each(function(release){ |
|||
in_library.include(release.quality.label) |
|||
}); |
|||
} |
|||
|
|||
self.options_el.grab( |
|||
new Element('div', { |
|||
'class': self.info.in_wanted && self.info.in_wanted.profile_id || in_library ? 'in_library_wanted' : '' |
|||
}).adopt( |
|||
self.info.in_wanted && self.info.in_wanted.profile_id ? new Element('span.in_wanted', { |
|||
'text': 'Already in wanted list: ' + Quality.getProfile(self.info.in_wanted.profile_id).get('label') |
|||
}) : (in_library ? new Element('span.in_library', { |
|||
'text': 'Already in library: ' + in_library.join(', ') |
|||
}) : null), |
|||
self.title_select = new Element('select', { |
|||
'name': 'title' |
|||
}), |
|||
self.profile_select = new Element('select', { |
|||
'name': 'profile' |
|||
}), |
|||
self.category_select = new Element('select', { |
|||
'name': 'category' |
|||
}).grab( |
|||
new Element('option', {'value': -1, 'text': 'None'}) |
|||
), |
|||
self.add_button = new Element('a.button', { |
|||
'text': 'Add', |
|||
'events': { |
|||
'click': self.add.bind(self) |
|||
} |
|||
}) |
|||
) |
|||
); |
|||
|
|||
Array.each(self.alternative_titles, function(alt){ |
|||
new Element('option', { |
|||
'text': alt.title |
|||
}).inject(self.title_select) |
|||
}) |
|||
|
|||
|
|||
// Fill categories
|
|||
var categories = CategoryList.getAll(); |
|||
|
|||
if(categories.length == 0) |
|||
self.category_select.hide(); |
|||
else { |
|||
self.category_select.show(); |
|||
categories.each(function(category){ |
|||
new Element('option', { |
|||
'value': category.data.id, |
|||
'text': category.data.label |
|||
}).inject(self.category_select); |
|||
}); |
|||
} |
|||
|
|||
// Fill profiles
|
|||
var profiles = Quality.getActiveProfiles(); |
|||
if(profiles.length == 1) |
|||
self.profile_select.hide(); |
|||
|
|||
profiles.each(function(profile){ |
|||
new Element('option', { |
|||
'value': profile.id ? profile.id : profile.data.id, |
|||
'text': profile.label ? profile.label : profile.data.label |
|||
}).inject(self.profile_select) |
|||
}); |
|||
|
|||
self.options_el.addClass('set'); |
|||
|
|||
if(categories.length == 0 && self.title_select.getElements('option').length == 1 && profiles.length == 1 && |
|||
!(self.info.in_wanted && self.info.in_wanted.profile_id || in_library)) |
|||
self.add(); |
|||
|
|||
} |
|||
|
|||
}, |
|||
|
|||
loadingMask: function(){ |
|||
var self = this; |
|||
|
|||
self.mask = new Element('div.mask').inject(self.el).fade('hide') |
|||
|
|||
createSpinner(self.mask) |
|||
self.mask.fade('in') |
|||
|
|||
}, |
|||
|
|||
toElement: function(){ |
|||
return this.el |
|||
} |
|||
|
|||
}); |
@ -0,0 +1,6 @@ |
|||
from .main import EpisodeLibraryPlugin |
|||
|
|||
def start(): |
|||
return EpisodeLibraryPlugin() |
|||
|
|||
config = [] |
@ -0,0 +1,266 @@ |
|||
from couchpotato import get_session |
|||
from couchpotato.core.event import addEvent, fireEventAsync, fireEvent |
|||
from couchpotato.core.helpers.encoding import toUnicode, simplifyString |
|||
from couchpotato.core.logger import CPLog |
|||
from couchpotato.core.settings.model import EpisodeLibrary, SeasonLibrary, LibraryTitle, File |
|||
from couchpotato.core.media._base.library.base import LibraryBase |
|||
from couchpotato.core.helpers.variable import tryInt |
|||
from string import ascii_letters |
|||
import time |
|||
import traceback |
|||
|
|||
log = CPLog(__name__) |
|||
|
|||
|
|||
class EpisodeLibraryPlugin(LibraryBase): |
|||
|
|||
default_dict = {'titles': {}, 'files':{}} |
|||
|
|||
def __init__(self): |
|||
addEvent('library.query', self.query) |
|||
addEvent('library.identifier', self.identifier) |
|||
addEvent('library.add.episode', self.add) |
|||
addEvent('library.update.episode', self.update) |
|||
addEvent('library.update.episode_release_date', self.updateReleaseDate) |
|||
|
|||
def query(self, library, first = True, condense = True, include_identifier = True, **kwargs): |
|||
if library is list or library.get('type') != 'episode': |
|||
return |
|||
|
|||
# Get the titles of the season |
|||
if not library.get('related_libraries', {}).get('season', []): |
|||
log.warning('Invalid library, unable to determine title.') |
|||
return |
|||
|
|||
titles = fireEvent( |
|||
'library.query', |
|||
library['related_libraries']['season'][0], |
|||
first=False, |
|||
include_identifier=include_identifier, |
|||
condense=condense, |
|||
|
|||
single=True |
|||
) |
|||
|
|||
identifier = fireEvent('library.identifier', library, single = True) |
|||
|
|||
# Add episode identifier to titles |
|||
if include_identifier and identifier.get('episode'): |
|||
titles = [title + ('E%02d' % identifier['episode']) for title in titles] |
|||
|
|||
|
|||
if first: |
|||
return titles[0] if titles else None |
|||
|
|||
return titles |
|||
|
|||
|
|||
def identifier(self, library): |
|||
if library.get('type') != 'episode': |
|||
return |
|||
|
|||
identifier = { |
|||
'season': None, |
|||
'episode': None |
|||
} |
|||
|
|||
scene_map = library['info'].get('map_episode', {}).get('scene') |
|||
|
|||
if scene_map: |
|||
# Use scene mappings if they are available |
|||
identifier['season'] = scene_map.get('season') |
|||
identifier['episode'] = scene_map.get('episode') |
|||
else: |
|||
# Fallback to normal season/episode numbers |
|||
identifier['season'] = library.get('season_number') |
|||
identifier['episode'] = library.get('episode_number') |
|||
|
|||
|
|||
# Cast identifiers to integers |
|||
# TODO this will need changing to support identifiers with trailing 'a', 'b' characters |
|||
identifier['season'] = tryInt(identifier['season'], None) |
|||
identifier['episode'] = tryInt(identifier['episode'], None) |
|||
|
|||
return identifier |
|||
|
|||
def add(self, attrs = {}, update_after = True): |
|||
type = attrs.get('type', 'episode') |
|||
primary_provider = attrs.get('primary_provider', 'thetvdb') |
|||
|
|||
db = get_session() |
|||
parent_identifier = attrs.get('parent_identifier', None) |
|||
|
|||
parent = None |
|||
if parent_identifier: |
|||
parent = db.query(SeasonLibrary).filter_by(primary_provider = primary_provider, identifier = attrs.get('parent_identifier')).first() |
|||
|
|||
l = db.query(EpisodeLibrary).filter_by(type = type, identifier = attrs.get('identifier')).first() |
|||
if not l: |
|||
status = fireEvent('status.get', 'needs_update', single = True) |
|||
l = EpisodeLibrary( |
|||
type = type, |
|||
primary_provider = primary_provider, |
|||
year = attrs.get('year'), |
|||
identifier = attrs.get('identifier'), |
|||
plot = toUnicode(attrs.get('plot')), |
|||
tagline = toUnicode(attrs.get('tagline')), |
|||
status_id = status.get('id'), |
|||
info = {}, |
|||
parent = parent, |
|||
season_number = tryInt(attrs.get('seasonnumber', None)), |
|||
episode_number = tryInt(attrs.get('episodenumber', None)), |
|||
absolute_number = tryInt(attrs.get('absolute_number', None)) |
|||
) |
|||
|
|||
title = LibraryTitle( |
|||
title = toUnicode(attrs.get('title')), |
|||
simple_title = self.simplifyTitle(attrs.get('title')), |
|||
) |
|||
|
|||
l.titles.append(title) |
|||
|
|||
db.add(l) |
|||
db.commit() |
|||
|
|||
# Update library info |
|||
if update_after is not False: |
|||
handle = fireEventAsync if update_after is 'async' else fireEvent |
|||
handle('library.update.episode', identifier = l.identifier, default_title = toUnicode(attrs.get('title', ''))) |
|||
|
|||
library_dict = l.to_dict(self.default_dict) |
|||
|
|||
db.expire_all() |
|||
return library_dict |
|||
|
|||
def update(self, identifier, default_title = '', force = False): |
|||
|
|||
if self.shuttingDown(): |
|||
return |
|||
|
|||
db = get_session() |
|||
library = db.query(EpisodeLibrary).filter_by(identifier = identifier).first() |
|||
done_status = fireEvent('status.get', 'done', single = True) |
|||
|
|||
if library: |
|||
library_dict = library.to_dict(self.default_dict) |
|||
|
|||
do_update = True |
|||
|
|||
parent_identifier = None |
|||
if library.parent is not None: |
|||
parent_identifier = library.parent.identifier |
|||
|
|||
if library.status_id == done_status.get('id') and not force: |
|||
do_update = False |
|||
|
|||
episode_params = {'season_identifier': parent_identifier, |
|||
'episode_identifier': identifier, |
|||
'episode': library.episode_number, |
|||
'absolute': library.absolute_number,} |
|||
info = fireEvent('episode.info', merge = True, params = episode_params) |
|||
|
|||
# Don't need those here |
|||
try: del info['in_wanted'] |
|||
except: pass |
|||
try: del info['in_library'] |
|||
except: pass |
|||
|
|||
if not info or len(info) == 0: |
|||
log.error('Could not update, no movie info to work with: %s', identifier) |
|||
return False |
|||
|
|||
# Main info |
|||
if do_update: |
|||
library.plot = toUnicode(info.get('plot', '')) |
|||
library.tagline = toUnicode(info.get('tagline', '')) |
|||
library.year = info.get('year', 0) |
|||
library.status_id = done_status.get('id') |
|||
library.season_number = tryInt(info.get('seasonnumber', None)) |
|||
library.episode_number = tryInt(info.get('episodenumber', None)) |
|||
library.absolute_number = tryInt(info.get('absolute_number', None)) |
|||
try: |
|||
library.last_updated = int(info.get('lastupdated')) |
|||
except: |
|||
library.last_updated = int(time.time()) |
|||
library.info.update(info) |
|||
db.commit() |
|||
|
|||
# Titles |
|||
[db.delete(title) for title in library.titles] |
|||
db.commit() |
|||
|
|||
titles = info.get('titles', []) |
|||
log.debug('Adding titles: %s', titles) |
|||
counter = 0 |
|||
for title in titles: |
|||
if not title: |
|||
continue |
|||
title = toUnicode(title) |
|||
t = LibraryTitle( |
|||
title = title, |
|||
simple_title = self.simplifyTitle(title), |
|||
default = (len(default_title) == 0 and counter == 0) or len(titles) == 1 or title.lower() == toUnicode(default_title.lower()) or (toUnicode(default_title) == u'' and toUnicode(titles[0]) == title) |
|||
) |
|||
library.titles.append(t) |
|||
counter += 1 |
|||
|
|||
db.commit() |
|||
|
|||
# Files |
|||
images = info.get('images', []) |
|||
for image_type in ['poster']: |
|||
for image in images.get(image_type, []): |
|||
if not isinstance(image, (str, unicode)): |
|||
continue |
|||
|
|||
file_path = fireEvent('file.download', url = image, single = True) |
|||
if file_path: |
|||
file_obj = fireEvent('file.add', path = file_path, type_tuple = ('image', image_type), single = True) |
|||
try: |
|||
file_obj = db.query(File).filter_by(id = file_obj.get('id')).one() |
|||
library.files.append(file_obj) |
|||
db.commit() |
|||
|
|||
break |
|||
except: |
|||
log.debug('Failed to attach to library: %s', traceback.format_exc()) |
|||
|
|||
library_dict = library.to_dict(self.default_dict) |
|||
db.expire_all() |
|||
return library_dict |
|||
|
|||
def updateReleaseDate(self, identifier): |
|||
'''XXX: Not sure what this is for yet in relation to an episode''' |
|||
pass |
|||
#db = get_session() |
|||
#library = db.query(EpisodeLibrary).filter_by(identifier = identifier).first() |
|||
|
|||
#if not library.info: |
|||
#library_dict = self.update(identifier, force = True) |
|||
#dates = library_dict.get('info', {}).get('release_date') |
|||
#else: |
|||
#dates = library.info.get('release_date') |
|||
|
|||
#if dates and dates.get('expires', 0) < time.time() or not dates: |
|||
#dates = fireEvent('movie.release_date', identifier = identifier, merge = True) |
|||
#library.info.update({'release_date': dates }) |
|||
#db.commit() |
|||
|
|||
#db.expire_all() |
|||
#return dates |
|||
|
|||
|
|||
#TODO: Add to base class |
|||
def simplifyTitle(self, title): |
|||
|
|||
title = toUnicode(title) |
|||
|
|||
nr_prefix = '' if title[0] in ascii_letters else '#' |
|||
title = simplifyString(title) |
|||
|
|||
for prefix in ['the ']: |
|||
if prefix == title[:len(prefix)]: |
|||
title = title[len(prefix):] |
|||
break |
|||
|
|||
return nr_prefix + title |
@ -0,0 +1,6 @@ |
|||
from .main import SeasonLibraryPlugin |
|||
|
|||
def start(): |
|||
return SeasonLibraryPlugin() |
|||
|
|||
config = [] |
@ -0,0 +1,242 @@ |
|||
from couchpotato import get_session |
|||
from couchpotato.core.event import addEvent, fireEventAsync, fireEvent |
|||
from couchpotato.core.helpers.encoding import toUnicode, simplifyString |
|||
from couchpotato.core.logger import CPLog |
|||
from couchpotato.core.settings.model import SeasonLibrary, ShowLibrary, LibraryTitle, File |
|||
from couchpotato.core.media._base.library.base import LibraryBase |
|||
from couchpotato.core.helpers.variable import tryInt |
|||
from string import ascii_letters |
|||
import time |
|||
import traceback |
|||
|
|||
log = CPLog(__name__) |
|||
|
|||
|
|||
class SeasonLibraryPlugin(LibraryBase): |
|||
|
|||
default_dict = {'titles': {}, 'files':{}} |
|||
|
|||
def __init__(self): |
|||
addEvent('library.query', self.query) |
|||
addEvent('library.identifier', self.identifier) |
|||
addEvent('library.add.season', self.add) |
|||
addEvent('library.update.season', self.update) |
|||
addEvent('library.update.season_release_date', self.updateReleaseDate) |
|||
|
|||
def query(self, library, first = True, condense = True, include_identifier = True, **kwargs): |
|||
if library is list or library.get('type') != 'season': |
|||
return |
|||
|
|||
# Get the titles of the show |
|||
if not library.get('related_libraries', {}).get('show', []): |
|||
log.warning('Invalid library, unable to determine title.') |
|||
return |
|||
|
|||
titles = fireEvent( |
|||
'library.query', |
|||
library['related_libraries']['show'][0], |
|||
first=False, |
|||
condense=condense, |
|||
|
|||
single=True |
|||
) |
|||
|
|||
# Add season map_names if they exist |
|||
if 'map_names' in library['info']: |
|||
season_names = library['info']['map_names'].get(str(library['season_number']), {}) |
|||
|
|||
# Add titles from all locations |
|||
# TODO only add name maps from a specific location |
|||
for location, names in season_names.items(): |
|||
titles += [name for name in names if name and name not in titles] |
|||
|
|||
|
|||
identifier = fireEvent('library.identifier', library, single = True) |
|||
|
|||
# Add season identifier to titles |
|||
if include_identifier and identifier.get('season') is not None: |
|||
titles = [title + (' S%02d' % identifier['season']) for title in titles] |
|||
|
|||
|
|||
if first: |
|||
return titles[0] if titles else None |
|||
|
|||
return titles |
|||
|
|||
def identifier(self, library): |
|||
if library.get('type') != 'season': |
|||
return |
|||
|
|||
return { |
|||
'season': tryInt(library['season_number'], None) |
|||
} |
|||
|
|||
def add(self, attrs = {}, update_after = True): |
|||
type = attrs.get('type', 'season') |
|||
primary_provider = attrs.get('primary_provider', 'thetvdb') |
|||
|
|||
db = get_session() |
|||
parent_identifier = attrs.get('parent_identifier', None) |
|||
|
|||
parent = None |
|||
if parent_identifier: |
|||
parent = db.query(ShowLibrary).filter_by(primary_provider = primary_provider, identifier = attrs.get('parent_identifier')).first() |
|||
|
|||
l = db.query(SeasonLibrary).filter_by(type = type, identifier = attrs.get('identifier')).first() |
|||
if not l: |
|||
status = fireEvent('status.get', 'needs_update', single = True) |
|||
l = SeasonLibrary( |
|||
type = type, |
|||
primary_provider = primary_provider, |
|||
year = attrs.get('year'), |
|||
identifier = attrs.get('identifier'), |
|||
plot = toUnicode(attrs.get('plot')), |
|||
tagline = toUnicode(attrs.get('tagline')), |
|||
status_id = status.get('id'), |
|||
info = {}, |
|||
parent = parent, |
|||
) |
|||
|
|||
title = LibraryTitle( |
|||
title = toUnicode(attrs.get('title')), |
|||
simple_title = self.simplifyTitle(attrs.get('title')), |
|||
) |
|||
|
|||
l.titles.append(title) |
|||
|
|||
db.add(l) |
|||
db.commit() |
|||
|
|||
# Update library info |
|||
if update_after is not False: |
|||
handle = fireEventAsync if update_after is 'async' else fireEvent |
|||
handle('library.update.season', identifier = l.identifier, default_title = toUnicode(attrs.get('title', ''))) |
|||
|
|||
library_dict = l.to_dict(self.default_dict) |
|||
db.expire_all() |
|||
return library_dict |
|||
|
|||
def update(self, identifier, default_title = '', force = False): |
|||
|
|||
if self.shuttingDown(): |
|||
return |
|||
|
|||
db = get_session() |
|||
library = db.query(SeasonLibrary).filter_by(identifier = identifier).first() |
|||
done_status = fireEvent('status.get', 'done', single = True) |
|||
|
|||
if library: |
|||
library_dict = library.to_dict(self.default_dict) |
|||
|
|||
do_update = True |
|||
|
|||
parent_identifier = None |
|||
if library.parent is not None: |
|||
parent_identifier = library.parent.identifier |
|||
|
|||
if library.status_id == done_status.get('id') and not force: |
|||
do_update = False |
|||
|
|||
season_params = {'season_identifier': identifier} |
|||
info = fireEvent('season.info', merge = True, identifier = parent_identifier, params = season_params) |
|||
|
|||
# Don't need those here |
|||
try: del info['in_wanted'] |
|||
except: pass |
|||
try: del info['in_library'] |
|||
except: pass |
|||
|
|||
if not info or len(info) == 0: |
|||
log.error('Could not update, no movie info to work with: %s', identifier) |
|||
return False |
|||
|
|||
# Main info |
|||
if do_update: |
|||
library.plot = toUnicode(info.get('plot', '')) |
|||
library.tagline = toUnicode(info.get('tagline', '')) |
|||
library.year = info.get('year', 0) |
|||
library.status_id = done_status.get('id') |
|||
library.season_number = tryInt(info.get('seasonnumber', None)) |
|||
library.info.update(info) |
|||
db.commit() |
|||
|
|||
# Titles |
|||
[db.delete(title) for title in library.titles] |
|||
db.commit() |
|||
|
|||
titles = info.get('titles', []) |
|||
log.debug('Adding titles: %s', titles) |
|||
counter = 0 |
|||
for title in titles: |
|||
if not title: |
|||
continue |
|||
title = toUnicode(title) |
|||
t = LibraryTitle( |
|||
title = title, |
|||
simple_title = self.simplifyTitle(title), |
|||
# XXX: default was None; so added a quick hack since we don't really need titiles for seasons anyway |
|||
#default = (len(default_title) == 0 and counter == 0) or len(titles) == 1 or title.lower() == toUnicode(default_title.lower()) or (toUnicode(default_title) == u'' and toUnicode(titles[0]) == title) |
|||
default = True, |
|||
) |
|||
library.titles.append(t) |
|||
counter += 1 |
|||
|
|||
db.commit() |
|||
|
|||
# Files |
|||
images = info.get('images', []) |
|||
for image_type in ['poster']: |
|||
for image in images.get(image_type, []): |
|||
if not isinstance(image, (str, unicode)): |
|||
continue |
|||
|
|||
file_path = fireEvent('file.download', url = image, single = True) |
|||
if file_path: |
|||
file_obj = fireEvent('file.add', path = file_path, type_tuple = ('image', image_type), single = True) |
|||
try: |
|||
file_obj = db.query(File).filter_by(id = file_obj.get('id')).one() |
|||
library.files.append(file_obj) |
|||
db.commit() |
|||
break |
|||
except: |
|||
log.debug('Failed to attach to library: %s', traceback.format_exc()) |
|||
|
|||
library_dict = library.to_dict(self.default_dict) |
|||
db.expire_all() |
|||
return library_dict |
|||
|
|||
def updateReleaseDate(self, identifier): |
|||
'''XXX: Not sure what this is for yet in relation to a tvshow''' |
|||
pass |
|||
#db = get_session() |
|||
#library = db.query(SeasonLibrary).filter_by(identifier = identifier).first() |
|||
|
|||
#if not library.info: |
|||
#library_dict = self.update(identifier, force = True) |
|||
#dates = library_dict.get('info', {}).get('release_date') |
|||
#else: |
|||
#dates = library.info.get('release_date') |
|||
|
|||
#if dates and dates.get('expires', 0) < time.time() or not dates: |
|||
#dates = fireEvent('movie.release_date', identifier = identifier, merge = True) |
|||
#library.info.update({'release_date': dates }) |
|||
#db.commit() |
|||
|
|||
#db.expire_all() |
|||
#return dates |
|||
|
|||
|
|||
#TODO: Add to base class |
|||
def simplifyTitle(self, title): |
|||
|
|||
title = toUnicode(title) |
|||
|
|||
nr_prefix = '' if title[0] in ascii_letters else '#' |
|||
title = simplifyString(title) |
|||
|
|||
for prefix in ['the ']: |
|||
if prefix == title[:len(prefix)]: |
|||
title = title[len(prefix):] |
|||
break |
|||
|
|||
return nr_prefix + title |
@ -0,0 +1,6 @@ |
|||
from .main import ShowLibraryPlugin |
|||
|
|||
def start(): |
|||
return ShowLibraryPlugin() |
|||
|
|||
config = [] |
@ -0,0 +1,229 @@ |
|||
from couchpotato import get_session |
|||
from couchpotato.core.event import addEvent, fireEventAsync, fireEvent |
|||
from couchpotato.core.helpers.encoding import toUnicode, simplifyString |
|||
from couchpotato.core.logger import CPLog |
|||
from couchpotato.core.settings.model import ShowLibrary, LibraryTitle, File |
|||
from couchpotato.core.media._base.library.base import LibraryBase |
|||
from qcond.helpers import simplify |
|||
from qcond import QueryCondenser |
|||
from string import ascii_letters |
|||
import time |
|||
import traceback |
|||
|
|||
log = CPLog(__name__) |
|||
|
|||
|
|||
class ShowLibraryPlugin(LibraryBase): |
|||
|
|||
default_dict = {'titles': {}, 'files':{}} |
|||
|
|||
def __init__(self): |
|||
self.query_condenser = QueryCondenser() |
|||
|
|||
addEvent('library.query', self.query) |
|||
addEvent('library.add.show', self.add) |
|||
addEvent('library.update.show', self.update) |
|||
addEvent('library.update.show_release_date', self.updateReleaseDate) |
|||
|
|||
def query(self, library, first = True, condense = True, **kwargs): |
|||
if library is list or library.get('type') != 'show': |
|||
return |
|||
|
|||
titles = [title['title'] for title in library['titles']] |
|||
|
|||
if condense: |
|||
# Use QueryCondenser to build a list of optimal search titles |
|||
condensed_titles = self.query_condenser.distinct(titles) |
|||
|
|||
if condensed_titles: |
|||
# Use condensed titles if we got a valid result |
|||
titles = condensed_titles |
|||
else: |
|||
# Fallback to simplifying titles |
|||
titles = [simplify(title) for title in titles] |
|||
|
|||
if first: |
|||
return titles[0] if titles else None |
|||
|
|||
return titles |
|||
|
|||
def add(self, attrs = {}, update_after = True): |
|||
type = attrs.get('type', 'show') |
|||
primary_provider = attrs.get('primary_provider', 'thetvdb') |
|||
|
|||
db = get_session() |
|||
|
|||
l = db.query(ShowLibrary).filter_by(type = type, identifier = attrs.get('identifier')).first() |
|||
if not l: |
|||
status = fireEvent('status.get', 'needs_update', single = True) |
|||
l = ShowLibrary( |
|||
type = type, |
|||
primary_provider = primary_provider, |
|||
year = attrs.get('year'), |
|||
identifier = attrs.get('identifier'), |
|||
plot = toUnicode(attrs.get('plot')), |
|||
tagline = toUnicode(attrs.get('tagline')), |
|||
status_id = status.get('id'), |
|||
info = {}, |
|||
parent = None, |
|||
) |
|||
|
|||
title = LibraryTitle( |
|||
title = toUnicode(attrs.get('title')), |
|||
simple_title = self.simplifyTitle(attrs.get('title')), |
|||
) |
|||
|
|||
l.titles.append(title) |
|||
|
|||
db.add(l) |
|||
db.commit() |
|||
|
|||
# Update library info |
|||
if update_after is not False: |
|||
handle = fireEventAsync if update_after is 'async' else fireEvent |
|||
handle('library.update.show', identifier = l.identifier, default_title = toUnicode(attrs.get('title', ''))) |
|||
|
|||
library_dict = l.to_dict(self.default_dict) |
|||
db.expire_all() |
|||
return library_dict |
|||
|
|||
def update(self, identifier, default_title = '', force = False): |
|||
|
|||
if self.shuttingDown(): |
|||
return |
|||
|
|||
db = get_session() |
|||
library = db.query(ShowLibrary).filter_by(identifier = identifier).first() |
|||
done_status = fireEvent('status.get', 'done', single = True) |
|||
|
|||
if library: |
|||
library_dict = library.to_dict(self.default_dict) |
|||
|
|||
do_update = True |
|||
|
|||
info = fireEvent('show.info', merge = True, identifier = identifier) |
|||
|
|||
# Don't need those here |
|||
try: del info['in_wanted'] |
|||
except: pass |
|||
try: del info['in_library'] |
|||
except: pass |
|||
|
|||
if not info or len(info) == 0: |
|||
log.error('Could not update, no show info to work with: %s', identifier) |
|||
return False |
|||
|
|||
# Main info |
|||
if do_update: |
|||
library.plot = toUnicode(info.get('plot', '')) |
|||
library.tagline = toUnicode(info.get('tagline', '')) |
|||
library.year = info.get('year', 0) |
|||
library.status_id = done_status.get('id') |
|||
library.show_status = toUnicode(info.get('status', '').lower()) |
|||
library.airs_time = info.get('airs_time', None) |
|||
|
|||
# Bits |
|||
days_of_week_map = { |
|||
u'Monday': 1, |
|||
u'Tuesday': 2, |
|||
u'Wednesday': 4, |
|||
u'Thursday': 8, |
|||
u'Friday': 16, |
|||
u'Saturday': 32, |
|||
u'Sunday': 64, |
|||
u'Daily': 127, |
|||
} |
|||
try: |
|||
library.airs_dayofweek = days_of_week_map.get(info.get('airs_dayofweek')) |
|||
except: |
|||
library.airs_dayofweek = 0 |
|||
|
|||
try: |
|||
library.last_updated = int(info.get('lastupdated')) |
|||
except: |
|||
library.last_updated = int(time.time()) |
|||
|
|||
library.info.update(info) |
|||
|
|||
db.commit() |
|||
|
|||
# Titles |
|||
[db.delete(title) for title in library.titles] |
|||
db.commit() |
|||
|
|||
titles = info.get('titles', []) |
|||
log.debug('Adding titles: %s', titles) |
|||
counter = 0 |
|||
for title in titles: |
|||
if not title: |
|||
continue |
|||
title = toUnicode(title) |
|||
t = LibraryTitle( |
|||
title = title, |
|||
simple_title = self.simplifyTitle(title), |
|||
default = (len(default_title) == 0 and counter == 0) or len(titles) == 1 or title.lower() == toUnicode(default_title.lower()) or (toUnicode(default_title) == u'' and toUnicode(titles[0]) == title) |
|||
) |
|||
library.titles.append(t) |
|||
counter += 1 |
|||
|
|||
db.commit() |
|||
|
|||
# Files |
|||
images = info.get('images', []) |
|||
for image_type in ['poster']: |
|||
for image in images.get(image_type, []): |
|||
if not isinstance(image, (str, unicode)): |
|||
continue |
|||
|
|||
file_path = fireEvent('file.download', url = image, single = True) |
|||
if file_path: |
|||
file_obj = fireEvent('file.add', path = file_path, type_tuple = ('image', image_type), single = True) |
|||
try: |
|||
file_obj = db.query(File).filter_by(id = file_obj.get('id')).one() |
|||
library.files.append(file_obj) |
|||
db.commit() |
|||
|
|||
break |
|||
except: |
|||
log.debug('Failed to attach to library: %s', traceback.format_exc()) |
|||
|
|||
library_dict = library.to_dict(self.default_dict) |
|||
|
|||
db.expire_all() |
|||
return library_dict |
|||
|
|||
def updateReleaseDate(self, identifier): |
|||
'''XXX: Not sure what this is for yet in relation to a show''' |
|||
pass |
|||
#db = get_session() |
|||
#library = db.query(ShowLibrary).filter_by(identifier = identifier).first() |
|||
|
|||
#if not library.info: |
|||
#library_dict = self.update(identifier, force = True) |
|||
#dates = library_dict.get('info', {}).get('release_date') |
|||
#else: |
|||
#dates = library.info.get('release_date') |
|||
|
|||
#if dates and dates.get('expires', 0) < time.time() or not dates: |
|||
#dates = fireEvent('movie.release_date', identifier = identifier, merge = True) |
|||
#library.info.update({'release_date': dates }) |
|||
#db.commit() |
|||
|
|||
#db.expire_all() |
|||
#return dates |
|||
|
|||
|
|||
#TODO: Add to base class |
|||
def simplifyTitle(self, title): |
|||
|
|||
title = toUnicode(title) |
|||
|
|||
nr_prefix = '' if title[0] in ascii_letters else '#' |
|||
title = simplifyString(title) |
|||
|
|||
for prefix in ['the ']: |
|||
if prefix == title[:len(prefix)]: |
|||
title = title[len(prefix):] |
|||
break |
|||
|
|||
return nr_prefix + title |
@ -0,0 +1,6 @@ |
|||
from .main import ShowMatcher |
|||
|
|||
def start(): |
|||
return ShowMatcher() |
|||
|
|||
config = [] |
@ -0,0 +1,127 @@ |
|||
from couchpotato import CPLog |
|||
from couchpotato.core.event import addEvent, fireEvent |
|||
from couchpotato.core.helpers.variable import dictIsSubset, tryInt, toIterable |
|||
from couchpotato.core.media._base.matcher.base import MatcherBase |
|||
from couchpotato.core.providers.base import MultiProvider |
|||
|
|||
log = CPLog(__name__) |
|||
|
|||
|
|||
class ShowMatcher(MultiProvider): |
|||
|
|||
def getTypes(self): |
|||
return [Season, Episode] |
|||
|
|||
|
|||
class Base(MatcherBase): |
|||
# TODO come back to this later, think this could be handled better, this is starting to get out of hand.... |
|||
quality_map = { |
|||
'bluray_1080p': {'resolution': ['1080p'], 'source': ['bluray']}, |
|||
'bluray_720p': {'resolution': ['720p'], 'source': ['bluray']}, |
|||
|
|||
'bdrip_1080p': {'resolution': ['1080p'], 'source': ['BDRip']}, |
|||
'bdrip_720p': {'resolution': ['720p'], 'source': ['BDRip']}, |
|||
|
|||
'brrip_1080p': {'resolution': ['1080p'], 'source': ['BRRip']}, |
|||
'brrip_720p': {'resolution': ['720p'], 'source': ['BRRip']}, |
|||
|
|||
'webdl_1080p': {'resolution': ['1080p'], 'source': ['webdl', ['web', 'dl']]}, |
|||
'webdl_720p': {'resolution': ['720p'], 'source': ['webdl', ['web', 'dl']]}, |
|||
'webdl_480p': {'resolution': ['480p'], 'source': ['webdl', ['web', 'dl']]}, |
|||
|
|||
'hdtv_720p': {'resolution': ['720p'], 'source': ['hdtv']}, |
|||
'hdtv_sd': {'resolution': ['480p', None], 'source': ['hdtv']}, |
|||
} |
|||
|
|||
def __init__(self): |
|||
super(Base, self).__init__() |
|||
|
|||
addEvent('%s.matcher.correct_identifier' % self.type, self.correctIdentifier) |
|||
|
|||
def correct(self, chain, release, media, quality): |
|||
log.info("Checking if '%s' is valid", release['name']) |
|||
log.info2('Release parsed as: %s', chain.info) |
|||
|
|||
if not fireEvent('matcher.correct_quality', chain, quality, self.quality_map, single = True): |
|||
log.info('Wrong: %s, quality does not match', release['name']) |
|||
return False |
|||
|
|||
if not fireEvent('%s.matcher.correct_identifier' % self.type, chain, media): |
|||
log.info('Wrong: %s, identifier does not match', release['name']) |
|||
return False |
|||
|
|||
if not fireEvent('matcher.correct_title', chain, media): |
|||
log.info("Wrong: '%s', undetermined naming.", (' '.join(chain.info['show_name']))) |
|||
return False |
|||
|
|||
return True |
|||
|
|||
def correctIdentifier(self, chain, media): |
|||
raise NotImplementedError() |
|||
|
|||
def getChainIdentifier(self, chain): |
|||
if 'identifier' not in chain.info: |
|||
return None |
|||
|
|||
identifier = self.flattenInfo(chain.info['identifier']) |
|||
|
|||
# Try cast values to integers |
|||
for key, value in identifier.items(): |
|||
if isinstance(value, list): |
|||
if len(value) <= 1: |
|||
value = value[0] |
|||
else: |
|||
log.warning('Wrong: identifier contains multiple season or episode values, unsupported') |
|||
return None |
|||
|
|||
identifier[key] = tryInt(value, value) |
|||
|
|||
return identifier |
|||
|
|||
|
|||
class Episode(Base): |
|||
type = 'episode' |
|||
|
|||
def correctIdentifier(self, chain, media): |
|||
identifier = self.getChainIdentifier(chain) |
|||
if not identifier: |
|||
log.info2('Wrong: release identifier is not valid (unsupported or missing identifier)') |
|||
return False |
|||
|
|||
# TODO - Parse episode ranges from identifier to determine if they are multi-part episodes |
|||
if any([x in identifier for x in ['episode_from', 'episode_to']]): |
|||
log.info2('Wrong: releases with identifier ranges are not supported yet') |
|||
return False |
|||
|
|||
required = fireEvent('library.identifier', media['library'], single = True) |
|||
|
|||
# TODO - Support air by date episodes |
|||
# TODO - Support episode parts |
|||
|
|||
if identifier != required: |
|||
log.info2('Wrong: required identifier (%s) does not match release identifier (%s)', (required, identifier)) |
|||
return False |
|||
|
|||
return True |
|||
|
|||
class Season(Base): |
|||
type = 'season' |
|||
|
|||
def correctIdentifier(self, chain, media): |
|||
identifier = self.getChainIdentifier(chain) |
|||
if not identifier: |
|||
log.info2('Wrong: release identifier is not valid (unsupported or missing identifier)') |
|||
return False |
|||
|
|||
# TODO - Parse episode ranges from identifier to determine if they are season packs |
|||
if any([x in identifier for x in ['episode_from', 'episode_to']]): |
|||
log.info2('Wrong: releases with identifier ranges are not supported yet') |
|||
return False |
|||
|
|||
required = fireEvent('library.identifier', media['library'], single = True) |
|||
|
|||
if identifier != required: |
|||
log.info2('Wrong: required identifier (%s) does not match release identifier (%s)', (required, identifier)) |
|||
return False |
|||
|
|||
return True |
@ -0,0 +1,7 @@ |
|||
from .main import ShowSearcher |
|||
import random |
|||
|
|||
def start(): |
|||
return ShowSearcher() |
|||
|
|||
config = [] |
@ -0,0 +1,189 @@ |
|||
from couchpotato import Env, get_session |
|||
from couchpotato.core.event import addEvent, fireEvent |
|||
from couchpotato.core.helpers.variable import getTitle, toIterable |
|||
from couchpotato.core.logger import CPLog |
|||
from couchpotato.core.media._base.searcher.main import SearchSetupError |
|||
from couchpotato.core.media.show._base import ShowBase |
|||
from couchpotato.core.plugins.base import Plugin |
|||
from couchpotato.core.settings.model import Media |
|||
from qcond import QueryCondenser |
|||
from qcond.helpers import simplify |
|||
|
|||
log = CPLog(__name__) |
|||
|
|||
|
|||
class ShowSearcher(Plugin): |
|||
|
|||
type = ['show', 'season', 'episode'] |
|||
|
|||
in_progress = False |
|||
|
|||
def __init__(self): |
|||
super(ShowSearcher, self).__init__() |
|||
|
|||
self.query_condenser = QueryCondenser() |
|||
|
|||
for type in toIterable(self.type): |
|||
addEvent('%s.searcher.single' % type, self.single) |
|||
|
|||
addEvent('searcher.correct_release', self.correctRelease) |
|||
|
|||
def single(self, media, search_protocols = None, manual = False): |
|||
show, season, episode = self.getLibraries(media['library']) |
|||
|
|||
db = get_session() |
|||
|
|||
if media['type'] == 'show': |
|||
for library in season: |
|||
# TODO ideally we shouldn't need to fetch the media for each season library here |
|||
m = db.query(Media).filter_by(library_id = library['library_id']).first() |
|||
|
|||
fireEvent('season.searcher.single', m.to_dict(ShowBase.search_dict)) |
|||
|
|||
return |
|||
|
|||
# Find out search type |
|||
try: |
|||
if not search_protocols: |
|||
search_protocols = fireEvent('searcher.protocols', single = True) |
|||
except SearchSetupError: |
|||
return |
|||
|
|||
done_status, available_status, ignored_status, failed_status = fireEvent('status.get', ['done', 'available', 'ignored', 'failed'], single = True) |
|||
|
|||
if not media['profile'] or media['status_id'] == done_status.get('id'): |
|||
log.debug('Episode doesn\'t have a profile or already done, assuming in manage tab.') |
|||
return |
|||
|
|||
#pre_releases = fireEvent('quality.pre_releases', single = True) |
|||
|
|||
found_releases = [] |
|||
too_early_to_search = [] |
|||
|
|||
default_title = fireEvent('library.query', media['library'], condense = False, single=True) |
|||
if not default_title: |
|||
log.error('No proper info found for episode, removing it from library to cause it from having more issues.') |
|||
#fireEvent('episode.delete', episode['id'], single = True) |
|||
return |
|||
|
|||
if not show or not season: |
|||
log.error('Unable to find show or season library in database, missing required data for searching') |
|||
return |
|||
|
|||
fireEvent('notify.frontend', type = 'show.searcher.started.%s' % media['id'], data = True, message = 'Searching for "%s"' % default_title) |
|||
|
|||
ret = False |
|||
has_better_quality = None |
|||
|
|||
for quality_type in media['profile']['types']: |
|||
# TODO check air date? |
|||
#if not self.conf('always_search') and not self.couldBeReleased(quality_type['quality']['identifier'] in pre_releases, release_dates, movie['library']['year']): |
|||
# too_early_to_search.append(quality_type['quality']['identifier']) |
|||
# continue |
|||
|
|||
has_better_quality = 0 |
|||
|
|||
# See if better quality is available |
|||
for release in media['releases']: |
|||
if release['quality']['order'] <= quality_type['quality']['order'] and release['status_id'] not in [available_status.get('id'), ignored_status.get('id'), failed_status.get('id')]: |
|||
has_better_quality += 1 |
|||
|
|||
# Don't search for quality lower then already available. |
|||
if has_better_quality is 0: |
|||
|
|||
log.info('Search for %s S%02d%s in %s', ( |
|||
getTitle(show), |
|||
season['season_number'], |
|||
"E%02d" % episode['episode_number'] if episode and len(episode) == 1 else "", |
|||
quality_type['quality']['label']) |
|||
) |
|||
quality = fireEvent('quality.single', identifier = quality_type['quality']['identifier'], single = True) |
|||
|
|||
results = fireEvent('searcher.search', search_protocols, media, quality, single = True) |
|||
if len(results) == 0: |
|||
log.debug('Nothing found for %s in %s', (default_title, quality_type['quality']['label'])) |
|||
|
|||
# Check if movie isn't deleted while searching |
|||
if not db.query(Media).filter_by(id = media.get('id')).first(): |
|||
break |
|||
|
|||
# Add them to this movie releases list |
|||
found_releases += fireEvent('release.create_from_search', results, media, quality_type, single = True) |
|||
|
|||
# Try find a valid result and download it |
|||
if fireEvent('release.try_download_result', results, media, quality_type, manual, single = True): |
|||
ret = True |
|||
|
|||
# Remove releases that aren't found anymore |
|||
for release in media.get('releases', []): |
|||
if release.get('status_id') == available_status.get('id') and release.get('identifier') not in found_releases: |
|||
fireEvent('release.delete', release.get('id'), single = True) |
|||
else: |
|||
log.info('Better quality (%s) already available or snatched for %s', (quality_type['quality']['label'], default_title)) |
|||
fireEvent('media.restatus', media['id']) |
|||
break |
|||
|
|||
# Break if CP wants to shut down |
|||
if self.shuttingDown() or ret: |
|||
break |
|||
|
|||
if len(too_early_to_search) > 0: |
|||
log.info2('Too early to search for %s, %s', (too_early_to_search, default_title)) |
|||
elif media['type'] == 'season' and not ret and has_better_quality is 0: |
|||
# If nothing was found, start searching for episodes individually |
|||
log.info('No season pack found, starting individual episode search') |
|||
|
|||
for library in episode: |
|||
# TODO ideally we shouldn't need to fetch the media for each episode library here |
|||
m = db.query(Media).filter_by(library_id = library['library_id']).first() |
|||
|
|||
fireEvent('episode.searcher.single', m.to_dict(ShowBase.search_dict)) |
|||
|
|||
|
|||
fireEvent('notify.frontend', type = 'show.searcher.ended.%s' % media['id'], data = True) |
|||
|
|||
return ret |
|||
|
|||
def correctRelease(self, release = None, media = None, quality = None, **kwargs): |
|||
|
|||
if media.get('type') not in ['season', 'episode']: return |
|||
|
|||
retention = Env.setting('retention', section = 'nzb') |
|||
|
|||
if release.get('seeders') is None and 0 < retention < release.get('age', 0): |
|||
log.info2('Wrong: Outside retention, age is %s, needs %s or lower: %s', (release['age'], retention, release['name'])) |
|||
return False |
|||
|
|||
# Check for required and ignored words |
|||
if not fireEvent('searcher.correct_words', release['name'], media, single = True): |
|||
return False |
|||
|
|||
# TODO Matching is quite costly, maybe we should be caching release matches somehow? (also look at caper optimizations) |
|||
match = fireEvent('matcher.match', release, media, quality, single = True) |
|||
if match: |
|||
return match.weight |
|||
|
|||
return False |
|||
|
|||
def getLibraries(self, library): |
|||
if 'related_libraries' not in library: |
|||
log.warning("'related_libraries' missing from media library, unable to continue searching") |
|||
return None, None, None |
|||
|
|||
libraries = library['related_libraries'] |
|||
|
|||
# Show always collapses as there can never be any multiples |
|||
show = libraries.get('show', []) |
|||
show = show[0] if len(show) else None |
|||
|
|||
# Season collapses if the subject is a season or episode |
|||
season = libraries.get('season', []) |
|||
if library['type'] in ['season', 'episode']: |
|||
season = season[0] if len(season) else None |
|||
|
|||
# Episode collapses if the subject is a episode |
|||
episode = libraries.get('episode', []) |
|||
if library['type'] == 'episode': |
|||
episode = episode[0] if len(episode) else None |
|||
|
|||
return show, season, episode |
@ -1,7 +1,7 @@ |
|||
from .main import MovieResultModifier |
|||
from .main import InfoResultModifier |
|||
|
|||
def start(): |
|||
|
|||
return MovieResultModifier() |
|||
return InfoResultModifier() |
|||
|
|||
config = [] |
|||
|
@ -0,0 +1,24 @@ |
|||
from .main import TheTVDb |
|||
|
|||
def start(): |
|||
return TheTVDb() |
|||
|
|||
config = [{ |
|||
'name': 'thetvdb', |
|||
'groups': [ |
|||
{ |
|||
'tab': 'providers', |
|||
'name': 'tmdb', |
|||
'label': 'TheTVDB', |
|||
'hidden': True, |
|||
'description': 'Used for all calls to TheTVDB.', |
|||
'options': [ |
|||
{ |
|||
'name': 'api_key', |
|||
'default': '7966C02F860586D2', |
|||
'label': 'Api Key', |
|||
}, |
|||
], |
|||
}, |
|||
], |
|||
}] |
@ -0,0 +1,468 @@ |
|||
from couchpotato.core.event import addEvent |
|||
from couchpotato.core.helpers.encoding import simplifyString, toUnicode |
|||
from couchpotato.core.logger import CPLog |
|||
from couchpotato.core.providers.info.base import ShowProvider |
|||
from couchpotato.environment import Env |
|||
from tvdb_api import tvdb_api, tvdb_exceptions |
|||
from datetime import datetime |
|||
import traceback |
|||
import os |
|||
|
|||
log = CPLog(__name__) |
|||
|
|||
# TODO: Consider grabbing zips to put less strain on tvdb |
|||
# TODO: Unicode stuff (check) |
|||
# TODO: Notigy frontend on error (tvdb down at monent) |
|||
# TODO: Expose apikey in setting so it can be changed by user |
|||
|
|||
class TheTVDb(ShowProvider): |
|||
|
|||
def __init__(self): |
|||
addEvent('info.search', self.search, priority = 1) |
|||
addEvent('show.search', self.search, priority = 1) |
|||
addEvent('show.info', self.getShowInfo, priority = 1) |
|||
addEvent('season.info', self.getSeasonInfo, priority = 1) |
|||
addEvent('episode.info', self.getEpisodeInfo, priority = 1) |
|||
|
|||
self.tvdb_api_parms = { |
|||
'apikey': self.conf('api_key'), |
|||
'banners': True, |
|||
'language': 'en', |
|||
'cache': os.path.join(Env.get('cache_dir'), 'thetvdb_api'), |
|||
} |
|||
self._setup() |
|||
|
|||
def _setup(self): |
|||
self.tvdb = tvdb_api.Tvdb(**self.tvdb_api_parms) |
|||
self.valid_languages = self.tvdb.config['valid_languages'] |
|||
|
|||
def search(self, q, limit = 12, language = 'en'): |
|||
''' Find show by name |
|||
show = { 'id': 74713, |
|||
'language': 'en', |
|||
'lid': 7, |
|||
'seriesid': '74713', |
|||
'seriesname': u'Breaking Bad',} |
|||
''' |
|||
|
|||
if self.isDisabled(): |
|||
return False |
|||
|
|||
if language != self.tvdb_api_parms['language'] and language in self.valid_languages: |
|||
self.tvdb_api_parms['language'] = language |
|||
self._setup() |
|||
|
|||
search_string = simplifyString(q) |
|||
cache_key = 'thetvdb.cache.%s.%s' % (search_string, limit) |
|||
results = self.getCache(cache_key) |
|||
|
|||
if not results: |
|||
log.debug('Searching for show: %s', q) |
|||
raw = None |
|||
try: |
|||
raw = self.tvdb.search(search_string) |
|||
except (tvdb_exceptions.tvdb_error, IOError), e: |
|||
log.error('Failed searching TheTVDB for "%s": %s', (search_string, traceback.format_exc())) |
|||
return False |
|||
|
|||
results = [] |
|||
if raw: |
|||
try: |
|||
nr = 0 |
|||
for show_info in raw: |
|||
show = self.tvdb[int(show_info['id'])] |
|||
results.append(self._parseShow(show)) |
|||
nr += 1 |
|||
if nr == limit: |
|||
break |
|||
log.info('Found: %s', [result['titles'][0] + ' (' + str(result.get('year', 0)) + ')' for result in results]) |
|||
self.setCache(cache_key, results) |
|||
return results |
|||
except (tvdb_exceptions.tvdb_error, IOError), e: |
|||
log.error('Failed parsing TheTVDB for "%s": %s', (show, traceback.format_exc())) |
|||
return False |
|||
return results |
|||
|
|||
def getShow(self, identifier = None): |
|||
show = None |
|||
try: |
|||
log.debug('Getting show: %s', identifier) |
|||
show = self.tvdb[int(identifier)] |
|||
except (tvdb_exceptions.tvdb_error, IOError), e: |
|||
log.error('Failed to getShowInfo for show id "%s": %s', (identifier, traceback.format_exc())) |
|||
return None |
|||
|
|||
return show |
|||
|
|||
def getShowInfo(self, identifier = None): |
|||
if not identifier: |
|||
return None |
|||
|
|||
cache_key = 'thetvdb.cache.%s' % identifier |
|||
log.debug('Getting showInfo: %s', cache_key) |
|||
result = self.getCache(cache_key) or {} |
|||
if result: |
|||
return result |
|||
|
|||
show = self.getShow(identifier = identifier) |
|||
if show: |
|||
result = self._parseShow(show) |
|||
self.setCache(cache_key, result) |
|||
|
|||
return result |
|||
|
|||
def getSeasonInfo(self, identifier = None, params = {}): |
|||
"""Either return a list of all seasons or a single season by number. |
|||
identifier is the show 'id' |
|||
""" |
|||
if not identifier: |
|||
return False |
|||
|
|||
season_identifier = params.get('season_identifier', None) |
|||
|
|||
# season_identifier must contain the 'show id : season number' since there is no tvdb id |
|||
# for season and we need a reference to both the show id and season number |
|||
if season_identifier: |
|||
try: season_identifier = int(season_identifier.split(':')[1]) |
|||
except: return False |
|||
|
|||
cache_key = 'thetvdb.cache.%s.%s' % (identifier, season_identifier) |
|||
log.debug('Getting SeasonInfo: %s', cache_key) |
|||
result = self.getCache(cache_key) or {} |
|||
if result: |
|||
return result |
|||
|
|||
try: |
|||
show = self.tvdb[int(identifier)] |
|||
except (tvdb_exceptions.tvdb_error, IOError), e: |
|||
log.error('Failed parsing TheTVDB SeasonInfo for "%s" id "%s": %s', (show, identifier, traceback.format_exc())) |
|||
return False |
|||
|
|||
result = [] |
|||
for number, season in show.items(): |
|||
if season_identifier is not None and number == season_identifier: |
|||
result = self._parseSeason(show, (number, season)) |
|||
self.setCache(cache_key, result) |
|||
return result |
|||
else: |
|||
result.append(self._parseSeason(show, (number, season))) |
|||
|
|||
self.setCache(cache_key, result) |
|||
return result |
|||
|
|||
def getEpisodeInfo(self, identifier = None, params = {}): |
|||
"""Either return a list of all episodes or a single episode. |
|||
If episode_identifer contains an episode number to search for |
|||
""" |
|||
season_identifier = params.get('season_identifier', None) |
|||
episode_identifier = params.get('episode_identifier', None) |
|||
|
|||
if not identifier and season_identifier is None: |
|||
return False |
|||
|
|||
# season_identifier must contain the 'show id : season number' since there is no tvdb id |
|||
# for season and we need a reference to both the show id and season number |
|||
if season_identifier: |
|||
try: |
|||
identifier, season_identifier = season_identifier.split(':') |
|||
season_identifier = int(season_identifier) |
|||
except: return None |
|||
|
|||
cache_key = 'thetvdb.cache.%s.%s.%s' % (identifier, episode_identifier, season_identifier) |
|||
log.debug('Getting EpisodeInfo: %s', cache_key) |
|||
result = self.getCache(cache_key) or {} |
|||
if result: |
|||
return result |
|||
|
|||
try: |
|||
show = self.tvdb[int(identifier)] |
|||
except (tvdb_exceptions.tvdb_error, IOError), e: |
|||
log.error('Failed parsing TheTVDB EpisodeInfo for "%s" id "%s": %s', (show, identifier, traceback.format_exc())) |
|||
return False |
|||
|
|||
result = [] |
|||
for number, season in show.items(): |
|||
if season_identifier is not None and number != season_identifier: |
|||
continue |
|||
|
|||
for episode in season.values(): |
|||
if episode_identifier is not None and episode['id'] == toUnicode(episode_identifier): |
|||
result = self._parseEpisode(show, episode) |
|||
self.setCache(cache_key, result) |
|||
return result |
|||
else: |
|||
result.append(self._parseEpisode(show, episode)) |
|||
|
|||
self.setCache(cache_key, result) |
|||
return result |
|||
|
|||
def _parseShow(self, show): |
|||
""" |
|||
'actors': u'|Bryan Cranston|Aaron Paul|Dean Norris|RJ Mitte|Betsy Brandt|Anna Gunn|Laura Fraser|Jesse Plemons|Christopher Cousins|Steven Michael Quezada|Jonathan Banks|Giancarlo Esposito|Bob Odenkirk|', |
|||
'added': None, |
|||
'addedby': None, |
|||
'airs_dayofweek': u'Sunday', |
|||
'airs_time': u'9:00 PM', |
|||
'banner': u'http://thetvdb.com/banners/graphical/81189-g13.jpg', |
|||
'contentrating': u'TV-MA', |
|||
'fanart': u'http://thetvdb.com/banners/fanart/original/81189-28.jpg', |
|||
'firstaired': u'2008-01-20', |
|||
'genre': u'|Crime|Drama|Suspense|', |
|||
'id': u'81189', |
|||
'imdb_id': u'tt0903747', |
|||
'language': u'en', |
|||
'lastupdated': u'1376620212', |
|||
'network': u'AMC', |
|||
'networkid': None, |
|||
'overview': u"Walter White, a struggling high school chemistry teacher is diagnosed with advanced lung cancer. He turns to a life of crime, producing and selling methamphetamine accompanied by a former student, Jesse Pinkman with the aim of securing his family's financial future before he dies.", |
|||
'poster': u'http://thetvdb.com/banners/posters/81189-22.jpg', |
|||
'rating': u'9.3', |
|||
'ratingcount': u'473', |
|||
'runtime': u'60', |
|||
'seriesid': u'74713', |
|||
'seriesname': u'Breaking Bad', |
|||
'status': u'Continuing', |
|||
'zap2it_id': u'SH01009396' |
|||
""" |
|||
|
|||
# |
|||
# NOTE: show object only allows direct access via |
|||
# show['id'], not show.get('id') |
|||
# |
|||
|
|||
# TODO: Make sure we have a valid show id, not '' or None |
|||
#if len (show['id']) is 0: |
|||
# return None |
|||
|
|||
## Images |
|||
poster = show['poster'] or None |
|||
backdrop = show['fanart'] or None |
|||
|
|||
genres = [] if show['genre'] is None else show['genre'].strip('|').split('|') |
|||
if show['firstaired'] is not None: |
|||
try: year = datetime.strptime(show['firstaired'], '%Y-%m-%d').year |
|||
except: year = None |
|||
else: |
|||
year = None |
|||
|
|||
try: |
|||
id = int(show['id']) |
|||
except: |
|||
id = None |
|||
|
|||
show_data = { |
|||
'id': id, |
|||
'type': 'show', |
|||
'primary_provider': 'thetvdb', |
|||
'titles': [show['seriesname'] or u'', ], |
|||
'original_title': show['seriesname'] or u'', |
|||
'images': { |
|||
'poster': [poster] if poster else [], |
|||
'backdrop': [backdrop] if backdrop else [], |
|||
'poster_original': [], |
|||
'backdrop_original': [], |
|||
}, |
|||
'year': year, |
|||
'genres': genres, |
|||
'imdb': show['imdb_id'] or None, |
|||
'zap2it_id': show['zap2it_id'] or None, |
|||
'seriesid': show['seriesid'] or None, |
|||
'network': show['network'] or None, |
|||
'networkid': show['networkid'] or None, |
|||
'airs_dayofweek': show['airs_dayofweek'] or None, |
|||
'airs_time': show['airs_time'] or None, |
|||
'firstaired': show['firstaired'] or None, |
|||
'released': show['firstaired'] or None, |
|||
'runtime': show['runtime'] or None, |
|||
'contentrating': show['contentrating'] or None, |
|||
'rating': show['rating'] or None, |
|||
'ratingcount': show['ratingcount'] or None, |
|||
'actors': show['actors'] or None, |
|||
'lastupdated': show['lastupdated'] or None, |
|||
'status': show['status'] or None, |
|||
'language': show['language'] or None, |
|||
} |
|||
|
|||
show_data = dict((k, v) for k, v in show_data.iteritems() if v) |
|||
|
|||
# Add alternative titles |
|||
try: |
|||
raw = self.tvdb.search(show['seriesname']) |
|||
if raw: |
|||
for show_info in raw: |
|||
if show_info['id'] == show_data['id'] and show_info.get('aliasnames', None): |
|||
for alt_name in show_info['aliasnames'].split('|'): |
|||
show_data['titles'].append(toUnicode(alt_name)) |
|||
except (tvdb_exceptions.tvdb_error, IOError), e: |
|||
log.error('Failed searching TheTVDB for "%s": %s', (show['seriesname'], traceback.format_exc())) |
|||
|
|||
return show_data |
|||
|
|||
def _parseSeason(self, show, season_tuple): |
|||
""" |
|||
contains no data |
|||
""" |
|||
|
|||
number, season = season_tuple |
|||
title = toUnicode('%s - Season %s' % (show['seriesname'] or u'', str(number))) |
|||
poster = [] |
|||
try: |
|||
for id, data in show.data['_banners']['season']['season'].items(): |
|||
if data.get('season', None) == str(number) and data['bannertype'] == 'season' and data['bannertype2'] == 'season': |
|||
poster.append(data.get('_bannerpath')) |
|||
break # Only really need one |
|||
except: |
|||
pass |
|||
|
|||
try: |
|||
id = (show['id'] + ':' + str(number)) |
|||
except: |
|||
id = None |
|||
|
|||
# XXX: work on title; added defualt_title to fix an error |
|||
season_data = { |
|||
'id': id, |
|||
'type': 'season', |
|||
'primary_provider': 'thetvdb', |
|||
'titles': [title, ], |
|||
'original_title': title, |
|||
'via_thetvdb': True, |
|||
'parent_identifier': show['id'] or None, |
|||
'seasonnumber': str(number), |
|||
'images': { |
|||
'poster': poster, |
|||
'backdrop': [], |
|||
'poster_original': [], |
|||
'backdrop_original': [], |
|||
}, |
|||
'year': None, |
|||
'genres': None, |
|||
'imdb': None, |
|||
} |
|||
|
|||
season_data = dict((k, v) for k, v in season_data.iteritems() if v) |
|||
return season_data |
|||
|
|||
def _parseEpisode(self, show, episode): |
|||
""" |
|||
('episodenumber', u'1'), |
|||
('thumb_added', None), |
|||
('rating', u'7.7'), |
|||
('overview', |
|||
u'Experienced waitress Max Black meets her new co-worker, former rich-girl Caroline Channing, and puts her skills to the test at an old but re-emerging Brooklyn diner. Despite her initial distaste for Caroline, Max eventually softens and the two team up for a new business venture.'), |
|||
('dvd_episodenumber', None), |
|||
('dvd_discid', None), |
|||
('combined_episodenumber', u'1'), |
|||
('epimgflag', u'7'), |
|||
('id', u'4099506'), |
|||
('seasonid', u'465948'), |
|||
('thumb_height', u'225'), |
|||
('tms_export', u'1374789754'), |
|||
('seasonnumber', u'1'), |
|||
('writer', u'|Michael Patrick King|Whitney Cummings|'), |
|||
('lastupdated', u'1371420338'), |
|||
('filename', u'http://thetvdb.com/banners/episodes/248741/4099506.jpg'), |
|||
('absolute_number', u'1'), |
|||
('ratingcount', u'102'), |
|||
('combined_season', u'1'), |
|||
('thumb_width', u'400'), |
|||
('imdb_id', u'tt1980319'), |
|||
('director', u'James Burrows'), |
|||
('dvd_chapter', None), |
|||
('dvd_season', None), |
|||
('gueststars', |
|||
u'|Brooke Lyons|Noah Mills|Shoshana Bush|Cale Hartmann|Adam Korson|Alex Enriquez|Matt Cook|Bill Parks|Eugene Shaw|Sergey Brusilovsky|Greg Lewis|Cocoa Brown|Nick Jameson|'), |
|||
('seriesid', u'248741'), |
|||
('language', u'en'), |
|||
('productioncode', u'296793'), |
|||
('firstaired', u'2011-09-19'), |
|||
('episodename', u'Pilot')] |
|||
""" |
|||
|
|||
poster = episode.get('filename', []) |
|||
backdrop = [] |
|||
genres = [] |
|||
plot = "%s - %sx%s - %s" % (show['seriesname'] or u'', |
|||
episode.get('seasonnumber', u'?'), |
|||
episode.get('episodenumber', u'?'), |
|||
episode.get('overview', u'')) |
|||
if episode.get('firstaired', None) is not None: |
|||
try: year = datetime.strptime(episode['firstaired'], '%Y-%m-%d').year |
|||
except: year = None |
|||
else: |
|||
year = None |
|||
|
|||
try: |
|||
id = int(episode['id']) |
|||
except: |
|||
id = None |
|||
|
|||
episode_data = { |
|||
'id': id, |
|||
'type': 'episode', |
|||
'primary_provider': 'thetvdb', |
|||
'via_thetvdb': True, |
|||
'thetvdb_id': id, |
|||
'titles': [episode.get('episodename', u''), ], |
|||
'original_title': episode.get('episodename', u'') , |
|||
'images': { |
|||
'poster': [poster] if poster else [], |
|||
'backdrop': [backdrop] if backdrop else [], |
|||
'poster_original': [], |
|||
'backdrop_original': [], |
|||
}, |
|||
'imdb': episode.get('imdb_id', None), |
|||
'runtime': None, |
|||
'released': episode.get('firstaired', None), |
|||
'year': year, |
|||
'plot': plot, |
|||
'genres': genres, |
|||
'parent_identifier': show['id'] or None, |
|||
'seasonnumber': episode.get('seasonnumber', None), |
|||
'episodenumber': episode.get('episodenumber', None), |
|||
'combined_episodenumber': episode.get('combined_episodenumber', None), |
|||
'absolute_number': episode.get('absolute_number', None), |
|||
'combined_season': episode.get('combined_season', None), |
|||
'productioncode': episode.get('productioncode', None), |
|||
'seriesid': episode.get('seriesid', None), |
|||
'seasonid': episode.get('seasonid', None), |
|||
'firstaired': episode.get('firstaired', None), |
|||
'thumb_added': episode.get('thumb_added', None), |
|||
'thumb_height': episode.get('thumb_height', None), |
|||
'thumb_width': episode.get('thumb_width', None), |
|||
'rating': episode.get('rating', None), |
|||
'ratingcount': episode.get('ratingcount', None), |
|||
'epimgflag': episode.get('epimgflag', None), |
|||
'dvd_episodenumber': episode.get('dvd_episodenumber', None), |
|||
'dvd_discid': episode.get('dvd_discid', None), |
|||
'dvd_chapter': episode.get('dvd_chapter', None), |
|||
'dvd_season': episode.get('dvd_season', None), |
|||
'tms_export': episode.get('tms_export', None), |
|||
'writer': episode.get('writer', None), |
|||
'director': episode.get('director', None), |
|||
'gueststars': episode.get('gueststars', None), |
|||
'lastupdated': episode.get('lastupdated', None), |
|||
'language': episode.get('language', None), |
|||
} |
|||
|
|||
episode_data = dict((k, v) for k, v in episode_data.iteritems() if v) |
|||
return episode_data |
|||
|
|||
#def getImage(self, show, type = 'poster', size = 'cover'): |
|||
#"""""" |
|||
## XXX: Need to implement size |
|||
#image_url = '' |
|||
|
|||
#for res, res_data in show['_banners'].get(type, {}).items(): |
|||
#for bid, banner_info in res_data.items(): |
|||
#image_url = banner_info.get('_bannerpath', '') |
|||
#break |
|||
|
|||
#return image_url |
|||
|
|||
def isDisabled(self): |
|||
if self.conf('api_key') == '': |
|||
log.error('No API key provided.') |
|||
True |
|||
else: |
|||
False |
@ -0,0 +1,24 @@ |
|||
from .main import Xem |
|||
|
|||
def start(): |
|||
return Xem() |
|||
|
|||
config = [{ |
|||
'name': 'xem', |
|||
'groups': [ |
|||
{ |
|||
'tab': 'providers', |
|||
'name': 'xem', |
|||
'label': 'TheXem', |
|||
'hidden': True, |
|||
'description': 'Used for all calls to TheXem.', |
|||
'options': [ |
|||
{ |
|||
'name': 'enabled', |
|||
'default': True, |
|||
'label': 'Enabled', |
|||
}, |
|||
], |
|||
}, |
|||
], |
|||
}] |
@ -0,0 +1,184 @@ |
|||
from couchpotato.core.event import addEvent |
|||
from couchpotato.core.logger import CPLog |
|||
from couchpotato.core.providers.info.base import ShowProvider |
|||
from couchpotato.core.helpers.encoding import toUnicode, tryUrlencode |
|||
import traceback |
|||
|
|||
log = CPLog(__name__) |
|||
|
|||
|
|||
class Xem(ShowProvider): |
|||
''' |
|||
Mapping Information |
|||
=================== |
|||
|
|||
Single |
|||
------ |
|||
You will need the id / identifier of the show e.g. tvdb-id for American Dad! is 73141 |
|||
the origin is the name of the site/entity the episode, season (and/or absolute) numbers are based on |
|||
|
|||
http://thexem.de/map/single?id=&origin=&episode=&season=&absolute= |
|||
|
|||
episode, season and absolute are all optional but it wont work if you don't provide either episode and season OR absolute in |
|||
addition you can provide destination as the name of the wished destination, if not provided it will output all available |
|||
|
|||
When a destination has two or more addresses another entry will be added as _ ... for now the second address gets the index "2" |
|||
(the first index is omitted) and so on |
|||
|
|||
http://thexem.de/map/single?id=7529&origin=anidb&season=1&episode=2&destination=trakt |
|||
{ |
|||
"result":"success", |
|||
"data":{ |
|||
"trakt": {"season":1,"episode":3,"absolute":3}, |
|||
"trakt_2":{"season":1,"episode":4,"absolute":4} |
|||
}, |
|||
"message":"single mapping for 7529 on anidb." |
|||
} |
|||
|
|||
All |
|||
--- |
|||
Basically same as "single" just a little easier |
|||
The origin address is added into the output too!! |
|||
|
|||
http://thexem.de/map/all?id=7529&origin=anidb |
|||
|
|||
All Names |
|||
--------- |
|||
Get all names xem has to offer |
|||
non optional params: origin(an entity string like 'tvdb') |
|||
optional params: season, language |
|||
- season: a season number or a list like: 1,3,5 or a compare operator like ne,gt,ge,lt,le,eq and a season number. default would |
|||
return all |
|||
- language: a language string like 'us' or 'jp' default is all |
|||
- defaultNames: 1(yes) or 0(no) should the default names be added to the list ? default is 0(no) |
|||
|
|||
http://thexem.de/map/allNames?origin=tvdb&season=le1 |
|||
|
|||
{ |
|||
"result": "success", |
|||
"data": { |
|||
"248812": ["Dont Trust the Bitch in Apartment 23", "Don't Trust the Bitch in Apartment 23"], |
|||
"257571": ["Nazo no Kanojo X"], |
|||
"257875": ["Lupin III - Mine Fujiko to Iu Onna", "Lupin III Fujiko to Iu Onna", "Lupin the Third - Mine Fujiko to Iu Onna"] |
|||
}, |
|||
"message": "" |
|||
} |
|||
''' |
|||
|
|||
def __init__(self): |
|||
addEvent('show.info', self.getShowInfo, priority = 5) |
|||
addEvent('episode.info', self.getEpisodeInfo, priority = 5) |
|||
|
|||
self.config = {} |
|||
self.config['base_url'] = "http://thexem.de" |
|||
self.config['url_single'] = u"%(base_url)s/map/single?" % self.config |
|||
self.config['url_all'] = u"%(base_url)s/map/all?" % self.config |
|||
self.config['url_names'] = u"%(base_url)s/map/names?" % self.config |
|||
self.config['url_all_names'] = u"%(base_url)s/map/allNames?" % self.config |
|||
|
|||
# TODO: Also get show aliases (store as titles) |
|||
def getShowInfo(self, identifier = None): |
|||
if self.isDisabled(): |
|||
return {} |
|||
|
|||
cache_key = 'xem.cache.%s' % identifier |
|||
log.debug('Getting showInfo: %s', cache_key) |
|||
result = self.getCache(cache_key) or {} |
|||
if result: |
|||
return result |
|||
|
|||
# Create season/episode and absolute mappings |
|||
url = self.config['url_all'] + "id=%s&origin=tvdb" % tryUrlencode(identifier) |
|||
response = self.getJsonData(url) |
|||
if response: |
|||
if response.get('result') == 'success': |
|||
data = response.get('data', None) |
|||
result = self._parse(data) |
|||
|
|||
# Create name alias mappings |
|||
url = self.config['url_names'] + "id=%s&origin=tvdb" % tryUrlencode(identifier) |
|||
response = self.getJsonData(url) |
|||
if response: |
|||
if response.get('result') == 'success': |
|||
data = response.get('data', None) |
|||
result.update({'map_names': data}) |
|||
|
|||
self.setCache(cache_key, result) |
|||
return result |
|||
|
|||
def getEpisodeInfo(self, identifier = None, params = {}): |
|||
episode = params.get('episode', None) |
|||
if episode is None: |
|||
return False |
|||
|
|||
season_identifier = params.get('season_identifier', None) |
|||
if season_identifier is None: |
|||
return False |
|||
|
|||
episode_identifier = params.get('episode_identifier', None) |
|||
absolute = params.get('absolute', None) |
|||
|
|||
# season_identifier must contain the 'show id : season number' since there is no tvdb id |
|||
# for season and we need a reference to both the show id and season number |
|||
if season_identifier: |
|||
try: |
|||
identifier, season_identifier = season_identifier.split(':') |
|||
season = int(season_identifier) |
|||
except: return False |
|||
|
|||
result = self.getShowInfo(identifier) |
|||
map = {} |
|||
if result: |
|||
map_episode = result.get('map_episode', {}).get(season, {}).get(episode, {}) |
|||
if map_episode: |
|||
map.update({'map_episode': map_episode}) |
|||
|
|||
if absolute: |
|||
map_absolute = result.get('map_absolute', {}).get(absolute, {}) |
|||
if map_absolute: |
|||
map.update({'map_absolute': map_absolute}) |
|||
|
|||
map_names = result.get('map_names', {}).get(toUnicode(season), {}) |
|||
if map_names: |
|||
map.update({'map_names': map_names}) |
|||
|
|||
return map |
|||
|
|||
|
|||
def _parse(self, data, master = 'tvdb'): |
|||
'''parses xem map and returns a custom formatted dict map |
|||
|
|||
To retreive map for scene: |
|||
if 'scene' in map['map_episode'][1][1]: |
|||
print map['map_episode'][1][1]['scene']['season'] |
|||
''' |
|||
if not isinstance(data, list): |
|||
return {} |
|||
|
|||
map = {'map_episode': {}, 'map_absolute': {}} |
|||
for maps in data: |
|||
origin = maps.pop(master, None) |
|||
if origin is None: |
|||
continue # No master origin to map to |
|||
map.get('map_episode').setdefault(origin['season'], {}).setdefault(origin['episode'], maps.copy()) |
|||
map.get('map_absolute').setdefault(origin['absolute'], maps.copy()) |
|||
|
|||
return map |
|||
|
|||
def isDisabled(self): |
|||
if __name__ == '__main__': |
|||
return False |
|||
if self.conf('enabled'): |
|||
return False |
|||
else: |
|||
return True |
|||
|
|||
#XXX: REMOVE, just for degugging |
|||
def main(): |
|||
"""Simple example of using xem |
|||
""" |
|||
xem_instance = Xem() |
|||
print xem_instance.getShowInfo(identifier=73141) # (American Dad) |
|||
|
|||
if __name__ == '__main__': |
|||
main() |
@ -0,0 +1,195 @@ |
|||
# Copyright 2013 Dean Gardiner <gardiner91@gmail.com> |
|||
# |
|||
# Licensed under the Apache License, Version 2.0 (the "License"); |
|||
# you may not use this file except in compliance with the License. |
|||
# You may obtain a copy of the License at |
|||
# |
|||
# http://www.apache.org/licenses/LICENSE-2.0 |
|||
# |
|||
# Unless required by applicable law or agreed to in writing, software |
|||
# distributed under the License is distributed on an "AS IS" BASIS, |
|||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
|||
# See the License for the specific language governing permissions and |
|||
# limitations under the License. |
|||
|
|||
from logr import Logr |
|||
from caper.matcher import FragmentMatcher |
|||
from caper.objects import CaperFragment, CaperClosure |
|||
from caper.parsers.anime import AnimeParser |
|||
from caper.parsers.scene import SceneParser |
|||
from caper.parsers.usenet import UsenetParser |
|||
|
|||
|
|||
__version_info__ = ('0', '3', '1') |
|||
__version_branch__ = 'master' |
|||
|
|||
__version__ = "%s%s" % ( |
|||
'.'.join(__version_info__), |
|||
'-' + __version_branch__ if __version_branch__ else '' |
|||
) |
|||
|
|||
|
|||
CL_START_CHARS = ['(', '[', '<', '>'] |
|||
CL_END_CHARS = [')', ']', '<', '>'] |
|||
CL_END_STRINGS = [' - '] |
|||
|
|||
STRIP_START_CHARS = ''.join(CL_START_CHARS) |
|||
STRIP_END_CHARS = ''.join(CL_END_CHARS) |
|||
STRIP_CHARS = ''.join(['_', ' ', '.']) |
|||
|
|||
FRAGMENT_SEPARATORS = ['.', '-', '_', ' '] |
|||
|
|||
|
|||
CL_START = 0 |
|||
CL_END = 1 |
|||
|
|||
|
|||
class Caper(object): |
|||
def __init__(self, debug=False): |
|||
self.debug = debug |
|||
|
|||
self.parsers = { |
|||
'anime': AnimeParser, |
|||
'scene': SceneParser, |
|||
'usenet': UsenetParser |
|||
} |
|||
|
|||
def _closure_split(self, name): |
|||
""" |
|||
:type name: str |
|||
|
|||
:rtype: list of CaperClosure |
|||
""" |
|||
|
|||
closures = [] |
|||
|
|||
def end_closure(closures, buf): |
|||
buf = buf.strip(STRIP_CHARS) |
|||
if len(buf) < 2: |
|||
return |
|||
|
|||
cur = CaperClosure(len(closures), buf) |
|||
cur.left = closures[len(closures) - 1] if len(closures) > 0 else None |
|||
|
|||
if cur.left: |
|||
cur.left.right = cur |
|||
|
|||
closures.append(cur) |
|||
|
|||
state = CL_START |
|||
buf = "" |
|||
for x, ch in enumerate(name): |
|||
# Check for start characters |
|||
if state == CL_START and ch in CL_START_CHARS: |
|||
end_closure(closures, buf) |
|||
|
|||
state = CL_END |
|||
buf = "" |
|||
|
|||
buf += ch |
|||
|
|||
if state == CL_END and ch in CL_END_CHARS: |
|||
# End character found, create the closure |
|||
end_closure(closures, buf) |
|||
|
|||
state = CL_START |
|||
buf = "" |
|||
elif state == CL_START and buf[-3:] in CL_END_STRINGS: |
|||
# End string found, create the closure |
|||
end_closure(closures, buf[:-3]) |
|||
|
|||
state = CL_START |
|||
buf = "" |
|||
|
|||
end_closure(closures, buf) |
|||
|
|||
return closures |
|||
|
|||
def _clean_closure(self, closure): |
|||
""" |
|||
:type closure: str |
|||
|
|||
:rtype: str |
|||
""" |
|||
|
|||
return closure.lstrip(STRIP_START_CHARS).rstrip(STRIP_END_CHARS) |
|||
|
|||
def _fragment_split(self, closures): |
|||
""" |
|||
:type closures: list of CaperClosure |
|||
|
|||
:rtype: list of CaperClosure |
|||
""" |
|||
|
|||
cur_position = 0 |
|||
cur = None |
|||
|
|||
def end_fragment(fragments, cur, cur_position): |
|||
cur.position = cur_position |
|||
|
|||
cur.left = fragments[len(fragments) - 1] if len(fragments) > 0 else None |
|||
if cur.left: |
|||
cur.left_sep = cur.left.right_sep |
|||
cur.left.right = cur |
|||
|
|||
cur.right_sep = ch |
|||
|
|||
fragments.append(cur) |
|||
|
|||
for closure in closures: |
|||
closure.fragments = [] |
|||
|
|||
separator_buffer = "" |
|||
|
|||
for x, ch in enumerate(self._clean_closure(closure.value)): |
|||
if not cur: |
|||
cur = CaperFragment(closure) |
|||
|
|||
if ch in FRAGMENT_SEPARATORS: |
|||
if cur.value: |
|||
separator_buffer = "" |
|||
|
|||
separator_buffer += ch |
|||
|
|||
if cur.value or not closure.fragments: |
|||
end_fragment(closure.fragments, cur, cur_position) |
|||
elif len(separator_buffer) > 1: |
|||
cur.value = separator_buffer.strip() |
|||
|
|||
if cur.value: |
|||
end_fragment(closure.fragments, cur, cur_position) |
|||
|
|||
separator_buffer = "" |
|||
|
|||
# Reset |
|||
cur = None |
|||
cur_position += 1 |
|||
else: |
|||
cur.value += ch |
|||
|
|||
# Finish parsing the last fragment |
|||
if cur and cur.value: |
|||
end_fragment(closure.fragments, cur, cur_position) |
|||
|
|||
# Reset |
|||
cur_position = 0 |
|||
cur = None |
|||
|
|||
return closures |
|||
|
|||
def parse(self, name, parser='scene'): |
|||
closures = self._closure_split(name) |
|||
closures = self._fragment_split(closures) |
|||
|
|||
# Print closures |
|||
for closure in closures: |
|||
Logr.debug("closure [%s]", closure.value) |
|||
|
|||
for fragment in closure.fragments: |
|||
Logr.debug("\tfragment [%s]", fragment.value) |
|||
|
|||
if parser not in self.parsers: |
|||
raise ValueError("Unknown parser") |
|||
|
|||
# TODO autodetect the parser type |
|||
return self.parsers[parser](self.debug).run(closures) |
@ -0,0 +1,134 @@ |
|||
# Copyright 2013 Dean Gardiner <gardiner91@gmail.com> |
|||
# |
|||
# Licensed under the Apache License, Version 2.0 (the "License"); |
|||
# you may not use this file except in compliance with the License. |
|||
# You may obtain a copy of the License at |
|||
# |
|||
# http://www.apache.org/licenses/LICENSE-2.0 |
|||
# |
|||
# Unless required by applicable law or agreed to in writing, software |
|||
# distributed under the License is distributed on an "AS IS" BASIS, |
|||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
|||
# See the License for the specific language governing permissions and |
|||
# limitations under the License. |
|||
|
|||
|
|||
class CaptureConstraint(object): |
|||
def __init__(self, capture_group, constraint_type, comparisons=None, target=None, **kwargs): |
|||
"""Capture constraint object |
|||
|
|||
:type capture_group: CaptureGroup |
|||
""" |
|||
|
|||
self.capture_group = capture_group |
|||
|
|||
self.constraint_type = constraint_type |
|||
self.target = target |
|||
|
|||
self.comparisons = comparisons if comparisons else [] |
|||
self.kwargs = {} |
|||
|
|||
for orig_key, value in kwargs.items(): |
|||
key = orig_key.split('__') |
|||
if len(key) != 2: |
|||
self.kwargs[orig_key] = value |
|||
continue |
|||
name, method = key |
|||
|
|||
method = 'constraint_match_' + method |
|||
if not hasattr(self, method): |
|||
self.kwargs[orig_key] = value |
|||
continue |
|||
|
|||
self.comparisons.append((name, getattr(self, method), value)) |
|||
|
|||
def execute(self, parent_node, node, **kwargs): |
|||
func_name = 'constraint_%s' % self.constraint_type |
|||
|
|||
if hasattr(self, func_name): |
|||
return getattr(self, func_name)(parent_node, node, **kwargs) |
|||
|
|||
raise ValueError('Unknown constraint type "%s"' % self.constraint_type) |
|||
|
|||
# |
|||
# Node Matching |
|||
# |
|||
|
|||
def constraint_match(self, parent_node, node): |
|||
results = [] |
|||
total_weight = 0 |
|||
|
|||
for name, method, argument in self.comparisons: |
|||
weight, success = method(node, name, argument) |
|||
total_weight += weight |
|||
results.append(success) |
|||
|
|||
return total_weight / (float(len(results)) or 1), all(results) if len(results) > 0 else False |
|||
|
|||
def constraint_match_eq(self, node, name, expected): |
|||
if not hasattr(node, name): |
|||
return 1.0, False |
|||
|
|||
return 1.0, getattr(node, name) == expected |
|||
|
|||
def constraint_match_re(self, node, name, arg): |
|||
# Node match |
|||
if name == 'node': |
|||
group, minimum_weight = arg if type(arg) is tuple and len(arg) > 1 else (arg, 0) |
|||
|
|||
weight, match, num_fragments = self.capture_group.parser.matcher.fragment_match(node, group) |
|||
return weight, weight > minimum_weight |
|||
|
|||
# Regex match |
|||
if type(arg).__name__ == 'SRE_Pattern': |
|||
return 1.0, arg.match(getattr(node, name)) is not None |
|||
|
|||
# Value match |
|||
if hasattr(node, name): |
|||
match = self.capture_group.parser.matcher.value_match(getattr(node, name), arg, single=True) |
|||
return 1.0, match is not None |
|||
|
|||
raise ValueError("Unknown constraint match type '%s'" % name) |
|||
|
|||
# |
|||
# Result |
|||
# |
|||
|
|||
def constraint_result(self, parent_node, fragment): |
|||
ctag = self.kwargs.get('tag') |
|||
if not ctag: |
|||
return 0, False |
|||
|
|||
ckey = self.kwargs.get('key') |
|||
|
|||
for tag, result in parent_node.captured(): |
|||
if tag != ctag: |
|||
continue |
|||
|
|||
if not ckey or ckey in result.keys(): |
|||
return 1.0, True |
|||
|
|||
return 0.0, False |
|||
|
|||
# |
|||
# Failure |
|||
# |
|||
|
|||
def constraint_failure(self, parent_node, fragment, match): |
|||
if not match or not match.success: |
|||
return 1.0, True |
|||
|
|||
return 0, False |
|||
|
|||
# |
|||
# Success |
|||
# |
|||
|
|||
def constraint_success(self, parent_node, fragment, match): |
|||
if match and match.success: |
|||
return 1.0, True |
|||
|
|||
return 0, False |
|||
|
|||
def __repr__(self): |
|||
return "CaptureConstraint(comparisons=%s)" % repr(self.comparisons) |
@ -0,0 +1,284 @@ |
|||
# Copyright 2013 Dean Gardiner <gardiner91@gmail.com> |
|||
# |
|||
# Licensed under the Apache License, Version 2.0 (the "License"); |
|||
# you may not use this file except in compliance with the License. |
|||
# You may obtain a copy of the License at |
|||
# |
|||
# http://www.apache.org/licenses/LICENSE-2.0 |
|||
# |
|||
# Unless required by applicable law or agreed to in writing, software |
|||
# distributed under the License is distributed on an "AS IS" BASIS, |
|||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
|||
# See the License for the specific language governing permissions and |
|||
# limitations under the License. |
|||
|
|||
|
|||
from logr import Logr |
|||
from caper import CaperClosure, CaperFragment |
|||
from caper.helpers import clean_dict |
|||
from caper.result import CaperFragmentNode, CaperClosureNode |
|||
from caper.step import CaptureStep |
|||
from caper.constraint import CaptureConstraint |
|||
|
|||
|
|||
class CaptureGroup(object): |
|||
def __init__(self, parser, result): |
|||
"""Capture group object |
|||
|
|||
:type parser: caper.parsers.base.Parser |
|||
:type result: caper.result.CaperResult |
|||
""" |
|||
|
|||
self.parser = parser |
|||
self.result = result |
|||
|
|||
#: @type: list of CaptureStep |
|||
self.steps = [] |
|||
|
|||
#: type: str |
|||
self.step_source = None |
|||
|
|||
#: @type: list of CaptureConstraint |
|||
self.pre_constraints = [] |
|||
|
|||
#: :type: list of CaptureConstraint |
|||
self.post_constraints = [] |
|||
|
|||
def capture_fragment(self, tag, regex=None, func=None, single=True, **kwargs): |
|||
Logr.debug('capture_fragment("%s", "%s", %s, %s)', tag, regex, func, single) |
|||
|
|||
if self.step_source != 'fragment': |
|||
if self.step_source is None: |
|||
self.step_source = 'fragment' |
|||
else: |
|||
raise ValueError("Unable to mix fragment and closure capturing in a group") |
|||
|
|||
self.steps.append(CaptureStep( |
|||
self, tag, |
|||
'fragment', |
|||
regex=regex, |
|||
func=func, |
|||
single=single, |
|||
**kwargs |
|||
)) |
|||
|
|||
return self |
|||
|
|||
def capture_closure(self, tag, regex=None, func=None, single=True, **kwargs): |
|||
Logr.debug('capture_closure("%s", "%s", %s, %s)', tag, regex, func, single) |
|||
|
|||
if self.step_source != 'closure': |
|||
if self.step_source is None: |
|||
self.step_source = 'closure' |
|||
else: |
|||
raise ValueError("Unable to mix fragment and closure capturing in a group") |
|||
|
|||
self.steps.append(CaptureStep( |
|||
self, tag, |
|||
'closure', |
|||
regex=regex, |
|||
func=func, |
|||
single=single, |
|||
**kwargs |
|||
)) |
|||
|
|||
return self |
|||
|
|||
def until_closure(self, **kwargs): |
|||
self.pre_constraints.append(CaptureConstraint(self, 'match', target='closure', **kwargs)) |
|||
|
|||
return self |
|||
|
|||
def until_fragment(self, **kwargs): |
|||
self.pre_constraints.append(CaptureConstraint(self, 'match', target='fragment', **kwargs)) |
|||
|
|||
return self |
|||
|
|||
def until_result(self, **kwargs): |
|||
self.pre_constraints.append(CaptureConstraint(self, 'result', **kwargs)) |
|||
|
|||
return self |
|||
|
|||
def until_failure(self, **kwargs): |
|||
self.post_constraints.append(CaptureConstraint(self, 'failure', **kwargs)) |
|||
|
|||
return self |
|||
|
|||
def until_success(self, **kwargs): |
|||
self.post_constraints.append(CaptureConstraint(self, 'success', **kwargs)) |
|||
|
|||
return self |
|||
|
|||
def parse_subject(self, parent_head, subject): |
|||
Logr.debug("parse_subject (%s) subject: %s", self.step_source, repr(subject)) |
|||
|
|||
if type(subject) is CaperClosure: |
|||
return self.parse_closure(parent_head, subject) |
|||
|
|||
if type(subject) is CaperFragment: |
|||
return self.parse_fragment(parent_head, subject) |
|||
|
|||
raise ValueError('Unknown subject (%s)', subject) |
|||
|
|||
def parse_fragment(self, parent_head, subject): |
|||
parent_node = parent_head[0] if type(parent_head) is list else parent_head |
|||
|
|||
nodes, match = self.match(parent_head, parent_node, subject) |
|||
|
|||
# Capturing broke on constraint, return now |
|||
if not match: |
|||
return nodes |
|||
|
|||
Logr.debug('created fragment node with subject.value: "%s"' % subject.value) |
|||
|
|||
result = [CaperFragmentNode( |
|||
parent_node.closure, |
|||
subject.take_right(match.num_fragments), |
|||
parent_head, |
|||
match |
|||
)] |
|||
|
|||
# Branch if the match was indefinite (weight below 1.0) |
|||
if match.result and match.weight < 1.0: |
|||
if match.num_fragments == 1: |
|||
result.append(CaperFragmentNode(parent_node.closure, [subject], parent_head)) |
|||
else: |
|||
nodes.append(CaperFragmentNode(parent_node.closure, [subject], parent_head)) |
|||
|
|||
nodes.append(result[0] if len(result) == 1 else result) |
|||
|
|||
return nodes |
|||
|
|||
def parse_closure(self, parent_head, subject): |
|||
parent_node = parent_head[0] if type(parent_head) is list else parent_head |
|||
|
|||
nodes, match = self.match(parent_head, parent_node, subject) |
|||
|
|||
# Capturing broke on constraint, return now |
|||
if not match: |
|||
return nodes |
|||
|
|||
Logr.debug('created closure node with subject.value: "%s"' % subject.value) |
|||
|
|||
result = [CaperClosureNode( |
|||
subject, |
|||
parent_head, |
|||
match |
|||
)] |
|||
|
|||
# Branch if the match was indefinite (weight below 1.0) |
|||
if match.result and match.weight < 1.0: |
|||
if match.num_fragments == 1: |
|||
result.append(CaperClosureNode(subject, parent_head)) |
|||
else: |
|||
nodes.append(CaperClosureNode(subject, parent_head)) |
|||
|
|||
nodes.append(result[0] if len(result) == 1 else result) |
|||
|
|||
return nodes |
|||
|
|||
def match(self, parent_head, parent_node, subject): |
|||
nodes = [] |
|||
|
|||
# Check pre constaints |
|||
broke, definite = self.check_constraints(self.pre_constraints, parent_head, subject) |
|||
|
|||
if broke: |
|||
nodes.append(parent_head) |
|||
|
|||
if definite: |
|||
return nodes, None |
|||
|
|||
# Try match subject against the steps available |
|||
match = None |
|||
|
|||
for step in self.steps: |
|||
if step.source == 'closure' and type(subject) is not CaperClosure: |
|||
pass |
|||
elif step.source == 'fragment' and type(subject) is CaperClosure: |
|||
Logr.debug('Closure encountered on fragment step, jumping into fragments') |
|||
return [CaperClosureNode(subject, parent_head, None)], None |
|||
|
|||
match = step.execute(subject) |
|||
|
|||
if match.success: |
|||
if type(match.result) is dict: |
|||
match.result = clean_dict(match.result) |
|||
|
|||
Logr.debug('Found match with weight %s, match: %s, num_fragments: %s' % ( |
|||
match.weight, match.result, match.num_fragments |
|||
)) |
|||
|
|||
step.matched = True |
|||
|
|||
break |
|||
|
|||
if all([step.single and step.matched for step in self.steps]): |
|||
Logr.debug('All steps completed, group finished') |
|||
parent_node.finished_groups.append(self) |
|||
return nodes, match |
|||
|
|||
# Check post constraints |
|||
broke, definite = self.check_constraints(self.post_constraints, parent_head, subject, match=match) |
|||
if broke: |
|||
return nodes, None |
|||
|
|||
return nodes, match |
|||
|
|||
def check_constraints(self, constraints, parent_head, subject, **kwargs): |
|||
parent_node = parent_head[0] if type(parent_head) is list else parent_head |
|||
|
|||
# Check constraints |
|||
for constraint in [c for c in constraints if c.target == subject.__key__ or not c.target]: |
|||
Logr.debug("Testing constraint %s against subject %s", repr(constraint), repr(subject)) |
|||
|
|||
weight, success = constraint.execute(parent_node, subject, **kwargs) |
|||
|
|||
if success: |
|||
Logr.debug('capturing broke on "%s" at %s', subject.value, constraint) |
|||
parent_node.finished_groups.append(self) |
|||
|
|||
return True, weight == 1.0 |
|||
|
|||
return False, None |
|||
|
|||
def execute(self): |
|||
heads_finished = None |
|||
|
|||
while heads_finished is None or not (len(heads_finished) == len(self.result.heads) and all(heads_finished)): |
|||
heads_finished = [] |
|||
|
|||
heads = self.result.heads |
|||
self.result.heads = [] |
|||
|
|||
for head in heads: |
|||
node = head[0] if type(head) is list else head |
|||
|
|||
if self in node.finished_groups: |
|||
Logr.debug("head finished for group") |
|||
self.result.heads.append(head) |
|||
heads_finished.append(True) |
|||
continue |
|||
|
|||
Logr.debug('') |
|||
|
|||
Logr.debug(node) |
|||
|
|||
next_subject = node.next() |
|||
|
|||
Logr.debug('----------[%s] (%s)----------' % (next_subject, repr(next_subject.value) if next_subject else None)) |
|||
|
|||
if next_subject: |
|||
for node_result in self.parse_subject(head, next_subject): |
|||
self.result.heads.append(node_result) |
|||
|
|||
Logr.debug('Heads: %s', self.result.heads) |
|||
|
|||
heads_finished.append(self in node.finished_groups or next_subject is None) |
|||
|
|||
if len(self.result.heads) == 0: |
|||
self.result.heads = heads |
|||
|
|||
Logr.debug("heads_finished: %s, self.result.heads: %s", heads_finished, self.result.heads) |
|||
|
|||
Logr.debug("group finished") |
@ -0,0 +1,80 @@ |
|||
# Copyright 2013 Dean Gardiner <gardiner91@gmail.com> |
|||
# |
|||
# Licensed under the Apache License, Version 2.0 (the "License"); |
|||
# you may not use this file except in compliance with the License. |
|||
# You may obtain a copy of the License at |
|||
# |
|||
# http://www.apache.org/licenses/LICENSE-2.0 |
|||
# |
|||
# Unless required by applicable law or agreed to in writing, software |
|||
# distributed under the License is distributed on an "AS IS" BASIS, |
|||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
|||
# See the License for the specific language governing permissions and |
|||
# limitations under the License. |
|||
|
|||
import sys |
|||
|
|||
|
|||
PY2 = sys.version_info[0] == 2 |
|||
PY3 = sys.version_info[0] == 3 |
|||
|
|||
|
|||
def is_list_type(obj, element_type): |
|||
if not type(obj) is list: |
|||
return False |
|||
|
|||
if len(obj) < 1: |
|||
raise ValueError("Unable to determine list element type from empty list") |
|||
|
|||
return type(obj[0]) is element_type |
|||
|
|||
|
|||
def clean_dict(target, remove=None): |
|||
"""Recursively remove items matching a value 'remove' from the dictionary |
|||
|
|||
:type target: dict |
|||
""" |
|||
if type(target) is not dict: |
|||
raise ValueError("Target is required to be a dict") |
|||
|
|||
remove_keys = [] |
|||
for key in target.keys(): |
|||
if type(target[key]) is not dict: |
|||
if target[key] == remove: |
|||
remove_keys.append(key) |
|||
else: |
|||
clean_dict(target[key], remove) |
|||
|
|||
for key in remove_keys: |
|||
target.pop(key) |
|||
|
|||
return target |
|||
|
|||
|
|||
def update_dict(a, b): |
|||
for key, value in b.items(): |
|||
if key not in a: |
|||
a[key] = value |
|||
elif isinstance(a[key], dict) and isinstance(value, dict): |
|||
update_dict(a[key], value) |
|||
elif isinstance(a[key], list): |
|||
a[key].append(value) |
|||
else: |
|||
a[key] = [a[key], value] |
|||
|
|||
|
|||
def xrange_six(start, stop=None, step=None): |
|||
if stop is not None and step is not None: |
|||
if PY3: |
|||
return range(start, stop, step) |
|||
else: |
|||
return xrange(start, stop, step) |
|||
else: |
|||
if PY3: |
|||
return range(start) |
|||
else: |
|||
return xrange(start) |
|||
|
|||
|
|||
def delta_seconds(td): |
|||
return (td.microseconds + (td.seconds + td.days * 24 * 3600) * 1e6) / 1e6 |
@ -0,0 +1,144 @@ |
|||
# Copyright 2013 Dean Gardiner <gardiner91@gmail.com> |
|||
# |
|||
# Licensed under the Apache License, Version 2.0 (the "License"); |
|||
# you may not use this file except in compliance with the License. |
|||
# You may obtain a copy of the License at |
|||
# |
|||
# http://www.apache.org/licenses/LICENSE-2.0 |
|||
# |
|||
# Unless required by applicable law or agreed to in writing, software |
|||
# distributed under the License is distributed on an "AS IS" BASIS, |
|||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
|||
# See the License for the specific language governing permissions and |
|||
# limitations under the License. |
|||
|
|||
from caper.helpers import is_list_type, update_dict, delta_seconds |
|||
from datetime import datetime |
|||
from logr import Logr |
|||
import re |
|||
|
|||
|
|||
class FragmentMatcher(object): |
|||
def __init__(self, pattern_groups): |
|||
self.regex = {} |
|||
|
|||
self.construct_patterns(pattern_groups) |
|||
|
|||
def construct_patterns(self, pattern_groups): |
|||
compile_start = datetime.now() |
|||
compile_count = 0 |
|||
|
|||
for group_name, patterns in pattern_groups: |
|||
if group_name not in self.regex: |
|||
self.regex[group_name] = [] |
|||
|
|||
# Transform into weight groups |
|||
if type(patterns[0]) is str or type(patterns[0][0]) not in [int, float]: |
|||
patterns = [(1.0, patterns)] |
|||
|
|||
for weight, patterns in patterns: |
|||
weight_patterns = [] |
|||
|
|||
for pattern in patterns: |
|||
# Transform into multi-fragment patterns |
|||
if type(pattern) is str: |
|||
pattern = (pattern,) |
|||
|
|||
if type(pattern) is tuple and len(pattern) == 2: |
|||
if type(pattern[0]) is str and is_list_type(pattern[1], str): |
|||
pattern = (pattern,) |
|||
|
|||
result = [] |
|||
for value in pattern: |
|||
if type(value) is tuple: |
|||
if len(value) == 2: |
|||
# Construct OR-list pattern |
|||
value = value[0] % '|'.join(value[1]) |
|||
elif len(value) == 1: |
|||
value = value[0] |
|||
|
|||
result.append(re.compile(value, re.IGNORECASE)) |
|||
compile_count += 1 |
|||
|
|||
weight_patterns.append(tuple(result)) |
|||
|
|||
self.regex[group_name].append((weight, weight_patterns)) |
|||
|
|||
Logr.info("Compiled %s patterns in %ss", compile_count, delta_seconds(datetime.now() - compile_start)) |
|||
|
|||
def find_group(self, name): |
|||
for group_name, weight_groups in self.regex.items(): |
|||
if group_name and group_name == name: |
|||
return group_name, weight_groups |
|||
|
|||
return None, None |
|||
|
|||
def value_match(self, value, group_name=None, single=True): |
|||
result = None |
|||
|
|||
for group, weight_groups in self.regex.items(): |
|||
if group_name and group != group_name: |
|||
continue |
|||
|
|||
# TODO handle multiple weights |
|||
weight, patterns = weight_groups[0] |
|||
|
|||
for pattern in patterns: |
|||
match = pattern[0].match(value) |
|||
if not match: |
|||
continue |
|||
|
|||
if result is None: |
|||
result = {} |
|||
if group not in result: |
|||
result[group] = {} |
|||
|
|||
result[group].update(match.groupdict()) |
|||
|
|||
if single: |
|||
return result |
|||
|
|||
return result |
|||
|
|||
def fragment_match(self, fragment, group_name=None): |
|||
"""Follow a fragment chain to try find a match |
|||
|
|||
:type fragment: caper.objects.CaperFragment |
|||
:type group_name: str or None |
|||
|
|||
:return: The weight of the match found between 0.0 and 1.0, |
|||
where 1.0 means perfect match and 0.0 means no match |
|||
:rtype: (float, dict, int) |
|||
""" |
|||
|
|||
group_name, weight_groups = self.find_group(group_name) |
|||
|
|||
for weight, patterns in weight_groups: |
|||
for pattern in patterns: |
|||
cur_fragment = fragment |
|||
success = True |
|||
result = {} |
|||
|
|||
# Ignore empty patterns |
|||
if len(pattern) < 1: |
|||
break |
|||
|
|||
for fragment_pattern in pattern: |
|||
if not cur_fragment: |
|||
success = False |
|||
break |
|||
|
|||
match = fragment_pattern.match(cur_fragment.value) |
|||
if match: |
|||
update_dict(result, match.groupdict()) |
|||
else: |
|||
success = False |
|||
break |
|||
|
|||
cur_fragment = cur_fragment.right if cur_fragment else None |
|||
|
|||
if success: |
|||
Logr.debug("Found match with weight %s" % weight) |
|||
return float(weight), result, len(pattern) |
|||
|
|||
return 0.0, None, 1 |
@ -0,0 +1,124 @@ |
|||
# Copyright 2013 Dean Gardiner <gardiner91@gmail.com> |
|||
# |
|||
# Licensed under the Apache License, Version 2.0 (the "License"); |
|||
# you may not use this file except in compliance with the License. |
|||
# You may obtain a copy of the License at |
|||
# |
|||
# http://www.apache.org/licenses/LICENSE-2.0 |
|||
# |
|||
# Unless required by applicable law or agreed to in writing, software |
|||
# distributed under the License is distributed on an "AS IS" BASIS, |
|||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
|||
# See the License for the specific language governing permissions and |
|||
# limitations under the License. |
|||
|
|||
from caper.helpers import xrange_six |
|||
|
|||
|
|||
class CaperClosure(object): |
|||
__key__ = 'closure' |
|||
|
|||
def __init__(self, index, value): |
|||
#: :type: int |
|||
self.index = index |
|||
|
|||
#: :type: str |
|||
self.value = value |
|||
|
|||
#: :type: CaperClosure |
|||
self.left = None |
|||
#: :type: CaperClosure |
|||
self.right = None |
|||
|
|||
#: :type: list of CaperFragment |
|||
self.fragments = [] |
|||
|
|||
def __str__(self): |
|||
return "<CaperClosure value: %s" % repr(self.value) |
|||
|
|||
def __repr__(self): |
|||
return self.__str__() |
|||
|
|||
|
|||
class CaperFragment(object): |
|||
__key__ = 'fragment' |
|||
|
|||
def __init__(self, closure=None): |
|||
#: :type: CaperClosure |
|||
self.closure = closure |
|||
|
|||
#: :type: str |
|||
self.value = "" |
|||
|
|||
#: :type: CaperFragment |
|||
self.left = None |
|||
#: :type: str |
|||
self.left_sep = None |
|||
|
|||
#: :type: CaperFragment |
|||
self.right = None |
|||
#: :type: str |
|||
self.right_sep = None |
|||
|
|||
#: :type: int |
|||
self.position = None |
|||
|
|||
def take(self, direction, count, include_self=True): |
|||
if direction not in ['left', 'right']: |
|||
raise ValueError('Un-Expected value for "direction", expected "left" or "right".') |
|||
|
|||
result = [] |
|||
|
|||
if include_self: |
|||
result.append(self) |
|||
count -= 1 |
|||
|
|||
cur = self |
|||
for x in xrange_six(count): |
|||
if cur and getattr(cur, direction): |
|||
cur = getattr(cur, direction) |
|||
result.append(cur) |
|||
else: |
|||
result.append(None) |
|||
cur = None |
|||
|
|||
return result |
|||
|
|||
def take_left(self, count, include_self=True): |
|||
return self.take('left', count, include_self) |
|||
|
|||
def take_right(self, count, include_self=True): |
|||
return self.take('right', count, include_self) |
|||
|
|||
def __str__(self): |
|||
return "<CaperFragment value: %s" % repr(self.value) |
|||
|
|||
def __repr__(self): |
|||
return self.__str__() |
|||
|
|||
|
|||
class CaptureMatch(object): |
|||
def __init__(self, tag, step, success=False, weight=None, result=None, num_fragments=1): |
|||
#: :type: bool |
|||
self.success = success |
|||
|
|||
#: :type: float |
|||
self.weight = weight |
|||
|
|||
#: :type: dict or str |
|||
self.result = result |
|||
|
|||
#: :type: int |
|||
self.num_fragments = num_fragments |
|||
|
|||
#: :type: str |
|||
self.tag = tag |
|||
|
|||
#: :type: CaptureStep |
|||
self.step = step |
|||
|
|||
def __str__(self): |
|||
return "<CaperMatch result: %s>" % repr(self.result) |
|||
|
|||
def __repr__(self): |
|||
return self.__str__() |
@ -0,0 +1,88 @@ |
|||
# Copyright 2013 Dean Gardiner <gardiner91@gmail.com> |
|||
# |
|||
# Licensed under the Apache License, Version 2.0 (the "License"); |
|||
# you may not use this file except in compliance with the License. |
|||
# You may obtain a copy of the License at |
|||
# |
|||
# http://www.apache.org/licenses/LICENSE-2.0 |
|||
# |
|||
# Unless required by applicable law or agreed to in writing, software |
|||
# distributed under the License is distributed on an "AS IS" BASIS, |
|||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
|||
# See the License for the specific language governing permissions and |
|||
# limitations under the License. |
|||
|
|||
import re |
|||
from caper.parsers.base import Parser |
|||
|
|||
|
|||
REGEX_GROUP = re.compile(r'(\(|\[)(?P<group>.*?)(\)|\])', re.IGNORECASE) |
|||
|
|||
|
|||
PATTERN_GROUPS = [ |
|||
('identifier', [ |
|||
r'S(?P<season>\d+)E(?P<episode>\d+)', |
|||
r'(S(?P<season>\d+))|(E(?P<episode>\d+))', |
|||
|
|||
r'Ep(?P<episode>\d+)', |
|||
r'$(?P<absolute>\d+)^', |
|||
|
|||
(r'Episode', r'(?P<episode>\d+)'), |
|||
]), |
|||
('video', [ |
|||
(r'(?P<h264_profile>%s)', [ |
|||
'Hi10P' |
|||
]), |
|||
(r'.(?P<resolution>%s)', [ |
|||
'720p', |
|||
'1080p', |
|||
|
|||
'960x720', |
|||
'1920x1080' |
|||
]), |
|||
(r'(?P<source>%s)', [ |
|||
'BD' |
|||
]), |
|||
]), |
|||
('audio', [ |
|||
(r'(?P<codec>%s)', [ |
|||
'FLAC' |
|||
]), |
|||
]) |
|||
] |
|||
|
|||
|
|||
class AnimeParser(Parser): |
|||
def __init__(self, debug=False): |
|||
super(AnimeParser, self).__init__(PATTERN_GROUPS, debug) |
|||
|
|||
def capture_group(self, fragment): |
|||
match = REGEX_GROUP.match(fragment.value) |
|||
|
|||
if not match: |
|||
return None |
|||
|
|||
return match.group('group') |
|||
|
|||
def run(self, closures): |
|||
""" |
|||
:type closures: list of CaperClosure |
|||
""" |
|||
|
|||
self.setup(closures) |
|||
|
|||
self.capture_closure('group', func=self.capture_group)\ |
|||
.execute(once=True) |
|||
|
|||
self.capture_fragment('show_name', single=False)\ |
|||
.until_fragment(value__re='identifier')\ |
|||
.until_fragment(value__re='video')\ |
|||
.execute() |
|||
|
|||
self.capture_fragment('identifier', regex='identifier') \ |
|||
.capture_fragment('video', regex='video', single=False) \ |
|||
.capture_fragment('audio', regex='audio', single=False) \ |
|||
.execute() |
|||
|
|||
self.result.build() |
|||
return self.result |
@ -0,0 +1,84 @@ |
|||
# Copyright 2013 Dean Gardiner <gardiner91@gmail.com> |
|||
# |
|||
# Licensed under the Apache License, Version 2.0 (the "License"); |
|||
# you may not use this file except in compliance with the License. |
|||
# You may obtain a copy of the License at |
|||
# |
|||
# http://www.apache.org/licenses/LICENSE-2.0 |
|||
# |
|||
# Unless required by applicable law or agreed to in writing, software |
|||
# distributed under the License is distributed on an "AS IS" BASIS, |
|||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
|||
# See the License for the specific language governing permissions and |
|||
# limitations under the License. |
|||
|
|||
from caper import FragmentMatcher |
|||
from caper.group import CaptureGroup |
|||
from caper.result import CaperResult, CaperClosureNode, CaperRootNode |
|||
from logr import Logr |
|||
|
|||
|
|||
class Parser(object): |
|||
def __init__(self, matcher, debug=False): |
|||
self.debug = debug |
|||
|
|||
self.matcher = matcher |
|||
|
|||
self.closures = None |
|||
#: :type: caper.result.CaperResult |
|||
self.result = None |
|||
|
|||
self._match_cache = None |
|||
self._fragment_pos = None |
|||
self._closure_pos = None |
|||
self._history = None |
|||
|
|||
self.reset() |
|||
|
|||
def reset(self): |
|||
self.closures = None |
|||
self.result = CaperResult() |
|||
|
|||
self._match_cache = {} |
|||
self._fragment_pos = -1 |
|||
self._closure_pos = -1 |
|||
self._history = [] |
|||
|
|||
def setup(self, closures): |
|||
""" |
|||
:type closures: list of CaperClosure |
|||
""" |
|||
|
|||
self.reset() |
|||
self.closures = closures |
|||
|
|||
self.result.heads = [CaperRootNode(closures[0])] |
|||
|
|||
def run(self, closures): |
|||
""" |
|||
:type closures: list of CaperClosure |
|||
""" |
|||
|
|||
raise NotImplementedError() |
|||
|
|||
# |
|||
# Capture Methods |
|||
# |
|||
|
|||
def capture_fragment(self, tag, regex=None, func=None, single=True, **kwargs): |
|||
return CaptureGroup(self, self.result).capture_fragment( |
|||
tag, |
|||
regex=regex, |
|||
func=func, |
|||
single=single, |
|||
**kwargs |
|||
) |
|||
|
|||
def capture_closure(self, tag, regex=None, func=None, single=True, **kwargs): |
|||
return CaptureGroup(self, self.result).capture_closure( |
|||
tag, |
|||
regex=regex, |
|||
func=func, |
|||
single=single, |
|||
**kwargs |
|||
) |
@ -0,0 +1,230 @@ |
|||
# Copyright 2013 Dean Gardiner <gardiner91@gmail.com> |
|||
# |
|||
# Licensed under the Apache License, Version 2.0 (the "License"); |
|||
# you may not use this file except in compliance with the License. |
|||
# You may obtain a copy of the License at |
|||
# |
|||
# http://www.apache.org/licenses/LICENSE-2.0 |
|||
# |
|||
# Unless required by applicable law or agreed to in writing, software |
|||
# distributed under the License is distributed on an "AS IS" BASIS, |
|||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
|||
# See the License for the specific language governing permissions and |
|||
# limitations under the License. |
|||
|
|||
from logr import Logr |
|||
from caper import FragmentMatcher |
|||
from caper.parsers.base import Parser |
|||
from caper.result import CaperFragmentNode |
|||
|
|||
|
|||
PATTERN_GROUPS = [ |
|||
('identifier', [ |
|||
(1.0, [ |
|||
# S01E01-E02 |
|||
('^S(?P<season>\d+)E(?P<episode_from>\d+)$', '^E(?P<episode_to>\d+)$'), |
|||
# 'S03 E01 to E08' or 'S03 E01 - E09' |
|||
('^S(?P<season>\d+)$', '^E(?P<episode_from>\d+)$', '^(to|-)$', '^E(?P<episode_to>\d+)$'), |
|||
# 'E01 to E08' or 'E01 - E09' |
|||
('^E(?P<episode_from>\d+)$', '^(to|-)$', '^E(?P<episode_to>\d+)$'), |
|||
|
|||
# S01-S03 |
|||
('^S(?P<season_from>\d+)$', '^S(?P<season_to>\d+)$'), |
|||
|
|||
# S02E13 |
|||
r'^S(?P<season>\d+)E(?P<episode>\d+)$', |
|||
# S01 E13 |
|||
(r'^(S(?P<season>\d+))$', r'^(E(?P<episode>\d+))$'), |
|||
# S02 |
|||
# E13 |
|||
r'^((S(?P<season>\d+))|(E(?P<episode>\d+)))$', |
|||
# 3x19 |
|||
r'^(?P<season>\d+)x(?P<episode>\d+)$', |
|||
|
|||
# 2013.09.15 |
|||
(r'^(?P<year>\d{4})$', r'^(?P<month>\d{2})$', r'^(?P<day>\d{2})$'), |
|||
# 09.15.2013 |
|||
(r'^(?P<month>\d{2})$', r'^(?P<day>\d{2})$', r'^(?P<year>\d{4})$'), |
|||
# TODO - US/UK Date Format Conflict? will only support US format for now.. |
|||
# 15.09.2013 |
|||
#(r'^(?P<day>\d{2})$', r'^(?P<month>\d{2})$', r'^(?P<year>\d{4})$'), |
|||
# 130915 |
|||
r'^(?P<year_short>\d{2})(?P<month>\d{2})(?P<day>\d{2})$', |
|||
|
|||
# Season 3 Episode 14 |
|||
(r'^Se(ason)?$', r'^(?P<season>\d+)$', r'^Ep(isode)?$', r'^(?P<episode>\d+)$'), |
|||
# Season 3 |
|||
(r'^Se(ason)?$', r'^(?P<season>\d+)$'), |
|||
# Episode 14 |
|||
(r'^Ep(isode)?$', r'^(?P<episode>\d+)$'), |
|||
|
|||
# Part.3 |
|||
# Part.1.and.Part.3 |
|||
('^Part$', '(?P<part>\d+)'), |
|||
|
|||
r'(?P<extra>Special)', |
|||
r'(?P<country>NZ|AU|US|UK)' |
|||
]), |
|||
(0.8, [ |
|||
# 100 - 1899, 2100 - 9999 (skips 1900 to 2099 - so we don't get years my mistake) |
|||
# TODO - Update this pattern on 31 Dec 2099 |
|||
r'^(?P<season>([1-9])|(1[0-8])|(2[1-9])|([3-9][0-9]))(?P<episode>\d{2})$' |
|||
]), |
|||
(0.5, [ |
|||
# 100 - 9999 |
|||
r'^(?P<season>([1-9])|([1-9][0-9]))(?P<episode>\d{2})$' |
|||
]) |
|||
]), |
|||
|
|||
('video', [ |
|||
r'(?P<aspect>FS|WS)', |
|||
|
|||
(r'(?P<resolution>%s)', [ |
|||
'480p', |
|||
'720p', |
|||
'1080p' |
|||
]), |
|||
|
|||
# |
|||
# Source |
|||
# |
|||
|
|||
(r'(?P<source>%s)', [ |
|||
'DVDRiP', |
|||
# HDTV |
|||
'HDTV', |
|||
'PDTV', |
|||
'DSR', |
|||
# WEB |
|||
'WEBRip', |
|||
'WEBDL', |
|||
# BluRay |
|||
'BluRay', |
|||
'B(D|R)Rip', |
|||
# DVD |
|||
'DVDR', |
|||
'DVD9', |
|||
'DVD5' |
|||
]), |
|||
|
|||
# For multi-fragment 'WEB-DL', 'WEB-Rip', etc... matches |
|||
('(?P<source>WEB)', '(?P<source>DL|Rip)'), |
|||
|
|||
# |
|||
# Codec |
|||
# |
|||
|
|||
(r'(?P<codec>%s)', [ |
|||
'x264', |
|||
'XViD', |
|||
'H264', |
|||
'AVC' |
|||
]), |
|||
|
|||
# For multi-fragment 'H 264' tags |
|||
('(?P<codec>H)', '(?P<codec>264)'), |
|||
]), |
|||
|
|||
('dvd', [ |
|||
r'D(ISC)?(?P<disc>\d+)', |
|||
|
|||
r'R(?P<region>[0-8])', |
|||
|
|||
(r'(?P<encoding>%s)', [ |
|||
'PAL', |
|||
'NTSC' |
|||
]), |
|||
]), |
|||
|
|||
('audio', [ |
|||
(r'(?P<codec>%s)', [ |
|||
'AC3', |
|||
'TrueHD' |
|||
]), |
|||
|
|||
(r'(?P<language>%s)', [ |
|||
'GERMAN', |
|||
'DUTCH', |
|||
'FRENCH', |
|||
'SWEDiSH', |
|||
'DANiSH', |
|||
'iTALiAN' |
|||
]), |
|||
]), |
|||
|
|||
('scene', [ |
|||
r'(?P<proper>PROPER|REAL)', |
|||
]) |
|||
] |
|||
|
|||
|
|||
class SceneParser(Parser): |
|||
matcher = None |
|||
|
|||
def __init__(self, debug=False): |
|||
if not SceneParser.matcher: |
|||
SceneParser.matcher = FragmentMatcher(PATTERN_GROUPS) |
|||
Logr.info("Fragment matcher for %s created", self.__class__.__name__) |
|||
|
|||
super(SceneParser, self).__init__(SceneParser.matcher, debug) |
|||
|
|||
def capture_group(self, fragment): |
|||
if fragment.closure.index + 1 != len(self.closures): |
|||
return None |
|||
|
|||
if fragment.left_sep != '-' or fragment.right: |
|||
return None |
|||
|
|||
return fragment.value |
|||
|
|||
def run(self, closures): |
|||
""" |
|||
:type closures: list of CaperClosure |
|||
""" |
|||
|
|||
self.setup(closures) |
|||
|
|||
self.capture_fragment('show_name', single=False)\ |
|||
.until_fragment(node__re='identifier')\ |
|||
.until_fragment(node__re='video')\ |
|||
.until_fragment(node__re='dvd')\ |
|||
.until_fragment(node__re='audio')\ |
|||
.until_fragment(node__re='scene')\ |
|||
.execute() |
|||
|
|||
self.capture_fragment('identifier', regex='identifier', single=False)\ |
|||
.capture_fragment('video', regex='video', single=False)\ |
|||
.capture_fragment('dvd', regex='dvd', single=False)\ |
|||
.capture_fragment('audio', regex='audio', single=False)\ |
|||
.capture_fragment('scene', regex='scene', single=False)\ |
|||
.until_fragment(left_sep__eq='-', right__eq=None)\ |
|||
.execute() |
|||
|
|||
self.capture_fragment('group', func=self.capture_group)\ |
|||
.execute() |
|||
|
|||
self.print_tree(self.result.heads) |
|||
|
|||
self.result.build() |
|||
return self.result |
|||
|
|||
def print_tree(self, heads): |
|||
if not self.debug: |
|||
return |
|||
|
|||
for head in heads: |
|||
head = head if type(head) is list else [head] |
|||
|
|||
if type(head[0]) is CaperFragmentNode: |
|||
for fragment in head[0].fragments: |
|||
Logr.debug(fragment.value) |
|||
else: |
|||
Logr.debug(head[0].closure.value) |
|||
|
|||
for node in head: |
|||
Logr.debug('\t' + str(node).ljust(55) + '\t' + ( |
|||
str(node.match.weight) + '\t' + str(node.match.result) |
|||
) if node.match else '') |
|||
|
|||
if len(head) > 0 and head[0].parent: |
|||
self.print_tree([head[0].parent]) |
@ -0,0 +1,115 @@ |
|||
# Copyright 2013 Dean Gardiner <gardiner91@gmail.com> |
|||
# |
|||
# Licensed under the Apache License, Version 2.0 (the "License"); |
|||
# you may not use this file except in compliance with the License. |
|||
# You may obtain a copy of the License at |
|||
# |
|||
# http://www.apache.org/licenses/LICENSE-2.0 |
|||
# |
|||
# Unless required by applicable law or agreed to in writing, software |
|||
# distributed under the License is distributed on an "AS IS" BASIS, |
|||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
|||
# See the License for the specific language governing permissions and |
|||
# limitations under the License. |
|||
|
|||
from logr import Logr |
|||
from caper import FragmentMatcher |
|||
from caper.parsers.base import Parser |
|||
|
|||
|
|||
PATTERN_GROUPS = [ |
|||
('usenet', [ |
|||
r'\[(?P<group>#[\w\.@]+)\]', |
|||
r'^\[(?P<code>\w+)\]$', |
|||
r'\[(?P<full>FULL)\]', |
|||
r'\[\s?(?P<group>TOWN)\s?\]', |
|||
r'(.*?\s)?[_\W]*(?P<site>www\..*?\.[a-z0-9]+)[_\W]*(.*?\s)?', |
|||
r'(.*?\s)?[_\W]*(?P<site>(www\.)?[-\w]+\.(com|org|info))[_\W]*(.*?\s)?' |
|||
]), |
|||
|
|||
('part', [ |
|||
r'.?(?P<current>\d+)/(?P<total>\d+).?' |
|||
]), |
|||
|
|||
('detail', [ |
|||
r'[\s-]*\w*?[\s-]*\"(?P<file_name>.*?)\"[\s-]*\w*?[\s-]*(?P<size>[\d,\.]*\s?MB)?[\s-]*(?P<extra>yEnc)?', |
|||
r'(?P<size>[\d,\.]*\s?MB)[\s-]*(?P<extra>yEnc)', |
|||
r'(?P<size>[\d,\.]*\s?MB)|(?P<extra>yEnc)' |
|||
]) |
|||
] |
|||
|
|||
|
|||
class UsenetParser(Parser): |
|||
matcher = None |
|||
|
|||
def __init__(self, debug=False): |
|||
if not UsenetParser.matcher: |
|||
UsenetParser.matcher = FragmentMatcher(PATTERN_GROUPS) |
|||
Logr.info("Fragment matcher for %s created", self.__class__.__name__) |
|||
|
|||
super(UsenetParser, self).__init__(UsenetParser.matcher, debug) |
|||
|
|||
def run(self, closures): |
|||
""" |
|||
:type closures: list of CaperClosure |
|||
""" |
|||
|
|||
self.setup(closures) |
|||
|
|||
# Capture usenet or part info until we get a part or matching fails |
|||
self.capture_closure('usenet', regex='usenet', single=False)\ |
|||
.capture_closure('part', regex='part', single=True) \ |
|||
.until_result(tag='part') \ |
|||
.until_failure()\ |
|||
.execute() |
|||
|
|||
is_town_release, has_part = self.get_state() |
|||
|
|||
if not is_town_release: |
|||
self.capture_release_name() |
|||
|
|||
# If we already have the part (TOWN releases), ignore matching part again |
|||
if not is_town_release and not has_part: |
|||
self.capture_fragment('part', regex='part', single=True)\ |
|||
.until_closure(node__re='usenet')\ |
|||
.until_success()\ |
|||
.execute() |
|||
|
|||
# Capture any leftover details |
|||
self.capture_closure('usenet', regex='usenet', single=False)\ |
|||
.capture_closure('detail', regex='detail', single=False)\ |
|||
.execute() |
|||
|
|||
self.result.build() |
|||
return self.result |
|||
|
|||
def capture_release_name(self): |
|||
self.capture_closure('detail', regex='detail', single=False)\ |
|||
.until_failure()\ |
|||
.execute() |
|||
|
|||
self.capture_fragment('release_name', single=False, include_separators=True) \ |
|||
.until_closure(node__re='usenet') \ |
|||
.until_closure(node__re='detail') \ |
|||
.until_closure(node__re='part') \ |
|||
.until_fragment(value__eq='-')\ |
|||
.execute() |
|||
|
|||
# Capture any detail after the release name |
|||
self.capture_closure('detail', regex='detail', single=False)\ |
|||
.until_failure()\ |
|||
.execute() |
|||
|
|||
def get_state(self): |
|||
# TODO multiple-chains? |
|||
is_town_release = False |
|||
has_part = False |
|||
|
|||
for tag, result in self.result.heads[0].captured(): |
|||
if tag == 'usenet' and result.get('group') == 'TOWN': |
|||
is_town_release = True |
|||
|
|||
if tag == 'part': |
|||
has_part = True |
|||
|
|||
return is_town_release, has_part |
@ -0,0 +1,213 @@ |
|||
# Copyright 2013 Dean Gardiner <gardiner91@gmail.com> |
|||
# |
|||
# Licensed under the Apache License, Version 2.0 (the "License"); |
|||
# you may not use this file except in compliance with the License. |
|||
# You may obtain a copy of the License at |
|||
# |
|||
# http://www.apache.org/licenses/LICENSE-2.0 |
|||
# |
|||
# Unless required by applicable law or agreed to in writing, software |
|||
# distributed under the License is distributed on an "AS IS" BASIS, |
|||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
|||
# See the License for the specific language governing permissions and |
|||
# limitations under the License. |
|||
|
|||
import copy |
|||
from logr import Logr |
|||
|
|||
|
|||
GROUP_MATCHES = ['identifier'] |
|||
|
|||
|
|||
class CaperNode(object): |
|||
def __init__(self, closure, parent=None, match=None): |
|||
""" |
|||
:type parent: CaperNode |
|||
:type weight: float |
|||
""" |
|||
|
|||
#: :type: caper.objects.CaperClosure |
|||
self.closure = closure |
|||
|
|||
#: :type: CaperNode |
|||
self.parent = parent |
|||
|
|||
#: :type: CaptureMatch |
|||
self.match = match |
|||
|
|||
#: :type: list of CaptureGroup |
|||
self.finished_groups = [] |
|||
|
|||
def next(self): |
|||
raise NotImplementedError() |
|||
|
|||
def captured(self): |
|||
cur = self |
|||
|
|||
if cur.match: |
|||
yield cur.match.tag, cur.match.result |
|||
|
|||
while cur.parent: |
|||
cur = cur.parent |
|||
|
|||
if cur.match: |
|||
yield cur.match.tag, cur.match.result |
|||
|
|||
|
|||
class CaperRootNode(CaperNode): |
|||
def __init__(self, closure): |
|||
""" |
|||
:type closure: caper.objects.CaperClosure or list of caper.objects.CaperClosure |
|||
""" |
|||
super(CaperRootNode, self).__init__(closure) |
|||
|
|||
def next(self): |
|||
return self.closure |
|||
|
|||
|
|||
class CaperClosureNode(CaperNode): |
|||
def __init__(self, closure, parent=None, match=None): |
|||
""" |
|||
:type closure: caper.objects.CaperClosure or list of caper.objects.CaperClosure |
|||
""" |
|||
super(CaperClosureNode, self).__init__(closure, parent, match) |
|||
|
|||
def next(self): |
|||
if not self.closure: |
|||
return None |
|||
|
|||
if self.match: |
|||
# Jump to next closure if we have a match |
|||
return self.closure.right |
|||
elif len(self.closure.fragments) > 0: |
|||
# Otherwise parse the fragments |
|||
return self.closure.fragments[0] |
|||
|
|||
return None |
|||
|
|||
def __str__(self): |
|||
return "<CaperClosureNode match: %s>" % repr(self.match) |
|||
|
|||
def __repr__(self): |
|||
return self.__str__() |
|||
|
|||
|
|||
class CaperFragmentNode(CaperNode): |
|||
def __init__(self, closure, fragments, parent=None, match=None): |
|||
""" |
|||
:type closure: caper.objects.CaperClosure |
|||
:type fragments: list of caper.objects.CaperFragment |
|||
""" |
|||
super(CaperFragmentNode, self).__init__(closure, parent, match) |
|||
|
|||
#: :type: caper.objects.CaperFragment or list of caper.objects.CaperFragment |
|||
self.fragments = fragments |
|||
|
|||
def next(self): |
|||
if len(self.fragments) > 0 and self.fragments[-1] and self.fragments[-1].right: |
|||
return self.fragments[-1].right |
|||
|
|||
if self.closure.right: |
|||
return self.closure.right |
|||
|
|||
return None |
|||
|
|||
def __str__(self): |
|||
return "<CaperFragmentNode match: %s>" % repr(self.match) |
|||
|
|||
def __repr__(self): |
|||
return self.__str__() |
|||
|
|||
|
|||
class CaperResult(object): |
|||
def __init__(self): |
|||
#: :type: list of CaperNode |
|||
self.heads = [] |
|||
|
|||
self.chains = [] |
|||
|
|||
def build(self): |
|||
max_matched = 0 |
|||
|
|||
for head in self.heads: |
|||
for chain in self.combine_chain(head): |
|||
if chain.num_matched > max_matched: |
|||
max_matched = chain.num_matched |
|||
|
|||
self.chains.append(chain) |
|||
|
|||
for chain in self.chains: |
|||
chain.weights.append(chain.num_matched / float(max_matched or chain.num_matched or 1)) |
|||
chain.finish() |
|||
|
|||
self.chains.sort(key=lambda chain: chain.weight, reverse=True) |
|||
|
|||
for chain in self.chains: |
|||
Logr.debug("chain weight: %.02f", chain.weight) |
|||
Logr.debug("\tInfo: %s", chain.info) |
|||
|
|||
Logr.debug("\tWeights: %s", chain.weights) |
|||
Logr.debug("\tNumber of Fragments Matched: %s", chain.num_matched) |
|||
|
|||
def combine_chain(self, subject, chain=None): |
|||
nodes = subject if type(subject) is list else [subject] |
|||
|
|||
if chain is None: |
|||
chain = CaperResultChain() |
|||
|
|||
result = [] |
|||
|
|||
for x, node in enumerate(nodes): |
|||
node_chain = chain if x == len(nodes) - 1 else chain.copy() |
|||
|
|||
if not node.parent: |
|||
result.append(node_chain) |
|||
continue |
|||
|
|||
node_chain.update(node) |
|||
result.extend(self.combine_chain(node.parent, node_chain)) |
|||
|
|||
return result |
|||
|
|||
|
|||
class CaperResultChain(object): |
|||
def __init__(self): |
|||
#: :type: float |
|||
self.weight = None |
|||
self.info = {} |
|||
self.num_matched = 0 |
|||
|
|||
self.weights = [] |
|||
|
|||
def update(self, subject): |
|||
""" |
|||
:type subject: CaperFragmentNode |
|||
""" |
|||
if not subject.match or not subject.match.success: |
|||
return |
|||
|
|||
# TODO this should support closure nodes |
|||
if type(subject) is CaperFragmentNode: |
|||
self.num_matched += len(subject.fragments) if subject.fragments is not None else 0 |
|||
|
|||
self.weights.append(subject.match.weight) |
|||
|
|||
if subject.match: |
|||
if subject.match.tag not in self.info: |
|||
self.info[subject.match.tag] = [] |
|||
|
|||
self.info[subject.match.tag].insert(0, subject.match.result) |
|||
|
|||
def finish(self): |
|||
self.weight = sum(self.weights) / len(self.weights) |
|||
|
|||
def copy(self): |
|||
chain = CaperResultChain() |
|||
|
|||
chain.weight = self.weight |
|||
chain.info = copy.deepcopy(self.info) |
|||
|
|||
chain.num_matched = self.num_matched |
|||
chain.weights = copy.copy(self.weights) |
|||
|
|||
return chain |
@ -0,0 +1,96 @@ |
|||
# Copyright 2013 Dean Gardiner <gardiner91@gmail.com> |
|||
# |
|||
# Licensed under the Apache License, Version 2.0 (the "License"); |
|||
# you may not use this file except in compliance with the License. |
|||
# You may obtain a copy of the License at |
|||
# |
|||
# http://www.apache.org/licenses/LICENSE-2.0 |
|||
# |
|||
# Unless required by applicable law or agreed to in writing, software |
|||
# distributed under the License is distributed on an "AS IS" BASIS, |
|||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
|||
# See the License for the specific language governing permissions and |
|||
# limitations under the License. |
|||
|
|||
from caper.objects import CaptureMatch |
|||
from logr import Logr |
|||
|
|||
|
|||
class CaptureStep(object): |
|||
REPR_KEYS = ['regex', 'func', 'single'] |
|||
|
|||
def __init__(self, capture_group, tag, source, regex=None, func=None, single=None, **kwargs): |
|||
#: @type: CaptureGroup |
|||
self.capture_group = capture_group |
|||
|
|||
#: @type: str |
|||
self.tag = tag |
|||
#: @type: str |
|||
self.source = source |
|||
#: @type: str |
|||
self.regex = regex |
|||
#: @type: function |
|||
self.func = func |
|||
#: @type: bool |
|||
self.single = single |
|||
|
|||
self.kwargs = kwargs |
|||
|
|||
self.matched = False |
|||
|
|||
def execute(self, fragment): |
|||
"""Execute step on fragment |
|||
|
|||
:type fragment: CaperFragment |
|||
:rtype : CaptureMatch |
|||
""" |
|||
|
|||
match = CaptureMatch(self.tag, self) |
|||
|
|||
if self.regex: |
|||
weight, result, num_fragments = self.capture_group.parser.matcher.fragment_match(fragment, self.regex) |
|||
Logr.debug('(execute) [regex] tag: "%s"', self.tag) |
|||
|
|||
if not result: |
|||
return match |
|||
|
|||
# Populate CaptureMatch |
|||
match.success = True |
|||
match.weight = weight |
|||
match.result = result |
|||
match.num_fragments = num_fragments |
|||
elif self.func: |
|||
result = self.func(fragment) |
|||
Logr.debug('(execute) [func] %s += "%s"', self.tag, match) |
|||
|
|||
if not result: |
|||
return match |
|||
|
|||
# Populate CaptureMatch |
|||
match.success = True |
|||
match.weight = 1.0 |
|||
match.result = result |
|||
else: |
|||
Logr.debug('(execute) [raw] %s += "%s"', self.tag, fragment.value) |
|||
|
|||
include_separators = self.kwargs.get('include_separators', False) |
|||
|
|||
# Populate CaptureMatch |
|||
match.success = True |
|||
match.weight = 1.0 |
|||
|
|||
if include_separators: |
|||
match.result = (fragment.left_sep, fragment.value, fragment.right_sep) |
|||
else: |
|||
match.result = fragment.value |
|||
|
|||
return match |
|||
|
|||
def __repr__(self): |
|||
attribute_values = [key + '=' + repr(getattr(self, key)) |
|||
for key in self.REPR_KEYS |
|||
if hasattr(self, key) and getattr(self, key)] |
|||
|
|||
attribute_string = ', ' + ', '.join(attribute_values) if len(attribute_values) > 0 else '' |
|||
|
|||
return "CaptureStep('%s'%s)" % (self.tag, attribute_string) |
@ -0,0 +1,225 @@ |
|||
# logr - Simple python logging wrapper |
|||
# Packed by Dean Gardiner <gardiner91@gmail.com> |
|||
# |
|||
# File part of: |
|||
# rdio-sock - Rdio WebSocket Library |
|||
# Copyright (C) 2013 fzza- <fzzzzzzzza@gmail.com> |
|||
|
|||
# This program is free software: you can redistribute it and/or modify |
|||
# it under the terms of the GNU General Public License as published by |
|||
# the Free Software Foundation, either version 3 of the License, or |
|||
# (at your option) any later version. |
|||
|
|||
# This program is distributed in the hope that it will be useful, |
|||
# but WITHOUT ANY WARRANTY; without even the implied warranty of |
|||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
|||
# GNU General Public License for more details. |
|||
|
|||
# You should have received a copy of the GNU General Public License |
|||
# along with this program. If not, see <http://www.gnu.org/licenses/>. |
|||
|
|||
|
|||
import inspect |
|||
import logging |
|||
import os |
|||
import sys |
|||
|
|||
IGNORE = () |
|||
PY3 = sys.version_info[0] == 3 |
|||
|
|||
|
|||
class Logr(object): |
|||
loggers = {} |
|||
handler = None |
|||
|
|||
trace_origin = False |
|||
name = "Logr" |
|||
|
|||
@staticmethod |
|||
def configure(level=logging.WARNING, handler=None, formatter=None, trace_origin=False, name="Logr"): |
|||
"""Configure Logr |
|||
|
|||
@param handler: Logger message handler |
|||
@type handler: logging.Handler or None |
|||
|
|||
@param formatter: Logger message Formatter |
|||
@type formatter: logging.Formatter or None |
|||
""" |
|||
if formatter is None: |
|||
formatter = LogrFormatter() |
|||
|
|||
if handler is None: |
|||
handler = logging.StreamHandler() |
|||
|
|||
handler.setFormatter(formatter) |
|||
handler.setLevel(level) |
|||
Logr.handler = handler |
|||
|
|||
Logr.trace_origin = trace_origin |
|||
Logr.name = name |
|||
|
|||
@staticmethod |
|||
def configure_check(): |
|||
if Logr.handler is None: |
|||
Logr.configure() |
|||
|
|||
@staticmethod |
|||
def _get_name_from_path(filename): |
|||
try: |
|||
return os.path.splitext(os.path.basename(filename))[0] |
|||
except TypeError: |
|||
return "<unknown>" |
|||
|
|||
@staticmethod |
|||
def get_frame_class(frame): |
|||
if len(frame.f_code.co_varnames) <= 0: |
|||
return None |
|||
|
|||
farg = frame.f_code.co_varnames[0] |
|||
|
|||
if farg not in frame.f_locals: |
|||
return None |
|||
|
|||
if farg == 'self': |
|||
return frame.f_locals[farg].__class__ |
|||
|
|||
if farg == 'cls': |
|||
return frame.f_locals[farg] |
|||
|
|||
return None |
|||
|
|||
|
|||
@staticmethod |
|||
def get_logger_name(): |
|||
if not Logr.trace_origin: |
|||
return Logr.name |
|||
|
|||
stack = inspect.stack() |
|||
|
|||
for x in xrange_six(len(stack)): |
|||
frame = stack[x][0] |
|||
name = None |
|||
|
|||
# Try find name of function defined inside a class |
|||
frame_class = Logr.get_frame_class(frame) |
|||
|
|||
if frame_class: |
|||
class_name = frame_class.__name__ |
|||
module_name = frame_class.__module__ |
|||
|
|||
if module_name != '__main__': |
|||
name = module_name + '.' + class_name |
|||
else: |
|||
name = class_name |
|||
|
|||
# Try find name of function defined outside of a class |
|||
if name is None: |
|||
if frame.f_code.co_name in frame.f_globals: |
|||
name = frame.f_globals.get('__name__') |
|||
if name == '__main__': |
|||
name = Logr._get_name_from_path(frame.f_globals.get('__file__')) |
|||
name = name |
|||
elif frame.f_code.co_name == '<module>': |
|||
name = Logr._get_name_from_path(frame.f_globals.get('__file__')) |
|||
|
|||
if name is not None and name not in IGNORE: |
|||
return name |
|||
|
|||
return "" |
|||
|
|||
@staticmethod |
|||
def get_logger(): |
|||
"""Get or create logger (if it does not exist) |
|||
|
|||
@rtype: RootLogger |
|||
""" |
|||
name = Logr.get_logger_name() |
|||
if name not in Logr.loggers: |
|||
Logr.configure_check() |
|||
Logr.loggers[name] = logging.Logger(name) |
|||
Logr.loggers[name].addHandler(Logr.handler) |
|||
return Logr.loggers[name] |
|||
|
|||
@staticmethod |
|||
def debug(msg, *args, **kwargs): |
|||
Logr.get_logger().debug(msg, *args, **kwargs) |
|||
|
|||
@staticmethod |
|||
def info(msg, *args, **kwargs): |
|||
Logr.get_logger().info(msg, *args, **kwargs) |
|||
|
|||
@staticmethod |
|||
def warning(msg, *args, **kwargs): |
|||
Logr.get_logger().warning(msg, *args, **kwargs) |
|||
|
|||
warn = warning |
|||
|
|||
@staticmethod |
|||
def error(msg, *args, **kwargs): |
|||
Logr.get_logger().error(msg, *args, **kwargs) |
|||
|
|||
@staticmethod |
|||
def exception(msg, *args, **kwargs): |
|||
Logr.get_logger().exception(msg, *args, **kwargs) |
|||
|
|||
@staticmethod |
|||
def critical(msg, *args, **kwargs): |
|||
Logr.get_logger().critical(msg, *args, **kwargs) |
|||
|
|||
fatal = critical |
|||
|
|||
@staticmethod |
|||
def log(level, msg, *args, **kwargs): |
|||
Logr.get_logger().log(level, msg, *args, **kwargs) |
|||
|
|||
|
|||
class LogrFormatter(logging.Formatter): |
|||
LENGTH_NAME = 32 |
|||
LENGTH_LEVEL_NAME = 5 |
|||
|
|||
def __init__(self, fmt=None, datefmt=None): |
|||
if sys.version_info[:2] > (2,6): |
|||
super(LogrFormatter, self).__init__(fmt, datefmt) |
|||
else: |
|||
logging.Formatter.__init__(self, fmt, datefmt) |
|||
|
|||
def usesTime(self): |
|||
return True |
|||
|
|||
def format(self, record): |
|||
record.message = record.getMessage() |
|||
if self.usesTime(): |
|||
record.asctime = self.formatTime(record, self.datefmt) |
|||
|
|||
s = "%(asctime)s %(name)s %(levelname)s %(message)s" % { |
|||
'asctime': record.asctime, |
|||
'name': record.name[-self.LENGTH_NAME:].rjust(self.LENGTH_NAME, ' '), |
|||
'levelname': record.levelname[:self.LENGTH_LEVEL_NAME].ljust(self.LENGTH_LEVEL_NAME, ' '), |
|||
'message': record.message |
|||
} |
|||
|
|||
if record.exc_info: |
|||
if not record.exc_text: |
|||
record.exc_text = self.formatException(record.exc_info) |
|||
if record.exc_text: |
|||
if s[-1:] != "\n": |
|||
s += "\n" |
|||
try: |
|||
s += record.exc_text |
|||
except UnicodeError: |
|||
s = s + record.exc_text.decode(sys.getfilesystemencoding(), |
|||
'replace') |
|||
return s |
|||
|
|||
|
|||
def xrange_six(start, stop=None, step=None): |
|||
if stop is not None and step is not None: |
|||
if PY3: |
|||
return range(start, stop, step) |
|||
else: |
|||
return xrange(start, stop, step) |
|||
else: |
|||
if PY3: |
|||
return range(start) |
|||
else: |
|||
return xrange(start) |
@ -0,0 +1,42 @@ |
|||
# Copyright 2013 Dean Gardiner <gardiner91@gmail.com> |
|||
# |
|||
# Licensed under the Apache License, Version 2.0 (the "License"); |
|||
# you may not use this file except in compliance with the License. |
|||
# You may obtain a copy of the License at |
|||
# |
|||
# http://www.apache.org/licenses/LICENSE-2.0 |
|||
# |
|||
# Unless required by applicable law or agreed to in writing, software |
|||
# distributed under the License is distributed on an "AS IS" BASIS, |
|||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
|||
# See the License for the specific language governing permissions and |
|||
# limitations under the License. |
|||
|
|||
|
|||
from qcond.transformers.merge import MergeTransformer |
|||
from qcond.transformers.slice import SliceTransformer |
|||
from qcond.transformers.strip_common import StripCommonTransformer |
|||
|
|||
|
|||
__version_info__ = ('0', '1', '0') |
|||
__version_branch__ = 'master' |
|||
|
|||
__version__ = "%s%s" % ( |
|||
'.'.join(__version_info__), |
|||
'-' + __version_branch__ if __version_branch__ else '' |
|||
) |
|||
|
|||
|
|||
class QueryCondenser(object): |
|||
def __init__(self): |
|||
self.transformers = [ |
|||
MergeTransformer(), |
|||
SliceTransformer(), |
|||
StripCommonTransformer() |
|||
] |
|||
|
|||
def distinct(self, titles): |
|||
for transformer in self.transformers: |
|||
titles = transformer.run(titles) |
|||
|
|||
return titles |
@ -0,0 +1,23 @@ |
|||
# Copyright 2013 Dean Gardiner <gardiner91@gmail.com> |
|||
# |
|||
# Licensed under the Apache License, Version 2.0 (the "License"); |
|||
# you may not use this file except in compliance with the License. |
|||
# You may obtain a copy of the License at |
|||
# |
|||
# http://www.apache.org/licenses/LICENSE-2.0 |
|||
# |
|||
# Unless required by applicable law or agreed to in writing, software |
|||
# distributed under the License is distributed on an "AS IS" BASIS, |
|||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
|||
# See the License for the specific language governing permissions and |
|||
# limitations under the License. |
|||
|
|||
|
|||
import sys |
|||
|
|||
PY3 = sys.version_info[0] == 3 |
|||
|
|||
if PY3: |
|||
xrange = range |
|||
else: |
|||
xrange = xrange |
@ -0,0 +1,84 @@ |
|||
# Copyright 2013 Dean Gardiner <gardiner91@gmail.com> |
|||
# |
|||
# Licensed under the Apache License, Version 2.0 (the "License"); |
|||
# you may not use this file except in compliance with the License. |
|||
# You may obtain a copy of the License at |
|||
# |
|||
# http://www.apache.org/licenses/LICENSE-2.0 |
|||
# |
|||
# Unless required by applicable law or agreed to in writing, software |
|||
# distributed under the License is distributed on an "AS IS" BASIS, |
|||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
|||
# See the License for the specific language governing permissions and |
|||
# limitations under the License. |
|||
|
|||
|
|||
from difflib import SequenceMatcher |
|||
import re |
|||
import sys |
|||
from logr import Logr |
|||
from qcond.compat import xrange |
|||
|
|||
|
|||
PY3 = sys.version_info[0] == 3 |
|||
|
|||
|
|||
def simplify(s): |
|||
s = s.lower() |
|||
s = re.sub(r"(\w)'(\w)", r"\1\2", s) |
|||
return s |
|||
|
|||
|
|||
def strip(s): |
|||
return re.sub(r"^(\W*)(.*?)(\W*)$", r"\2", s) |
|||
|
|||
|
|||
def create_matcher(a, b, swap_longest = True, case_sensitive = False): |
|||
# Ensure longest string is a |
|||
if swap_longest and len(b) > len(a): |
|||
a_ = a |
|||
a = b |
|||
b = a_ |
|||
|
|||
if not case_sensitive: |
|||
a = a.upper() |
|||
b = b.upper() |
|||
|
|||
return SequenceMatcher(None, a, b) |
|||
|
|||
|
|||
def first(function_or_none, sequence): |
|||
if PY3: |
|||
for item in filter(function_or_none, sequence): |
|||
return item |
|||
else: |
|||
result = filter(function_or_none, sequence) |
|||
if len(result): |
|||
return result[0] |
|||
|
|||
return None |
|||
|
|||
def sorted_append(sequence, item, func): |
|||
if not len(sequence): |
|||
sequence.insert(0, item) |
|||
return |
|||
|
|||
x = 0 |
|||
for x in xrange(len(sequence)): |
|||
if func(sequence[x]): |
|||
sequence.insert(x, item) |
|||
return |
|||
|
|||
sequence.append(item) |
|||
|
|||
def itemsMatch(L1, L2): |
|||
return len(L1) == len(L2) and sorted(L1) == sorted(L2) |
|||
|
|||
def distinct(sequence): |
|||
result = [] |
|||
|
|||
for item in sequence: |
|||
if item not in result: |
|||
result.append(item) |
|||
|
|||
return result |
@ -0,0 +1,21 @@ |
|||
# Copyright 2013 Dean Gardiner <gardiner91@gmail.com> |
|||
# |
|||
# Licensed under the Apache License, Version 2.0 (the "License"); |
|||
# you may not use this file except in compliance with the License. |
|||
# You may obtain a copy of the License at |
|||
# |
|||
# http://www.apache.org/licenses/LICENSE-2.0 |
|||
# |
|||
# Unless required by applicable law or agreed to in writing, software |
|||
# distributed under the License is distributed on an "AS IS" BASIS, |
|||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
|||
# See the License for the specific language governing permissions and |
|||
# limitations under the License. |
|||
|
|||
|
|||
class Transformer(object): |
|||
def __init__(self): |
|||
pass |
|||
|
|||
def run(self, titles): |
|||
raise NotImplementedError() |
@ -0,0 +1,241 @@ |
|||
# Copyright 2013 Dean Gardiner <gardiner91@gmail.com> |
|||
# |
|||
# Licensed under the Apache License, Version 2.0 (the "License"); |
|||
# you may not use this file except in compliance with the License. |
|||
# You may obtain a copy of the License at |
|||
# |
|||
# http://www.apache.org/licenses/LICENSE-2.0 |
|||
# |
|||
# Unless required by applicable law or agreed to in writing, software |
|||
# distributed under the License is distributed on an "AS IS" BASIS, |
|||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
|||
# See the License for the specific language governing permissions and |
|||
# limitations under the License. |
|||
|
|||
|
|||
from operator import itemgetter |
|||
from logr import Logr |
|||
from qcond.helpers import simplify, strip, first, sorted_append, distinct |
|||
from qcond.transformers.base import Transformer |
|||
from qcond.compat import xrange |
|||
|
|||
|
|||
class MergeTransformer(Transformer): |
|||
def __init__(self): |
|||
super(MergeTransformer, self).__init__() |
|||
|
|||
def run(self, titles): |
|||
titles = distinct([simplify(title) for title in titles]) |
|||
|
|||
Logr.info(str(titles)) |
|||
|
|||
Logr.debug("------------------------------------------------------------") |
|||
|
|||
root, tails = self.parse(titles) |
|||
|
|||
Logr.debug("--------------------------PARSE-----------------------------") |
|||
|
|||
for node in root: |
|||
print_tree(node) |
|||
|
|||
Logr.debug("--------------------------MERGE-----------------------------") |
|||
|
|||
self.merge(root) |
|||
|
|||
Logr.debug("--------------------------FINAL-----------------------------") |
|||
|
|||
for node in root: |
|||
print_tree(node) |
|||
|
|||
Logr.debug("--------------------------RESULT-----------------------------") |
|||
|
|||
scores = {} |
|||
results = [] |
|||
|
|||
for tail in tails: |
|||
score, value, original_value = tail.full_value() |
|||
|
|||
if value in scores: |
|||
scores[value] += score |
|||
else: |
|||
results.append((value, original_value)) |
|||
scores[value] = score |
|||
|
|||
Logr.debug("%s %s %s", score, value, original_value) |
|||
|
|||
sorted_results = sorted(results, key=lambda item: (scores[item[0]], item[1]), reverse = True) |
|||
|
|||
return [result[0] for result in sorted_results] |
|||
|
|||
def parse(self, titles): |
|||
root = [] |
|||
tails = [] |
|||
|
|||
for title in titles: |
|||
Logr.debug(title) |
|||
|
|||
cur = None |
|||
words = title.split(' ') |
|||
|
|||
for wx in xrange(len(words)): |
|||
word = strip(words[wx]) |
|||
|
|||
if cur is None: |
|||
cur = find_node(root, word) |
|||
|
|||
if cur is None: |
|||
cur = DNode(word, None, num_children=len(words) - wx, original_value=title) |
|||
root.append(cur) |
|||
else: |
|||
parent = cur |
|||
parent.weight += 1 |
|||
|
|||
cur = find_node(parent.right, word) |
|||
|
|||
if cur is None: |
|||
Logr.debug("%s %d", word, len(words) - wx) |
|||
cur = DNode(word, parent, num_children=len(words) - wx) |
|||
sorted_append(parent.right, cur, lambda a: a.num_children < cur.num_children) |
|||
else: |
|||
cur.weight += 1 |
|||
|
|||
tails.append(cur) |
|||
|
|||
return root, tails |
|||
|
|||
def merge(self, root): |
|||
for x in range(len(root)): |
|||
Logr.debug(root[x]) |
|||
root[x].right = self._merge(root[x].right) |
|||
Logr.debug('=================================================================') |
|||
|
|||
return root |
|||
|
|||
def get_nodes_right(self, value): |
|||
if type(value) is not list: |
|||
value = [value] |
|||
|
|||
nodes = [] |
|||
|
|||
for node in value: |
|||
nodes.append(node) |
|||
|
|||
for child in self.get_nodes_right(node.right): |
|||
nodes.append(child) |
|||
|
|||
return nodes |
|||
|
|||
def destroy_nodes_right(self, value): |
|||
nodes = self.get_nodes_right(value) |
|||
|
|||
for node in nodes: |
|||
node.value = None |
|||
node.dead = True |
|||
|
|||
def _merge(self, nodes, depth = 0): |
|||
Logr.debug(str('\t' * depth) + str(nodes)) |
|||
|
|||
if not len(nodes): |
|||
return [] |
|||
|
|||
top = nodes[0] |
|||
|
|||
# Merge into top |
|||
for x in range(len(nodes)): |
|||
# Merge extra results into top |
|||
if x > 0: |
|||
top.value = None |
|||
top.weight += nodes[x].weight |
|||
self.destroy_nodes_right(top.right) |
|||
|
|||
if len(nodes[x].right): |
|||
top.join_right(nodes[x].right) |
|||
|
|||
Logr.debug("= %s joined %s", nodes[x], top) |
|||
|
|||
nodes[x].dead = True |
|||
|
|||
nodes = [n for n in nodes if not n.dead] |
|||
|
|||
# Traverse further |
|||
for node in nodes: |
|||
if len(node.right): |
|||
node.right = self._merge(node.right, depth + 1) |
|||
|
|||
return nodes |
|||
|
|||
|
|||
def print_tree(node, depth = 0): |
|||
Logr.debug(str('\t' * depth) + str(node)) |
|||
|
|||
if len(node.right): |
|||
for child in node.right: |
|||
print_tree(child, depth + 1) |
|||
else: |
|||
Logr.debug(node.full_value()[1]) |
|||
|
|||
|
|||
def find_node(node_list, value): |
|||
# Try find adjacent node match |
|||
for node in node_list: |
|||
if node.value == value: |
|||
return node |
|||
|
|||
return None |
|||
|
|||
|
|||
class DNode(object): |
|||
def __init__(self, value, parent, right=None, weight=1, num_children=None, original_value=None): |
|||
self.value = value |
|||
|
|||
self.parent = parent |
|||
|
|||
if right is None: |
|||
right = [] |
|||
self.right = right |
|||
|
|||
self.weight = weight |
|||
|
|||
self.original_value = original_value |
|||
self.num_children = num_children |
|||
|
|||
self.dead = False |
|||
|
|||
def join_right(self, nodes): |
|||
for node in nodes: |
|||
duplicate = first(lambda x: x.value == node.value, self.right) |
|||
|
|||
if duplicate: |
|||
duplicate.weight += node.weight |
|||
duplicate.join_right(node.right) |
|||
else: |
|||
node.parent = self |
|||
self.right.append(node) |
|||
|
|||
def full_value(self): |
|||
words = [] |
|||
total_score = 0 |
|||
|
|||
cur = self |
|||
root = None |
|||
|
|||
while cur is not None: |
|||
if cur.value and not cur.dead: |
|||
words.insert(0, cur.value) |
|||
total_score += cur.weight |
|||
|
|||
if cur.parent is None: |
|||
root = cur |
|||
cur = cur.parent |
|||
|
|||
return float(total_score) / len(words), ' '.join(words), root.original_value if root else None |
|||
|
|||
def __repr__(self): |
|||
return '<%s value:"%s", weight: %s, num_children: %s%s%s>' % ( |
|||
'DNode', |
|||
self.value, |
|||
self.weight, |
|||
self.num_children, |
|||
(', original_value: %s' % self.original_value) if self.original_value else '', |
|||
' REMOVING' if self.dead else '' |
|||
) |
@ -0,0 +1,280 @@ |
|||
# Copyright 2013 Dean Gardiner <gardiner91@gmail.com> |
|||
# |
|||
# Licensed under the Apache License, Version 2.0 (the "License"); |
|||
# you may not use this file except in compliance with the License. |
|||
# You may obtain a copy of the License at |
|||
# |
|||
# http://www.apache.org/licenses/LICENSE-2.0 |
|||
# |
|||
# Unless required by applicable law or agreed to in writing, software |
|||
# distributed under the License is distributed on an "AS IS" BASIS, |
|||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
|||
# See the License for the specific language governing permissions and |
|||
# limitations under the License. |
|||
|
|||
|
|||
from logr import Logr |
|||
from qcond.helpers import create_matcher |
|||
from qcond.transformers.base import Transformer |
|||
|
|||
|
|||
class SliceTransformer(Transformer): |
|||
def __init__(self): |
|||
super(SliceTransformer, self).__init__() |
|||
|
|||
def run(self, titles): |
|||
nodes = [] |
|||
|
|||
# Create a node for each title |
|||
for title in titles: |
|||
nodes.append(SimNode(title)) |
|||
|
|||
# Calculate similarities between nodes |
|||
for node in nodes: |
|||
calculate_sim_links(node, [n for n in nodes if n != node]) |
|||
|
|||
kill_nodes_above(nodes, 0.90) |
|||
|
|||
Logr.debug('---------------------------------------------------------------------') |
|||
|
|||
print_link_tree(nodes) |
|||
Logr.debug('%s %s', len(nodes), [n.value for n in nodes]) |
|||
|
|||
Logr.debug('---------------------------------------------------------------------') |
|||
|
|||
kill_trailing_nodes(nodes) |
|||
|
|||
Logr.debug('---------------------------------------------------------------------') |
|||
|
|||
# Sort remaining nodes by 'num_merges' |
|||
nodes = sorted(nodes, key=lambda n: n.num_merges, reverse=True) |
|||
|
|||
print_link_tree(nodes) |
|||
|
|||
Logr.debug('---------------------------------------------------------------------') |
|||
|
|||
Logr.debug('%s %s', len(nodes), [n.value for n in nodes]) |
|||
|
|||
return [n.value for n in nodes] |
|||
|
|||
|
|||
class SimLink(object): |
|||
def __init__(self, similarity, opcodes, stats): |
|||
self.similarity = similarity |
|||
self.opcodes = opcodes |
|||
self.stats = stats |
|||
|
|||
|
|||
class SimNode(object): |
|||
def __init__(self, value): |
|||
self.value = value |
|||
|
|||
self.dead = False |
|||
self.num_merges = 0 |
|||
|
|||
self.links = {} # {<other SimNode>: <SimLink>} |
|||
|
|||
|
|||
def kill_nodes(nodes, killed_nodes): |
|||
# Remove killed nodes from root list |
|||
for node in killed_nodes: |
|||
if node in nodes: |
|||
nodes.remove(node) |
|||
|
|||
# Remove killed nodes from links |
|||
for killed_node in killed_nodes: |
|||
for node in nodes: |
|||
if killed_node in node.links: |
|||
node.links.pop(killed_node) |
|||
|
|||
|
|||
def kill_nodes_above(nodes, above_sim): |
|||
killed_nodes = [] |
|||
|
|||
for node in nodes: |
|||
if node.dead: |
|||
continue |
|||
|
|||
Logr.debug(node.value) |
|||
|
|||
for link_node, link in node.links.items(): |
|||
if link_node.dead: |
|||
continue |
|||
|
|||
Logr.debug('\t%0.2f -- %s', link.similarity, link_node.value) |
|||
|
|||
if link.similarity >= above_sim: |
|||
if len(link_node.value) > len(node.value): |
|||
Logr.debug('\t\tvery similar, killed this node') |
|||
link_node.dead = True |
|||
node.num_merges += 1 |
|||
killed_nodes.append(link_node) |
|||
else: |
|||
Logr.debug('\t\tvery similar, killed owner') |
|||
node.dead = True |
|||
link_node.num_merges += 1 |
|||
killed_nodes.append(node) |
|||
|
|||
kill_nodes(nodes, killed_nodes) |
|||
|
|||
|
|||
def print_link_tree(nodes): |
|||
for node in nodes: |
|||
Logr.debug(node.value) |
|||
Logr.debug('\tnum_merges: %s', node.num_merges) |
|||
|
|||
if len(node.links): |
|||
Logr.debug('\t========== LINKS ==========') |
|||
for link_node, link in node.links.items(): |
|||
Logr.debug('\t%0.2f -- %s', link.similarity, link_node.value) |
|||
|
|||
Logr.debug('\t---------------------------') |
|||
|
|||
|
|||
def kill_trailing_nodes(nodes): |
|||
killed_nodes = [] |
|||
|
|||
for node in nodes: |
|||
if node.dead: |
|||
continue |
|||
|
|||
Logr.debug(node.value) |
|||
|
|||
for link_node, link in node.links.items(): |
|||
if link_node.dead: |
|||
continue |
|||
|
|||
is_valid = link.stats.get('valid', False) |
|||
|
|||
has_deletions = False |
|||
has_insertions = False |
|||
has_replacements = False |
|||
|
|||
for opcode in link.opcodes: |
|||
if opcode[0] == 'delete': |
|||
has_deletions = True |
|||
if opcode[0] == 'insert': |
|||
has_insertions = True |
|||
if opcode[0] == 'replace': |
|||
has_replacements = True |
|||
|
|||
equal_perc = link.stats.get('equal', 0) / float(len(node.value)) |
|||
insert_perc = link.stats.get('insert', 0) / float(len(node.value)) |
|||
|
|||
Logr.debug('\t({0:<24}) [{1:02d}:{2:02d} = {3:02d} {4:3.0f}% {5:3.0f}%] -- {6:<45}'.format( |
|||
'd:%s, i:%s, r:%s' % (has_deletions, has_insertions, has_replacements), |
|||
len(node.value), len(link_node.value), link.stats.get('equal', 0), |
|||
equal_perc * 100, insert_perc * 100, |
|||
'"{0}"'.format(link_node.value) |
|||
)) |
|||
|
|||
Logr.debug('\t\t%s', link.stats) |
|||
|
|||
kill = all([ |
|||
is_valid, |
|||
equal_perc >= 0.5, |
|||
insert_perc < 2, |
|||
has_insertions, |
|||
not has_deletions, |
|||
not has_replacements |
|||
]) |
|||
|
|||
if kill: |
|||
Logr.debug('\t\tkilled this node') |
|||
|
|||
link_node.dead = True |
|||
node.num_merges += 1 |
|||
killed_nodes.append(link_node) |
|||
|
|||
kill_nodes(nodes, killed_nodes) |
|||
|
|||
stats_print_format = "\t{0:<8} ({1:2d}:{2:2d}) ({3:2d}:{4:2d})" |
|||
|
|||
|
|||
def get_index_values(iterable, a, b): |
|||
return ( |
|||
iterable[a] if a else None, |
|||
iterable[b] if b else None |
|||
) |
|||
|
|||
|
|||
def get_indices(iterable, a, b): |
|||
return ( |
|||
a if 0 < a < len(iterable) else None, |
|||
b if 0 < b < len(iterable) else None |
|||
) |
|||
|
|||
|
|||
def get_opcode_stats(for_node, node, opcodes): |
|||
stats = {} |
|||
|
|||
for tag, i1, i2, j1, j2 in opcodes: |
|||
Logr.debug(stats_print_format.format( |
|||
tag, i1, i2, j1, j2 |
|||
)) |
|||
|
|||
if tag in ['insert', 'delete']: |
|||
ax = None, None |
|||
bx = None, None |
|||
|
|||
if tag == 'insert': |
|||
ax = get_indices(for_node.value, i1 - 1, i1) |
|||
bx = get_indices(node.value, j1, j2 - 1) |
|||
|
|||
if tag == 'delete': |
|||
ax = get_indices(for_node.value, j1 - 1, j1) |
|||
bx = get_indices(node.value, i1, i2 - 1) |
|||
|
|||
av = get_index_values(for_node.value, *ax) |
|||
bv = get_index_values(node.value, *bx) |
|||
|
|||
Logr.debug( |
|||
'\t\t%s %s [%s><%s] <---> %s %s [%s><%s]', |
|||
ax, av, av[0], av[1], |
|||
bx, bv, bv[0], bv[1] |
|||
) |
|||
|
|||
head_valid = av[0] in [None, ' '] or bv[0] in [None, ' '] |
|||
tail_valid = av[1] in [None, ' '] or bv[1] in [None, ' '] |
|||
valid = head_valid and tail_valid |
|||
|
|||
if 'valid' not in stats or (stats['valid'] and not valid): |
|||
stats['valid'] = valid |
|||
|
|||
Logr.debug('\t\t' + ('VALID' if valid else 'INVALID')) |
|||
|
|||
if tag not in stats: |
|||
stats[tag] = 0 |
|||
|
|||
stats[tag] += (i2 - i1) or (j2 - j1) |
|||
|
|||
return stats |
|||
|
|||
|
|||
def calculate_sim_links(for_node, other_nodes): |
|||
for node in other_nodes: |
|||
if node in for_node.links: |
|||
continue |
|||
|
|||
Logr.debug('calculating similarity between "%s" and "%s"', for_node.value, node.value) |
|||
|
|||
# Get similarity |
|||
similarity_matcher = create_matcher(for_node.value, node.value) |
|||
similarity = similarity_matcher.quick_ratio() |
|||
|
|||
# Get for_node -> node opcodes |
|||
a_opcodes_matcher = create_matcher(for_node.value, node.value, swap_longest = False) |
|||
a_opcodes = a_opcodes_matcher.get_opcodes() |
|||
a_stats = get_opcode_stats(for_node, node, a_opcodes) |
|||
|
|||
Logr.debug('-' * 100) |
|||
|
|||
# Get node -> for_node opcodes |
|||
b_opcodes_matcher = create_matcher(node.value, for_node.value, swap_longest = False) |
|||
b_opcodes = b_opcodes_matcher.get_opcodes() |
|||
b_stats = get_opcode_stats(for_node, node, b_opcodes) |
|||
|
|||
for_node.links[node] = SimLink(similarity, a_opcodes, a_stats) |
|||
node.links[for_node] = SimLink(similarity, b_opcodes, b_stats) |
|||
|
|||
#raw_input('Press ENTER to continue') |
@ -0,0 +1,26 @@ |
|||
# Copyright 2013 Dean Gardiner <gardiner91@gmail.com> |
|||
# |
|||
# Licensed under the Apache License, Version 2.0 (the "License"); |
|||
# you may not use this file except in compliance with the License. |
|||
# You may obtain a copy of the License at |
|||
# |
|||
# http://www.apache.org/licenses/LICENSE-2.0 |
|||
# |
|||
# Unless required by applicable law or agreed to in writing, software |
|||
# distributed under the License is distributed on an "AS IS" BASIS, |
|||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
|||
# See the License for the specific language governing permissions and |
|||
# limitations under the License. |
|||
|
|||
|
|||
from qcond.transformers.base import Transformer |
|||
|
|||
|
|||
COMMON_WORDS = [ |
|||
'the' |
|||
] |
|||
|
|||
|
|||
class StripCommonTransformer(Transformer): |
|||
def run(self, titles): |
|||
return [title for title in titles if title.lower() not in COMMON_WORDS] |
@ -0,0 +1,4 @@ |
|||
.DS_Store |
|||
*.pyc |
|||
*.egg-info/* |
|||
dist/*.tar.gz |
@ -0,0 +1,9 @@ |
|||
language: python |
|||
python: |
|||
- 2.5 |
|||
- 2.6 |
|||
- 2.7 |
|||
|
|||
install: pip install nose |
|||
|
|||
script: nosetests |
@ -0,0 +1,4 @@ |
|||
include UNLICENSE |
|||
include readme.md |
|||
include tests/*.py |
|||
include Rakefile |
@ -0,0 +1,103 @@ |
|||
require 'fileutils' |
|||
|
|||
task :default => [:clean] |
|||
|
|||
task :clean do |
|||
[".", "tests"].each do |cd| |
|||
puts "Cleaning directory #{cd}" |
|||
Dir.new(cd).each do |t| |
|||
if t =~ /.*\.pyc$/ |
|||
puts "Removing #{File.join(cd, t)}" |
|||
File.delete(File.join(cd, t)) |
|||
end |
|||
end |
|||
end |
|||
end |
|||
|
|||
desc "Upversion files" |
|||
task :upversion do |
|||
puts "Upversioning" |
|||
|
|||
Dir.glob("*.py").each do |filename| |
|||
f = File.new(filename, File::RDWR) |
|||
contents = f.read() |
|||
|
|||
contents.gsub!(/__version__ = ".+?"/){|m| |
|||
cur_version = m.scan(/\d+\.\d+/)[0].to_f |
|||
new_version = cur_version + 0.1 |
|||
|
|||
puts "Current version: #{cur_version}" |
|||
puts "New version: #{new_version}" |
|||
|
|||
new_line = "__version__ = \"#{new_version}\"" |
|||
|
|||
puts "Old line: #{m}" |
|||
puts "New line: #{new_line}" |
|||
|
|||
m = new_line |
|||
} |
|||
|
|||
puts contents[0] |
|||
|
|||
f.truncate(0) # empty the existing file |
|||
f.seek(0) |
|||
f.write(contents.to_s) # write modified file |
|||
f.close() |
|||
end |
|||
end |
|||
|
|||
desc "Upload current version to PyPi" |
|||
task :topypi => :test do |
|||
cur_file = File.open("tvdb_api.py").read() |
|||
tvdb_api_version = cur_file.scan(/__version__ = "(.*)"/) |
|||
tvdb_api_version = tvdb_api_version[0][0].to_f |
|||
|
|||
puts "Build sdist and send tvdb_api v#{tvdb_api_version} to PyPi?" |
|||
if $stdin.gets.chomp == "y" |
|||
puts "Sending source-dist (sdist) to PyPi" |
|||
|
|||
if system("python setup.py sdist register upload") |
|||
puts "tvdb_api uploaded!" |
|||
end |
|||
|
|||
else |
|||
puts "Cancelled" |
|||
end |
|||
end |
|||
|
|||
desc "Profile by running unittests" |
|||
task :profile do |
|||
cd "tests" |
|||
puts "Profiling.." |
|||
`python -m cProfile -o prof_runtest.prof runtests.py` |
|||
puts "Converting prof to dot" |
|||
`python gprof2dot.py -o prof_runtest.dot -f pstats prof_runtest.prof` |
|||
puts "Generating graph" |
|||
`~/Applications/dev/graphviz.app/Contents/macOS/dot -Tpng -o profile.png prof_runtest.dot -Gbgcolor=black` |
|||
puts "Cleanup" |
|||
rm "prof_runtest.dot" |
|||
rm "prof_runtest.prof" |
|||
end |
|||
|
|||
task :test do |
|||
puts "Nosetest'ing" |
|||
if not system("nosetests -v --with-doctest") |
|||
raise "Test failed!" |
|||
end |
|||
|
|||
puts "Doctesting *.py (excluding setup.py)" |
|||
Dir.glob("*.py").select{|e| ! e.match(/setup.py/)}.each do |filename| |
|||
if filename =~ /^setup\.py/ |
|||
skip |
|||
end |
|||
puts "Doctesting #{filename}" |
|||
if not system("python", "-m", "doctest", filename) |
|||
raise "Failed doctest" |
|||
end |
|||
end |
|||
|
|||
puts "Doctesting readme.md" |
|||
if not system("python", "-m", "doctest", "readme.md") |
|||
raise "Doctest" |
|||
end |
|||
end |
@ -0,0 +1,26 @@ |
|||
Copyright 2011-2012 Ben Dickson (dbr) |
|||
|
|||
This is free and unencumbered software released into the public domain. |
|||
|
|||
Anyone is free to copy, modify, publish, use, compile, sell, or |
|||
distribute this software, either in source code form or as a compiled |
|||
binary, for any purpose, commercial or non-commercial, and by any |
|||
means. |
|||
|
|||
In jurisdictions that recognize copyright laws, the author or authors |
|||
of this software dedicate any and all copyright interest in the |
|||
software to the public domain. We make this dedication for the benefit |
|||
of the public at large and to the detriment of our heirs and |
|||
successors. We intend this dedication to be an overt act of |
|||
relinquishment in perpetuity of all present and future rights to this |
|||
software under copyright law. |
|||
|
|||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, |
|||
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF |
|||
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. |
|||
IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR |
|||
OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, |
|||
ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR |
|||
OTHER DEALINGS IN THE SOFTWARE. |
|||
|
|||
For more information, please refer to <http://unlicense.org/> |
@ -0,0 +1,109 @@ |
|||
# `tvdb_api` |
|||
|
|||
`tvdb_api` is an easy to use interface to [thetvdb.com][tvdb] |
|||
|
|||
`tvnamer` has moved to a separate repository: [github.com/dbr/tvnamer][tvnamer] - it is a utility which uses `tvdb_api` to rename files from `some.show.s01e03.blah.abc.avi` to `Some Show - [01x03] - The Episode Name.avi` (which works by getting the episode name from `tvdb_api`) |
|||
|
|||
[](http://travis-ci.org/dbr/tvdb_api) |
|||
|
|||
## To install |
|||
|
|||
You can easily install `tvdb_api` via `easy_install` |
|||
|
|||
easy_install tvdb_api |
|||
|
|||
You may need to use sudo, depending on your setup: |
|||
|
|||
sudo easy_install tvdb_api |
|||
|
|||
The [`tvnamer`][tvnamer] command-line tool can also be installed via `easy_install`, this installs `tvdb_api` as a dependancy: |
|||
|
|||
easy_install tvnamer |
|||
|
|||
|
|||
## Basic usage |
|||
|
|||
import tvdb_api |
|||
t = tvdb_api.Tvdb() |
|||
episode = t['My Name Is Earl'][1][3] # get season 1, episode 3 of show |
|||
print episode['episodename'] # Print episode name |
|||
|
|||
## Advanced usage |
|||
|
|||
Most of the documentation is in docstrings. The examples are tested (using doctest) so will always be up to date and working. |
|||
|
|||
The docstring for `Tvdb.__init__` lists all initialisation arguments, including support for non-English searches, custom "Select Series" interfaces and enabling the retrieval of banners and extended actor information. You can also override the default API key using `apikey`, recommended if you're using `tvdb_api` in a larger script or application |
|||
|
|||
### Exceptions |
|||
|
|||
There are several exceptions you may catch, these can be imported from `tvdb_api`: |
|||
|
|||
- `tvdb_error` - this is raised when there is an error communicating with [thetvdb.com][tvdb] (a network error most commonly) |
|||
- `tvdb_userabort` - raised when a user aborts the Select Series dialog (by `ctrl+c`, or entering `q`) |
|||
- `tvdb_shownotfound` - raised when `t['show name']` cannot find anything |
|||
- `tvdb_seasonnotfound` - raised when the requested series (`t['show name][99]`) does not exist |
|||
- `tvdb_episodenotfound` - raised when the requested episode (`t['show name][1][99]`) does not exist. |
|||
- `tvdb_attributenotfound` - raised when the requested attribute is not found (`t['show name']['an attribute']`, `t['show name'][1]['an attribute']`, or ``t['show name'][1][1]['an attribute']``) |
|||
|
|||
### Series data |
|||
|
|||
All data exposed by [thetvdb.com][tvdb] is accessible via the `Show` class. A Show is retrieved by doing.. |
|||
|
|||
>>> import tvdb_api |
|||
>>> t = tvdb_api.Tvdb() |
|||
>>> show = t['scrubs'] |
|||
>>> type(show) |
|||
<class 'tvdb_api.Show'> |
|||
|
|||
For example, to find out what network Scrubs is aired: |
|||
|
|||
>>> t['scrubs']['network'] |
|||
u'ABC' |
|||
|
|||
The data is stored in an attribute named `data`, within the Show instance: |
|||
|
|||
>>> t['scrubs'].data.keys() |
|||
['networkid', 'rating', 'airs_dayofweek', 'contentrating', 'seriesname', 'id', 'airs_time', 'network', 'fanart', 'lastupdated', 'actors', 'ratingcount', 'status', 'added', 'poster', 'imdb_id', 'genre', 'banner', 'seriesid', 'language', 'zap2it_id', 'addedby', 'firstaired', 'runtime', 'overview'] |
|||
|
|||
Although each element is also accessible via `t['scrubs']` for ease-of-use: |
|||
|
|||
>>> t['scrubs']['rating'] |
|||
u'9.0' |
|||
|
|||
This is the recommended way of retrieving "one-off" data (for example, if you are only interested in "seriesname"). If you wish to iterate over all data, or check if a particular show has a specific piece of data, use the `data` attribute, |
|||
|
|||
>>> 'rating' in t['scrubs'].data |
|||
True |
|||
|
|||
### Banners and actors |
|||
|
|||
Since banners and actors are separate XML files, retrieving them by default is undesirable. If you wish to retrieve banners (and other fanart), use the `banners` Tvdb initialisation argument: |
|||
|
|||
>>> from tvdb_api import Tvdb |
|||
>>> t = Tvdb(banners = True) |
|||
|
|||
Then access the data using a `Show`'s `_banner` key: |
|||
|
|||
>>> t['scrubs']['_banners'].keys() |
|||
['fanart', 'poster', 'series', 'season'] |
|||
|
|||
The banner data structure will be improved in future versions. |
|||
|
|||
Extended actor data is accessible similarly: |
|||
|
|||
>>> t = Tvdb(actors = True) |
|||
>>> actors = t['scrubs']['_actors'] |
|||
>>> actors[0] |
|||
<Actor "Zach Braff"> |
|||
>>> actors[0].keys() |
|||
['sortorder', 'image', 'role', 'id', 'name'] |
|||
>>> actors[0]['role'] |
|||
u'Dr. John Michael "J.D." Dorian' |
|||
|
|||
Remember a simple list of actors is accessible via the default Show data: |
|||
|
|||
>>> t['scrubs']['actors'] |
|||
u'|Zach Braff|Donald Faison|Sarah Chalke|Christa Miller|Aloma Wright|Robert Maschio|Sam Lloyd|Neil Flynn|Ken Jenkins|Judy Reyes|John C. McGinley|Travis Schuldt|Johnny Kastl|Heather Graham|Michael Mosley|Kerry Bish\xe9|Dave Franco|Eliza Coupe|' |
|||
|
|||
[tvdb]: http://thetvdb.com |
|||
[tvnamer]: http://github.com/dbr/tvnamer |
@ -0,0 +1,35 @@ |
|||
from setuptools import setup |
|||
setup( |
|||
name = 'tvdb_api', |
|||
version='1.8.2', |
|||
|
|||
author='dbr/Ben', |
|||
description='Interface to thetvdb.com', |
|||
url='http://github.com/dbr/tvdb_api/tree/master', |
|||
license='unlicense', |
|||
|
|||
long_description="""\ |
|||
An easy to use API interface to TheTVDB.com |
|||
Basic usage is: |
|||
|
|||
>>> import tvdb_api |
|||
>>> t = tvdb_api.Tvdb() |
|||
>>> ep = t['My Name Is Earl'][1][22] |
|||
>>> ep |
|||
<Episode 01x22 - Stole a Badge> |
|||
>>> ep['episodename'] |
|||
u'Stole a Badge' |
|||
""", |
|||
|
|||
py_modules = ['tvdb_api', 'tvdb_ui', 'tvdb_exceptions', 'tvdb_cache'], |
|||
|
|||
classifiers=[ |
|||
"Intended Audience :: Developers", |
|||
"Natural Language :: English", |
|||
"Operating System :: OS Independent", |
|||
"Programming Language :: Python", |
|||
"Topic :: Multimedia", |
|||
"Topic :: Utilities", |
|||
"Topic :: Software Development :: Libraries :: Python Modules", |
|||
] |
|||
) |
File diff suppressed because it is too large
@ -0,0 +1,28 @@ |
|||
#!/usr/bin/env python |
|||
#encoding:utf-8 |
|||
#author:dbr/Ben |
|||
#project:tvdb_api |
|||
#repository:http://github.com/dbr/tvdb_api |
|||
#license:unlicense (http://unlicense.org/) |
|||
|
|||
import sys |
|||
import unittest |
|||
|
|||
import test_tvdb_api |
|||
|
|||
def main(): |
|||
suite = unittest.TestSuite([ |
|||
unittest.TestLoader().loadTestsFromModule(test_tvdb_api) |
|||
]) |
|||
|
|||
runner = unittest.TextTestRunner(verbosity=2) |
|||
result = runner.run(suite) |
|||
if result.wasSuccessful(): |
|||
return 0 |
|||
else: |
|||
return 1 |
|||
|
|||
if __name__ == '__main__': |
|||
sys.exit( |
|||
int(main()) |
|||
) |
@ -0,0 +1,526 @@ |
|||
#!/usr/bin/env python |
|||
#encoding:utf-8 |
|||
#author:dbr/Ben |
|||
#project:tvdb_api |
|||
#repository:http://github.com/dbr/tvdb_api |
|||
#license:unlicense (http://unlicense.org/) |
|||
|
|||
"""Unittests for tvdb_api |
|||
""" |
|||
|
|||
import os |
|||
import sys |
|||
import datetime |
|||
import unittest |
|||
|
|||
# Force parent directory onto path |
|||
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) |
|||
|
|||
import tvdb_api |
|||
import tvdb_ui |
|||
from tvdb_api import (tvdb_shownotfound, tvdb_seasonnotfound, |
|||
tvdb_episodenotfound, tvdb_attributenotfound) |
|||
|
|||
class test_tvdb_basic(unittest.TestCase): |
|||
# Used to store the cached instance of Tvdb() |
|||
t = None |
|||
|
|||
def setUp(self): |
|||
if self.t is None: |
|||
self.__class__.t = tvdb_api.Tvdb(cache = True, banners = False) |
|||
|
|||
def test_different_case(self): |
|||
"""Checks the auto-correction of show names is working. |
|||
It should correct the weirdly capitalised 'sCruBs' to 'Scrubs' |
|||
""" |
|||
self.assertEquals(self.t['scrubs'][1][4]['episodename'], 'My Old Lady') |
|||
self.assertEquals(self.t['sCruBs']['seriesname'], 'Scrubs') |
|||
|
|||
def test_spaces(self): |
|||
"""Checks shownames with spaces |
|||
""" |
|||
self.assertEquals(self.t['My Name Is Earl']['seriesname'], 'My Name Is Earl') |
|||
self.assertEquals(self.t['My Name Is Earl'][1][4]['episodename'], 'Faked His Own Death') |
|||
|
|||
def test_numeric(self): |
|||
"""Checks numeric show names |
|||
""" |
|||
self.assertEquals(self.t['24'][2][20]['episodename'], 'Day 2: 3:00 A.M.-4:00 A.M.') |
|||
self.assertEquals(self.t['24']['seriesname'], '24') |
|||
|
|||
def test_show_iter(self): |
|||
"""Iterating over a show returns each seasons |
|||
""" |
|||
self.assertEquals( |
|||
len( |
|||
[season for season in self.t['Life on Mars']] |
|||
), |
|||
2 |
|||
) |
|||
|
|||
def test_season_iter(self): |
|||
"""Iterating over a show returns episodes |
|||
""" |
|||
self.assertEquals( |
|||
len( |
|||
[episode for episode in self.t['Life on Mars'][1]] |
|||
), |
|||
8 |
|||
) |
|||
|
|||
def test_get_episode_overview(self): |
|||
"""Checks episode overview is retrieved correctly. |
|||
""" |
|||
self.assertEquals( |
|||
self.t['Battlestar Galactica (2003)'][1][6]['overview'].startswith( |
|||
'When a new copy of Doral, a Cylon who had been previously'), |
|||
True |
|||
) |
|||
|
|||
def test_get_parent(self): |
|||
"""Check accessing series from episode instance |
|||
""" |
|||
show = self.t['Battlestar Galactica (2003)'] |
|||
season = show[1] |
|||
episode = show[1][1] |
|||
|
|||
self.assertEquals( |
|||
season.show, |
|||
show |
|||
) |
|||
|
|||
self.assertEquals( |
|||
episode.season, |
|||
season |
|||
) |
|||
|
|||
self.assertEquals( |
|||
episode.season.show, |
|||
show |
|||
) |
|||
|
|||
|
|||
class test_tvdb_errors(unittest.TestCase): |
|||
# Used to store the cached instance of Tvdb() |
|||
t = None |
|||
|
|||
def setUp(self): |
|||
if self.t is None: |
|||
self.__class__.t = tvdb_api.Tvdb(cache = True, banners = False) |
|||
|
|||
def test_seasonnotfound(self): |
|||
"""Checks exception is thrown when season doesn't exist. |
|||
""" |
|||
self.assertRaises(tvdb_seasonnotfound, lambda:self.t['CNNNN'][10][1]) |
|||
|
|||
def test_shownotfound(self): |
|||
"""Checks exception is thrown when episode doesn't exist. |
|||
""" |
|||
self.assertRaises(tvdb_shownotfound, lambda:self.t['the fake show thingy']) |
|||
|
|||
def test_episodenotfound(self): |
|||
"""Checks exception is raised for non-existent episode |
|||
""" |
|||
self.assertRaises(tvdb_episodenotfound, lambda:self.t['Scrubs'][1][30]) |
|||
|
|||
def test_attributenamenotfound(self): |
|||
"""Checks exception is thrown for if an attribute isn't found. |
|||
""" |
|||
self.assertRaises(tvdb_attributenotfound, lambda:self.t['CNNNN'][1][6]['afakeattributething']) |
|||
self.assertRaises(tvdb_attributenotfound, lambda:self.t['CNNNN']['afakeattributething']) |
|||
|
|||
class test_tvdb_search(unittest.TestCase): |
|||
# Used to store the cached instance of Tvdb() |
|||
t = None |
|||
|
|||
def setUp(self): |
|||
if self.t is None: |
|||
self.__class__.t = tvdb_api.Tvdb(cache = True, banners = False) |
|||
|
|||
def test_search_len(self): |
|||
"""There should be only one result matching |
|||
""" |
|||
self.assertEquals(len(self.t['My Name Is Earl'].search('Faked His Own Death')), 1) |
|||
|
|||
def test_search_checkname(self): |
|||
"""Checks you can get the episode name of a search result |
|||
""" |
|||
self.assertEquals(self.t['Scrubs'].search('my first')[0]['episodename'], 'My First Day') |
|||
self.assertEquals(self.t['My Name Is Earl'].search('Faked His Own Death')[0]['episodename'], 'Faked His Own Death') |
|||
|
|||
def test_search_multiresults(self): |
|||
"""Checks search can return multiple results |
|||
""" |
|||
self.assertEquals(len(self.t['Scrubs'].search('my first')) >= 3, True) |
|||
|
|||
def test_search_no_params_error(self): |
|||
"""Checks not supplying search info raises TypeError""" |
|||
self.assertRaises( |
|||
TypeError, |
|||
lambda: self.t['Scrubs'].search() |
|||
) |
|||
|
|||
def test_search_season(self): |
|||
"""Checks the searching of a single season""" |
|||
self.assertEquals( |
|||
len(self.t['Scrubs'][1].search("First")), |
|||
3 |
|||
) |
|||
|
|||
def test_search_show(self): |
|||
"""Checks the searching of an entire show""" |
|||
self.assertEquals( |
|||
len(self.t['CNNNN'].search('CNNNN', key='episodename')), |
|||
3 |
|||
) |
|||
|
|||
def test_aired_on(self): |
|||
"""Tests airedOn show method""" |
|||
sr = self.t['Scrubs'].airedOn(datetime.date(2001, 10, 2)) |
|||
self.assertEquals(len(sr), 1) |
|||
self.assertEquals(sr[0]['episodename'], u'My First Day') |
|||
|
|||
class test_tvdb_data(unittest.TestCase): |
|||
# Used to store the cached instance of Tvdb() |
|||
t = None |
|||
|
|||
def setUp(self): |
|||
if self.t is None: |
|||
self.__class__.t = tvdb_api.Tvdb(cache = True, banners = False) |
|||
|
|||
def test_episode_data(self): |
|||
"""Check the firstaired value is retrieved |
|||
""" |
|||
self.assertEquals( |
|||
self.t['lost']['firstaired'], |
|||
'2004-09-22' |
|||
) |
|||
|
|||
class test_tvdb_misc(unittest.TestCase): |
|||
# Used to store the cached instance of Tvdb() |
|||
t = None |
|||
|
|||
def setUp(self): |
|||
if self.t is None: |
|||
self.__class__.t = tvdb_api.Tvdb(cache = True, banners = False) |
|||
|
|||
def test_repr_show(self): |
|||
"""Check repr() of Season |
|||
""" |
|||
self.assertEquals( |
|||
repr(self.t['CNNNN']), |
|||
"<Show Chaser Non-Stop News Network (CNNNN) (containing 3 seasons)>" |
|||
) |
|||
def test_repr_season(self): |
|||
"""Check repr() of Season |
|||
""" |
|||
self.assertEquals( |
|||
repr(self.t['CNNNN'][1]), |
|||
"<Season instance (containing 9 episodes)>" |
|||
) |
|||
def test_repr_episode(self): |
|||
"""Check repr() of Episode |
|||
""" |
|||
self.assertEquals( |
|||
repr(self.t['CNNNN'][1][1]), |
|||
"<Episode 01x01 - Terror Alert>" |
|||
) |
|||
def test_have_all_languages(self): |
|||
"""Check valid_languages is up-to-date (compared to languages.xml) |
|||
""" |
|||
et = self.t._getetsrc( |
|||
"http://thetvdb.com/api/%s/languages.xml" % ( |
|||
self.t.config['apikey'] |
|||
) |
|||
) |
|||
languages = [x.find("abbreviation").text for x in et.findall("Language")] |
|||
|
|||
self.assertEquals( |
|||
sorted(languages), |
|||
sorted(self.t.config['valid_languages']) |
|||
) |
|||
|
|||
class test_tvdb_languages(unittest.TestCase): |
|||
def test_episode_name_french(self): |
|||
"""Check episode data is in French (language="fr") |
|||
""" |
|||
t = tvdb_api.Tvdb(cache = True, language = "fr") |
|||
self.assertEquals( |
|||
t['scrubs'][1][1]['episodename'], |
|||
"Mon premier jour" |
|||
) |
|||
self.assertTrue( |
|||
t['scrubs']['overview'].startswith( |
|||
u"J.D. est un jeune m\xe9decin qui d\xe9bute" |
|||
) |
|||
) |
|||
|
|||
def test_episode_name_spanish(self): |
|||
"""Check episode data is in Spanish (language="es") |
|||
""" |
|||
t = tvdb_api.Tvdb(cache = True, language = "es") |
|||
self.assertEquals( |
|||
t['scrubs'][1][1]['episodename'], |
|||
"Mi Primer Dia" |
|||
) |
|||
self.assertTrue( |
|||
t['scrubs']['overview'].startswith( |
|||
u'Scrubs es una divertida comedia' |
|||
) |
|||
) |
|||
|
|||
def test_multilanguage_selection(self): |
|||
"""Check selected language is used |
|||
""" |
|||
class SelectEnglishUI(tvdb_ui.BaseUI): |
|||
def selectSeries(self, allSeries): |
|||
return [x for x in allSeries if x['language'] == "en"][0] |
|||
|
|||
class SelectItalianUI(tvdb_ui.BaseUI): |
|||
def selectSeries(self, allSeries): |
|||
return [x for x in allSeries if x['language'] == "it"][0] |
|||
|
|||
t_en = tvdb_api.Tvdb( |
|||
cache=True, |
|||
custom_ui = SelectEnglishUI, |
|||
language = "en") |
|||
t_it = tvdb_api.Tvdb( |
|||
cache=True, |
|||
custom_ui = SelectItalianUI, |
|||
language = "it") |
|||
|
|||
self.assertEquals( |
|||
t_en['dexter'][1][2]['episodename'], "Crocodile" |
|||
) |
|||
self.assertEquals( |
|||
t_it['dexter'][1][2]['episodename'], "Lacrime di coccodrillo" |
|||
) |
|||
|
|||
|
|||
class test_tvdb_unicode(unittest.TestCase): |
|||
def test_search_in_chinese(self): |
|||
"""Check searching for show with language=zh returns Chinese seriesname |
|||
""" |
|||
t = tvdb_api.Tvdb(cache = True, language = "zh") |
|||
show = t[u'T\xecnh Ng\u01b0\u1eddi Hi\u1ec7n \u0110\u1ea1i'] |
|||
self.assertEquals( |
|||
type(show), |
|||
tvdb_api.Show |
|||
) |
|||
|
|||
self.assertEquals( |
|||
show['seriesname'], |
|||
u'T\xecnh Ng\u01b0\u1eddi Hi\u1ec7n \u0110\u1ea1i' |
|||
) |
|||
|
|||
def test_search_in_all_languages(self): |
|||
"""Check search_all_languages returns Chinese show, with language=en |
|||
""" |
|||
t = tvdb_api.Tvdb(cache = True, search_all_languages = True, language="en") |
|||
show = t[u'T\xecnh Ng\u01b0\u1eddi Hi\u1ec7n \u0110\u1ea1i'] |
|||
self.assertEquals( |
|||
type(show), |
|||
tvdb_api.Show |
|||
) |
|||
|
|||
self.assertEquals( |
|||
show['seriesname'], |
|||
u'Virtues Of Harmony II' |
|||
) |
|||
|
|||
class test_tvdb_banners(unittest.TestCase): |
|||
# Used to store the cached instance of Tvdb() |
|||
t = None |
|||
|
|||
def setUp(self): |
|||
if self.t is None: |
|||
self.__class__.t = tvdb_api.Tvdb(cache = True, banners = True) |
|||
|
|||
def test_have_banners(self): |
|||
"""Check banners at least one banner is found |
|||
""" |
|||
self.assertEquals( |
|||
len(self.t['scrubs']['_banners']) > 0, |
|||
True |
|||
) |
|||
|
|||
def test_banner_url(self): |
|||
"""Checks banner URLs start with http:// |
|||
""" |
|||
for banner_type, banner_data in self.t['scrubs']['_banners'].items(): |
|||
for res, res_data in banner_data.items(): |
|||
for bid, banner_info in res_data.items(): |
|||
self.assertEquals( |
|||
banner_info['_bannerpath'].startswith("http://"), |
|||
True |
|||
) |
|||
|
|||
def test_episode_image(self): |
|||
"""Checks episode 'filename' image is fully qualified URL |
|||
""" |
|||
self.assertEquals( |
|||
self.t['scrubs'][1][1]['filename'].startswith("http://"), |
|||
True |
|||
) |
|||
|
|||
def test_show_artwork(self): |
|||
"""Checks various image URLs within season data are fully qualified |
|||
""" |
|||
for key in ['banner', 'fanart', 'poster']: |
|||
self.assertEquals( |
|||
self.t['scrubs'][key].startswith("http://"), |
|||
True |
|||
) |
|||
|
|||
class test_tvdb_actors(unittest.TestCase): |
|||
t = None |
|||
def setUp(self): |
|||
if self.t is None: |
|||
self.__class__.t = tvdb_api.Tvdb(cache = True, actors = True) |
|||
|
|||
def test_actors_is_correct_datatype(self): |
|||
"""Check show/_actors key exists and is correct type""" |
|||
self.assertTrue( |
|||
isinstance( |
|||
self.t['scrubs']['_actors'], |
|||
tvdb_api.Actors |
|||
) |
|||
) |
|||
|
|||
def test_actors_has_actor(self): |
|||
"""Check show has at least one Actor |
|||
""" |
|||
self.assertTrue( |
|||
isinstance( |
|||
self.t['scrubs']['_actors'][0], |
|||
tvdb_api.Actor |
|||
) |
|||
) |
|||
|
|||
def test_actor_has_name(self): |
|||
"""Check first actor has a name""" |
|||
self.assertEquals( |
|||
self.t['scrubs']['_actors'][0]['name'], |
|||
"Zach Braff" |
|||
) |
|||
|
|||
def test_actor_image_corrected(self): |
|||
"""Check image URL is fully qualified |
|||
""" |
|||
for actor in self.t['scrubs']['_actors']: |
|||
if actor['image'] is not None: |
|||
# Actor's image can be None, it displays as the placeholder |
|||
# image on thetvdb.com |
|||
self.assertTrue( |
|||
actor['image'].startswith("http://") |
|||
) |
|||
|
|||
class test_tvdb_doctest(unittest.TestCase): |
|||
# Used to store the cached instance of Tvdb() |
|||
t = None |
|||
|
|||
def setUp(self): |
|||
if self.t is None: |
|||
self.__class__.t = tvdb_api.Tvdb(cache = True, banners = False) |
|||
|
|||
def test_doctest(self): |
|||
"""Check docstring examples works""" |
|||
import doctest |
|||
doctest.testmod(tvdb_api) |
|||
|
|||
|
|||
class test_tvdb_custom_caching(unittest.TestCase): |
|||
def test_true_false_string(self): |
|||
"""Tests setting cache to True/False/string |
|||
|
|||
Basic tests, only checking for errors |
|||
""" |
|||
|
|||
tvdb_api.Tvdb(cache = True) |
|||
tvdb_api.Tvdb(cache = False) |
|||
tvdb_api.Tvdb(cache = "/tmp") |
|||
|
|||
def test_invalid_cache_option(self): |
|||
"""Tests setting cache to invalid value |
|||
""" |
|||
|
|||
try: |
|||
tvdb_api.Tvdb(cache = 2.3) |
|||
except ValueError: |
|||
pass |
|||
else: |
|||
self.fail("Expected ValueError from setting cache to float") |
|||
|
|||
def test_custom_urlopener(self): |
|||
class UsedCustomOpener(Exception): |
|||
pass |
|||
|
|||
import urllib2 |
|||
class TestOpener(urllib2.BaseHandler): |
|||
def default_open(self, request): |
|||
print request.get_method() |
|||
raise UsedCustomOpener("Something") |
|||
|
|||
custom_opener = urllib2.build_opener(TestOpener()) |
|||
t = tvdb_api.Tvdb(cache = custom_opener) |
|||
try: |
|||
t['scrubs'] |
|||
except UsedCustomOpener: |
|||
pass |
|||
else: |
|||
self.fail("Did not use custom opener") |
|||
|
|||
class test_tvdb_by_id(unittest.TestCase): |
|||
t = None |
|||
def setUp(self): |
|||
if self.t is None: |
|||
self.__class__.t = tvdb_api.Tvdb(cache = True, actors = True) |
|||
|
|||
def test_actors_is_correct_datatype(self): |
|||
"""Check show/_actors key exists and is correct type""" |
|||
self.assertEquals( |
|||
self.t[76156]['seriesname'], |
|||
'Scrubs' |
|||
) |
|||
|
|||
|
|||
class test_tvdb_zip(unittest.TestCase): |
|||
# Used to store the cached instance of Tvdb() |
|||
t = None |
|||
|
|||
def setUp(self): |
|||
if self.t is None: |
|||
self.__class__.t = tvdb_api.Tvdb(cache = True, useZip = True) |
|||
|
|||
def test_get_series_from_zip(self): |
|||
""" |
|||
""" |
|||
self.assertEquals(self.t['scrubs'][1][4]['episodename'], 'My Old Lady') |
|||
self.assertEquals(self.t['sCruBs']['seriesname'], 'Scrubs') |
|||
|
|||
def test_spaces_from_zip(self): |
|||
"""Checks shownames with spaces |
|||
""" |
|||
self.assertEquals(self.t['My Name Is Earl']['seriesname'], 'My Name Is Earl') |
|||
self.assertEquals(self.t['My Name Is Earl'][1][4]['episodename'], 'Faked His Own Death') |
|||
|
|||
|
|||
class test_tvdb_show_search(unittest.TestCase): |
|||
# Used to store the cached instance of Tvdb() |
|||
t = None |
|||
|
|||
def setUp(self): |
|||
if self.t is None: |
|||
self.__class__.t = tvdb_api.Tvdb(cache = True, useZip = True) |
|||
|
|||
def test_search(self): |
|||
"""Test Tvdb.search method |
|||
""" |
|||
results = self.t.search("my name is earl") |
|||
all_ids = [x['seriesid'] for x in results] |
|||
self.assertTrue('75397' in all_ids) |
|||
|
|||
|
|||
if __name__ == '__main__': |
|||
runner = unittest.TextTestRunner(verbosity = 2) |
|||
unittest.main(testRunner = runner) |
@ -0,0 +1,874 @@ |
|||
#!/usr/bin/env python |
|||
#encoding:utf-8 |
|||
#author:dbr/Ben |
|||
#project:tvdb_api |
|||
#repository:http://github.com/dbr/tvdb_api |
|||
#license:unlicense (http://unlicense.org/) |
|||
|
|||
"""Simple-to-use Python interface to The TVDB's API (thetvdb.com) |
|||
|
|||
Example usage: |
|||
|
|||
>>> from tvdb_api import Tvdb |
|||
>>> t = Tvdb() |
|||
>>> t['Lost'][4][11]['episodename'] |
|||
u'Cabin Fever' |
|||
""" |
|||
__author__ = "dbr/Ben" |
|||
__version__ = "1.8.2" |
|||
|
|||
import os |
|||
import time |
|||
import urllib |
|||
import urllib2 |
|||
import getpass |
|||
import StringIO |
|||
import tempfile |
|||
import warnings |
|||
import logging |
|||
import datetime |
|||
import zipfile |
|||
|
|||
try: |
|||
import xml.etree.cElementTree as ElementTree |
|||
except ImportError: |
|||
import xml.etree.ElementTree as ElementTree |
|||
|
|||
try: |
|||
import gzip |
|||
except ImportError: |
|||
gzip = None |
|||
|
|||
|
|||
from tvdb_cache import CacheHandler |
|||
|
|||
from tvdb_ui import BaseUI, ConsoleUI |
|||
from tvdb_exceptions import (tvdb_error, tvdb_userabort, tvdb_shownotfound, |
|||
tvdb_seasonnotfound, tvdb_episodenotfound, tvdb_attributenotfound) |
|||
|
|||
lastTimeout = None |
|||
|
|||
def log(): |
|||
return logging.getLogger("tvdb_api") |
|||
|
|||
|
|||
class ShowContainer(dict): |
|||
"""Simple dict that holds a series of Show instances |
|||
""" |
|||
|
|||
def __init__(self): |
|||
self._stack = [] |
|||
self._lastgc = time.time() |
|||
|
|||
def __setitem__(self, key, value): |
|||
self._stack.append(key) |
|||
|
|||
#keep only the 100th latest results |
|||
if time.time() - self._lastgc > 20: |
|||
tbd = self._stack[:-100] |
|||
i = 0 |
|||
for o in tbd: |
|||
del self[o] |
|||
del self._stack[i] |
|||
i += 1 |
|||
|
|||
_lastgc = time.time() |
|||
del tbd |
|||
|
|||
super(ShowContainer, self).__setitem__(key, value) |
|||
|
|||
|
|||
class Show(dict): |
|||
"""Holds a dict of seasons, and show data. |
|||
""" |
|||
def __init__(self): |
|||
dict.__init__(self) |
|||
self.data = {} |
|||
|
|||
def __repr__(self): |
|||
return "<Show %s (containing %s seasons)>" % ( |
|||
self.data.get(u'seriesname', 'instance'), |
|||
len(self) |
|||
) |
|||
|
|||
def __getitem__(self, key): |
|||
if key in self: |
|||
# Key is an episode, return it |
|||
return dict.__getitem__(self, key) |
|||
|
|||
if key in self.data: |
|||
# Non-numeric request is for show-data |
|||
return dict.__getitem__(self.data, key) |
|||
|
|||
# Data wasn't found, raise appropriate error |
|||
if isinstance(key, int) or key.isdigit(): |
|||
# Episode number x was not found |
|||
raise tvdb_seasonnotfound("Could not find season %s" % (repr(key))) |
|||
else: |
|||
# If it's not numeric, it must be an attribute name, which |
|||
# doesn't exist, so attribute error. |
|||
raise tvdb_attributenotfound("Cannot find attribute %s" % (repr(key))) |
|||
|
|||
def airedOn(self, date): |
|||
ret = self.search(str(date), 'firstaired') |
|||
if len(ret) == 0: |
|||
raise tvdb_episodenotfound("Could not find any episodes that aired on %s" % date) |
|||
return ret |
|||
|
|||
def search(self, term = None, key = None): |
|||
""" |
|||
Search all episodes in show. Can search all data, or a specific key (for |
|||
example, episodename) |
|||
|
|||
Always returns an array (can be empty). First index contains the first |
|||
match, and so on. |
|||
|
|||
Each array index is an Episode() instance, so doing |
|||
search_results[0]['episodename'] will retrieve the episode name of the |
|||
first match. |
|||
|
|||
Search terms are converted to lower case (unicode) strings. |
|||
|
|||
# Examples |
|||
|
|||
These examples assume t is an instance of Tvdb(): |
|||
|
|||
>>> t = Tvdb() |
|||
>>> |
|||
|
|||
To search for all episodes of Scrubs with a bit of data |
|||
containing "my first day": |
|||
|
|||
>>> t['Scrubs'].search("my first day") |
|||
[<Episode 01x01 - My First Day>] |
|||
>>> |
|||
|
|||
Search for "My Name Is Earl" episode named "Faked His Own Death": |
|||
|
|||
>>> t['My Name Is Earl'].search('Faked His Own Death', key = 'episodename') |
|||
[<Episode 01x04 - Faked His Own Death>] |
|||
>>> |
|||
|
|||
To search Scrubs for all episodes with "mentor" in the episode name: |
|||
|
|||
>>> t['scrubs'].search('mentor', key = 'episodename') |
|||
[<Episode 01x02 - My Mentor>, <Episode 03x15 - My Tormented Mentor>] |
|||
>>> |
|||
|
|||
# Using search results |
|||
|
|||
>>> results = t['Scrubs'].search("my first") |
|||
>>> print results[0]['episodename'] |
|||
My First Day |
|||
>>> for x in results: print x['episodename'] |
|||
My First Day |
|||
My First Step |
|||
My First Kill |
|||
>>> |
|||
""" |
|||
results = [] |
|||
for cur_season in self.values(): |
|||
searchresult = cur_season.search(term = term, key = key) |
|||
if len(searchresult) != 0: |
|||
results.extend(searchresult) |
|||
|
|||
return results |
|||
|
|||
|
|||
class Season(dict): |
|||
def __init__(self, show = None): |
|||
"""The show attribute points to the parent show |
|||
""" |
|||
self.show = show |
|||
|
|||
def __repr__(self): |
|||
return "<Season instance (containing %s episodes)>" % ( |
|||
len(self.keys()) |
|||
) |
|||
|
|||
def __getitem__(self, episode_number): |
|||
if episode_number not in self: |
|||
raise tvdb_episodenotfound("Could not find episode %s" % (repr(episode_number))) |
|||
else: |
|||
return dict.__getitem__(self, episode_number) |
|||
|
|||
def search(self, term = None, key = None): |
|||
"""Search all episodes in season, returns a list of matching Episode |
|||
instances. |
|||
|
|||
>>> t = Tvdb() |
|||
>>> t['scrubs'][1].search('first day') |
|||
[<Episode 01x01 - My First Day>] |
|||
>>> |
|||
|
|||
See Show.search documentation for further information on search |
|||
""" |
|||
results = [] |
|||
for ep in self.values(): |
|||
searchresult = ep.search(term = term, key = key) |
|||
if searchresult is not None: |
|||
results.append( |
|||
searchresult |
|||
) |
|||
return results |
|||
|
|||
|
|||
class Episode(dict): |
|||
def __init__(self, season = None): |
|||
"""The season attribute points to the parent season |
|||
""" |
|||
self.season = season |
|||
|
|||
def __repr__(self): |
|||
seasno = int(self.get(u'seasonnumber', 0)) |
|||
epno = int(self.get(u'episodenumber', 0)) |
|||
epname = self.get(u'episodename') |
|||
if epname is not None: |
|||
return "<Episode %02dx%02d - %s>" % (seasno, epno, epname) |
|||
else: |
|||
return "<Episode %02dx%02d>" % (seasno, epno) |
|||
|
|||
def __getitem__(self, key): |
|||
try: |
|||
return dict.__getitem__(self, key) |
|||
except KeyError: |
|||
raise tvdb_attributenotfound("Cannot find attribute %s" % (repr(key))) |
|||
|
|||
def search(self, term = None, key = None): |
|||
"""Search episode data for term, if it matches, return the Episode (self). |
|||
The key parameter can be used to limit the search to a specific element, |
|||
for example, episodename. |
|||
|
|||
This primarily for use use by Show.search and Season.search. See |
|||
Show.search for further information on search |
|||
|
|||
Simple example: |
|||
|
|||
>>> e = Episode() |
|||
>>> e['episodename'] = "An Example" |
|||
>>> e.search("examp") |
|||
<Episode 00x00 - An Example> |
|||
>>> |
|||
|
|||
Limiting by key: |
|||
|
|||
>>> e.search("examp", key = "episodename") |
|||
<Episode 00x00 - An Example> |
|||
>>> |
|||
""" |
|||
if term == None: |
|||
raise TypeError("must supply string to search for (contents)") |
|||
|
|||
term = unicode(term).lower() |
|||
for cur_key, cur_value in self.items(): |
|||
cur_key, cur_value = unicode(cur_key).lower(), unicode(cur_value).lower() |
|||
if key is not None and cur_key != key: |
|||
# Do not search this key |
|||
continue |
|||
if cur_value.find( unicode(term).lower() ) > -1: |
|||
return self |
|||
|
|||
|
|||
class Actors(list): |
|||
"""Holds all Actor instances for a show |
|||
""" |
|||
pass |
|||
|
|||
|
|||
class Actor(dict): |
|||
"""Represents a single actor. Should contain.. |
|||
|
|||
id, |
|||
image, |
|||
name, |
|||
role, |
|||
sortorder |
|||
""" |
|||
def __repr__(self): |
|||
return "<Actor \"%s\">" % (self.get("name")) |
|||
|
|||
|
|||
class Tvdb: |
|||
"""Create easy-to-use interface to name of season/episode name |
|||
>>> t = Tvdb() |
|||
>>> t['Scrubs'][1][24]['episodename'] |
|||
u'My Last Day' |
|||
""" |
|||
def __init__(self, |
|||
interactive = False, |
|||
select_first = False, |
|||
debug = False, |
|||
cache = True, |
|||
banners = False, |
|||
actors = False, |
|||
custom_ui = None, |
|||
language = None, |
|||
search_all_languages = False, |
|||
apikey = None, |
|||
forceConnect=False, |
|||
useZip=False): |
|||
|
|||
"""interactive (True/False): |
|||
When True, uses built-in console UI is used to select the correct show. |
|||
When False, the first search result is used. |
|||
|
|||
select_first (True/False): |
|||
Automatically selects the first series search result (rather |
|||
than showing the user a list of more than one series). |
|||
Is overridden by interactive = False, or specifying a custom_ui |
|||
|
|||
debug (True/False) DEPRECATED: |
|||
Replaced with proper use of logging module. To show debug messages: |
|||
|
|||
>>> import logging |
|||
>>> logging.basicConfig(level = logging.DEBUG) |
|||
|
|||
cache (True/False/str/unicode/urllib2 opener): |
|||
Retrieved XML are persisted to to disc. If true, stores in |
|||
tvdb_api folder under your systems TEMP_DIR, if set to |
|||
str/unicode instance it will use this as the cache |
|||
location. If False, disables caching. Can also be passed |
|||
an arbitrary Python object, which is used as a urllib2 |
|||
opener, which should be created by urllib2.build_opener |
|||
|
|||
banners (True/False): |
|||
Retrieves the banners for a show. These are accessed |
|||
via the _banners key of a Show(), for example: |
|||
|
|||
>>> Tvdb(banners=True)['scrubs']['_banners'].keys() |
|||
['fanart', 'poster', 'series', 'season'] |
|||
|
|||
actors (True/False): |
|||
Retrieves a list of the actors for a show. These are accessed |
|||
via the _actors key of a Show(), for example: |
|||
|
|||
>>> t = Tvdb(actors=True) |
|||
>>> t['scrubs']['_actors'][0]['name'] |
|||
u'Zach Braff' |
|||
|
|||
custom_ui (tvdb_ui.BaseUI subclass): |
|||
A callable subclass of tvdb_ui.BaseUI (overrides interactive option) |
|||
|
|||
language (2 character language abbreviation): |
|||
The language of the returned data. Is also the language search |
|||
uses. Default is "en" (English). For full list, run.. |
|||
|
|||
>>> Tvdb().config['valid_languages'] #doctest: +ELLIPSIS |
|||
['da', 'fi', 'nl', ...] |
|||
|
|||
search_all_languages (True/False): |
|||
By default, Tvdb will only search in the language specified using |
|||
the language option. When this is True, it will search for the |
|||
show in and language |
|||
|
|||
apikey (str/unicode): |
|||
Override the default thetvdb.com API key. By default it will use |
|||
tvdb_api's own key (fine for small scripts), but you can use your |
|||
own key if desired - this is recommended if you are embedding |
|||
tvdb_api in a larger application) |
|||
See http://thetvdb.com/?tab=apiregister to get your own key |
|||
|
|||
forceConnect (bool): |
|||
If true it will always try to connect to theTVDB.com even if we |
|||
recently timed out. By default it will wait one minute before |
|||
trying again, and any requests within that one minute window will |
|||
return an exception immediately. |
|||
|
|||
useZip (bool): |
|||
Download the zip archive where possibale, instead of the xml. |
|||
This is only used when all episodes are pulled. |
|||
And only the main language xml is used, the actor and banner xml are lost. |
|||
""" |
|||
|
|||
global lastTimeout |
|||
|
|||
# if we're given a lastTimeout that is less than 1 min just give up |
|||
if not forceConnect and lastTimeout != None and datetime.datetime.now() - lastTimeout < datetime.timedelta(minutes=1): |
|||
raise tvdb_error("We recently timed out, so giving up early this time") |
|||
|
|||
self.shows = ShowContainer() # Holds all Show classes |
|||
self.corrections = {} # Holds show-name to show_id mapping |
|||
|
|||
self.config = {} |
|||
|
|||
if apikey is not None: |
|||
self.config['apikey'] = apikey |
|||
else: |
|||
self.config['apikey'] = "0629B785CE550C8D" # tvdb_api's API key |
|||
|
|||
self.config['debug_enabled'] = debug # show debugging messages |
|||
|
|||
self.config['custom_ui'] = custom_ui |
|||
|
|||
self.config['interactive'] = interactive # prompt for correct series? |
|||
|
|||
self.config['select_first'] = select_first |
|||
|
|||
self.config['search_all_languages'] = search_all_languages |
|||
|
|||
self.config['useZip'] = useZip |
|||
|
|||
|
|||
if cache is True: |
|||
self.config['cache_enabled'] = True |
|||
self.config['cache_location'] = self._getTempDir() |
|||
self.urlopener = urllib2.build_opener( |
|||
CacheHandler(self.config['cache_location']) |
|||
) |
|||
|
|||
elif cache is False: |
|||
self.config['cache_enabled'] = False |
|||
self.urlopener = urllib2.build_opener() # default opener with no caching |
|||
|
|||
elif isinstance(cache, basestring): |
|||
self.config['cache_enabled'] = True |
|||
self.config['cache_location'] = cache |
|||
self.urlopener = urllib2.build_opener( |
|||
CacheHandler(self.config['cache_location']) |
|||
) |
|||
|
|||
elif isinstance(cache, urllib2.OpenerDirector): |
|||
# If passed something from urllib2.build_opener, use that |
|||
log().debug("Using %r as urlopener" % cache) |
|||
self.config['cache_enabled'] = True |
|||
self.urlopener = cache |
|||
|
|||
else: |
|||
raise ValueError("Invalid value for Cache %r (type was %s)" % (cache, type(cache))) |
|||
|
|||
self.config['banners_enabled'] = banners |
|||
self.config['actors_enabled'] = actors |
|||
|
|||
if self.config['debug_enabled']: |
|||
warnings.warn("The debug argument to tvdb_api.__init__ will be removed in the next version. " |
|||
"To enable debug messages, use the following code before importing: " |
|||
"import logging; logging.basicConfig(level=logging.DEBUG)") |
|||
logging.basicConfig(level=logging.DEBUG) |
|||
|
|||
|
|||
# List of language from http://thetvdb.com/api/0629B785CE550C8D/languages.xml |
|||
# Hard-coded here as it is realtively static, and saves another HTTP request, as |
|||
# recommended on http://thetvdb.com/wiki/index.php/API:languages.xml |
|||
self.config['valid_languages'] = [ |
|||
"da", "fi", "nl", "de", "it", "es", "fr","pl", "hu","el","tr", |
|||
"ru","he","ja","pt","zh","cs","sl", "hr","ko","en","sv","no" |
|||
] |
|||
|
|||
# thetvdb.com should be based around numeric language codes, |
|||
# but to link to a series like http://thetvdb.com/?tab=series&id=79349&lid=16 |
|||
# requires the language ID, thus this mapping is required (mainly |
|||
# for usage in tvdb_ui - internally tvdb_api will use the language abbreviations) |
|||
self.config['langabbv_to_id'] = {'el': 20, 'en': 7, 'zh': 27, |
|||
'it': 15, 'cs': 28, 'es': 16, 'ru': 22, 'nl': 13, 'pt': 26, 'no': 9, |
|||
'tr': 21, 'pl': 18, 'fr': 17, 'hr': 31, 'de': 14, 'da': 10, 'fi': 11, |
|||
'hu': 19, 'ja': 25, 'he': 24, 'ko': 32, 'sv': 8, 'sl': 30} |
|||
|
|||
if language is None: |
|||
self.config['language'] = 'en' |
|||
else: |
|||
if language not in self.config['valid_languages']: |
|||
raise ValueError("Invalid language %s, options are: %s" % ( |
|||
language, self.config['valid_languages'] |
|||
)) |
|||
else: |
|||
self.config['language'] = language |
|||
|
|||
# The following url_ configs are based of the |
|||
# http://thetvdb.com/wiki/index.php/Programmers_API |
|||
self.config['base_url'] = "http://thetvdb.com" |
|||
|
|||
if self.config['search_all_languages']: |
|||
self.config['url_getSeries'] = u"%(base_url)s/api/GetSeries.php?seriesname=%%s&language=all" % self.config |
|||
else: |
|||
self.config['url_getSeries'] = u"%(base_url)s/api/GetSeries.php?seriesname=%%s&language=%(language)s" % self.config |
|||
|
|||
self.config['url_epInfo'] = u"%(base_url)s/api/%(apikey)s/series/%%s/all/%%s.xml" % self.config |
|||
self.config['url_epInfo_zip'] = u"%(base_url)s/api/%(apikey)s/series/%%s/all/%%s.zip" % self.config |
|||
|
|||
self.config['url_seriesInfo'] = u"%(base_url)s/api/%(apikey)s/series/%%s/%%s.xml" % self.config |
|||
self.config['url_actorsInfo'] = u"%(base_url)s/api/%(apikey)s/series/%%s/actors.xml" % self.config |
|||
|
|||
self.config['url_seriesBanner'] = u"%(base_url)s/api/%(apikey)s/series/%%s/banners.xml" % self.config |
|||
self.config['url_artworkPrefix'] = u"%(base_url)s/banners/%%s" % self.config |
|||
|
|||
def _getTempDir(self): |
|||
"""Returns the [system temp dir]/tvdb_api-u501 (or |
|||
tvdb_api-myuser) |
|||
""" |
|||
if hasattr(os, 'getuid'): |
|||
uid = "u%d" % (os.getuid()) |
|||
else: |
|||
# For Windows |
|||
try: |
|||
uid = getpass.getuser() |
|||
except ImportError: |
|||
return os.path.join(tempfile.gettempdir(), "tvdb_api") |
|||
|
|||
return os.path.join(tempfile.gettempdir(), "tvdb_api-%s" % (uid)) |
|||
|
|||
def _loadUrl(self, url, recache = False, language=None): |
|||
global lastTimeout |
|||
try: |
|||
log().debug("Retrieving URL %s" % url) |
|||
resp = self.urlopener.open(url) |
|||
if 'x-local-cache' in resp.headers: |
|||
log().debug("URL %s was cached in %s" % ( |
|||
url, |
|||
resp.headers['x-local-cache']) |
|||
) |
|||
if recache: |
|||
log().debug("Attempting to recache %s" % url) |
|||
resp.recache() |
|||
except (IOError, urllib2.URLError), errormsg: |
|||
if not str(errormsg).startswith('HTTP Error'): |
|||
lastTimeout = datetime.datetime.now() |
|||
raise tvdb_error("Could not connect to server: %s" % (errormsg)) |
|||
|
|||
|
|||
# handle gzipped content, |
|||
# http://dbr.lighthouseapp.com/projects/13342/tickets/72-gzipped-data-patch |
|||
if 'gzip' in resp.headers.get("Content-Encoding", ''): |
|||
if gzip: |
|||
stream = StringIO.StringIO(resp.read()) |
|||
gz = gzip.GzipFile(fileobj=stream) |
|||
return gz.read() |
|||
|
|||
raise tvdb_error("Received gzip data from thetvdb.com, but could not correctly handle it") |
|||
|
|||
if 'application/zip' in resp.headers.get("Content-Type", ''): |
|||
try: |
|||
# TODO: The zip contains actors.xml and banners.xml, which are currently ignored [GH-20] |
|||
log().debug("We recived a zip file unpacking now ...") |
|||
zipdata = StringIO.StringIO() |
|||
zipdata.write(resp.read()) |
|||
myzipfile = zipfile.ZipFile(zipdata) |
|||
return myzipfile.read('%s.xml' % language) |
|||
except zipfile.BadZipfile: |
|||
if 'x-local-cache' in resp.headers: |
|||
resp.delete_cache() |
|||
raise tvdb_error("Bad zip file received from thetvdb.com, could not read it") |
|||
|
|||
return resp.read() |
|||
|
|||
def _getetsrc(self, url, language=None): |
|||
"""Loads a URL using caching, returns an ElementTree of the source |
|||
""" |
|||
src = self._loadUrl(url, language=language) |
|||
try: |
|||
# TVDB doesn't sanitize \r (CR) from user input in some fields, |
|||
# remove it to avoid errors. Change from SickBeard, from will14m |
|||
return ElementTree.fromstring(src.rstrip("\r")) |
|||
except SyntaxError: |
|||
src = self._loadUrl(url, recache=True, language=language) |
|||
try: |
|||
return ElementTree.fromstring(src.rstrip("\r")) |
|||
except SyntaxError, exceptionmsg: |
|||
errormsg = "There was an error with the XML retrieved from thetvdb.com:\n%s" % ( |
|||
exceptionmsg |
|||
) |
|||
|
|||
if self.config['cache_enabled']: |
|||
errormsg += "\nFirst try emptying the cache folder at..\n%s" % ( |
|||
self.config['cache_location'] |
|||
) |
|||
|
|||
errormsg += "\nIf this does not resolve the issue, please try again later. If the error persists, report a bug on" |
|||
errormsg += "\nhttp://dbr.lighthouseapp.com/projects/13342-tvdb_api/overview\n" |
|||
raise tvdb_error(errormsg) |
|||
|
|||
def _setItem(self, sid, seas, ep, attrib, value): |
|||
"""Creates a new episode, creating Show(), Season() and |
|||
Episode()s as required. Called by _getShowData to populate show |
|||
|
|||
Since the nice-to-use tvdb[1][24]['name] interface |
|||
makes it impossible to do tvdb[1][24]['name] = "name" |
|||
and still be capable of checking if an episode exists |
|||
so we can raise tvdb_shownotfound, we have a slightly |
|||
less pretty method of setting items.. but since the API |
|||
is supposed to be read-only, this is the best way to |
|||
do it! |
|||
The problem is that calling tvdb[1][24]['episodename'] = "name" |
|||
calls __getitem__ on tvdb[1], there is no way to check if |
|||
tvdb.__dict__ should have a key "1" before we auto-create it |
|||
""" |
|||
if sid not in self.shows: |
|||
self.shows[sid] = Show() |
|||
if seas not in self.shows[sid]: |
|||
self.shows[sid][seas] = Season(show = self.shows[sid]) |
|||
if ep not in self.shows[sid][seas]: |
|||
self.shows[sid][seas][ep] = Episode(season = self.shows[sid][seas]) |
|||
self.shows[sid][seas][ep][attrib] = value |
|||
|
|||
def _setShowData(self, sid, key, value): |
|||
"""Sets self.shows[sid] to a new Show instance, or sets the data |
|||
""" |
|||
if sid not in self.shows: |
|||
self.shows[sid] = Show() |
|||
self.shows[sid].data[key] = value |
|||
|
|||
def _cleanData(self, data): |
|||
"""Cleans up strings returned by TheTVDB.com |
|||
|
|||
Issues corrected: |
|||
- Replaces & with & |
|||
- Trailing whitespace |
|||
""" |
|||
data = data.replace(u"&", u"&") |
|||
data = data.strip() |
|||
return data |
|||
|
|||
def search(self, series): |
|||
"""This searches TheTVDB.com for the series name |
|||
and returns the result list |
|||
""" |
|||
series = urllib.quote(series.encode("utf-8")) |
|||
log().debug("Searching for show %s" % series) |
|||
seriesEt = self._getetsrc(self.config['url_getSeries'] % (series)) |
|||
allSeries = [] |
|||
for series in seriesEt: |
|||
result = dict((k.tag.lower(), k.text) for k in series.getchildren()) |
|||
result['id'] = int(result['id']) |
|||
result['lid'] = self.config['langabbv_to_id'][result['language']] |
|||
log().debug('Found series %(seriesname)s' % result) |
|||
allSeries.append(result) |
|||
|
|||
return allSeries |
|||
|
|||
def _getSeries(self, series): |
|||
"""This searches TheTVDB.com for the series name, |
|||
If a custom_ui UI is configured, it uses this to select the correct |
|||
series. If not, and interactive == True, ConsoleUI is used, if not |
|||
BaseUI is used to select the first result. |
|||
""" |
|||
allSeries = self.search(series) |
|||
|
|||
if len(allSeries) == 0: |
|||
log().debug('Series result returned zero') |
|||
raise tvdb_shownotfound("Show-name search returned zero results (cannot find show on TVDB)") |
|||
|
|||
if self.config['custom_ui'] is not None: |
|||
log().debug("Using custom UI %s" % (repr(self.config['custom_ui']))) |
|||
ui = self.config['custom_ui'](config = self.config) |
|||
else: |
|||
if not self.config['interactive']: |
|||
log().debug('Auto-selecting first search result using BaseUI') |
|||
ui = BaseUI(config = self.config) |
|||
else: |
|||
log().debug('Interactively selecting show using ConsoleUI') |
|||
ui = ConsoleUI(config = self.config) |
|||
|
|||
return ui.selectSeries(allSeries) |
|||
|
|||
def _parseBanners(self, sid): |
|||
"""Parses banners XML, from |
|||
http://thetvdb.com/api/[APIKEY]/series/[SERIES ID]/banners.xml |
|||
|
|||
Banners are retrieved using t['show name]['_banners'], for example: |
|||
|
|||
>>> t = Tvdb(banners = True) |
|||
>>> t['scrubs']['_banners'].keys() |
|||
['fanart', 'poster', 'series', 'season'] |
|||
>>> t['scrubs']['_banners']['poster']['680x1000']['35308']['_bannerpath'] |
|||
u'http://thetvdb.com/banners/posters/76156-2.jpg' |
|||
>>> |
|||
|
|||
Any key starting with an underscore has been processed (not the raw |
|||
data from the XML) |
|||
|
|||
This interface will be improved in future versions. |
|||
""" |
|||
log().debug('Getting season banners for %s' % (sid)) |
|||
bannersEt = self._getetsrc( self.config['url_seriesBanner'] % (sid) ) |
|||
banners = {} |
|||
for cur_banner in bannersEt.findall('Banner'): |
|||
bid = cur_banner.find('id').text |
|||
btype = cur_banner.find('BannerType') |
|||
btype2 = cur_banner.find('BannerType2') |
|||
if btype is None or btype2 is None: |
|||
continue |
|||
btype, btype2 = btype.text, btype2.text |
|||
if not btype in banners: |
|||
banners[btype] = {} |
|||
if not btype2 in banners[btype]: |
|||
banners[btype][btype2] = {} |
|||
if not bid in banners[btype][btype2]: |
|||
banners[btype][btype2][bid] = {} |
|||
|
|||
for cur_element in cur_banner.getchildren(): |
|||
tag = cur_element.tag.lower() |
|||
value = cur_element.text |
|||
if tag is None or value is None: |
|||
continue |
|||
tag, value = tag.lower(), value.lower() |
|||
banners[btype][btype2][bid][tag] = value |
|||
|
|||
for k, v in banners[btype][btype2][bid].items(): |
|||
if k.endswith("path"): |
|||
new_key = "_%s" % (k) |
|||
log().debug("Transforming %s to %s" % (k, new_key)) |
|||
new_url = self.config['url_artworkPrefix'] % (v) |
|||
banners[btype][btype2][bid][new_key] = new_url |
|||
|
|||
self._setShowData(sid, "_banners", banners) |
|||
|
|||
def _parseActors(self, sid): |
|||
"""Parsers actors XML, from |
|||
http://thetvdb.com/api/[APIKEY]/series/[SERIES ID]/actors.xml |
|||
|
|||
Actors are retrieved using t['show name]['_actors'], for example: |
|||
|
|||
>>> t = Tvdb(actors = True) |
|||
>>> actors = t['scrubs']['_actors'] |
|||
>>> type(actors) |
|||
<class 'tvdb_api.Actors'> |
|||
>>> type(actors[0]) |
|||
<class 'tvdb_api.Actor'> |
|||
>>> actors[0] |
|||
<Actor "Zach Braff"> |
|||
>>> sorted(actors[0].keys()) |
|||
['id', 'image', 'name', 'role', 'sortorder'] |
|||
>>> actors[0]['name'] |
|||
u'Zach Braff' |
|||
>>> actors[0]['image'] |
|||
u'http://thetvdb.com/banners/actors/43640.jpg' |
|||
|
|||
Any key starting with an underscore has been processed (not the raw |
|||
data from the XML) |
|||
""" |
|||
log().debug("Getting actors for %s" % (sid)) |
|||
actorsEt = self._getetsrc(self.config['url_actorsInfo'] % (sid)) |
|||
|
|||
cur_actors = Actors() |
|||
for curActorItem in actorsEt.findall("Actor"): |
|||
curActor = Actor() |
|||
for curInfo in curActorItem: |
|||
tag = curInfo.tag.lower() |
|||
value = curInfo.text |
|||
if value is not None: |
|||
if tag == "image": |
|||
value = self.config['url_artworkPrefix'] % (value) |
|||
else: |
|||
value = self._cleanData(value) |
|||
curActor[tag] = value |
|||
cur_actors.append(curActor) |
|||
self._setShowData(sid, '_actors', cur_actors) |
|||
|
|||
def _getShowData(self, sid, language): |
|||
"""Takes a series ID, gets the epInfo URL and parses the TVDB |
|||
XML file into the shows dict in layout: |
|||
shows[series_id][season_number][episode_number] |
|||
""" |
|||
|
|||
if self.config['language'] is None: |
|||
log().debug('Config language is none, using show language') |
|||
if language is None: |
|||
raise tvdb_error("config['language'] was None, this should not happen") |
|||
getShowInLanguage = language |
|||
else: |
|||
log().debug( |
|||
'Configured language %s override show language of %s' % ( |
|||
self.config['language'], |
|||
language |
|||
) |
|||
) |
|||
getShowInLanguage = self.config['language'] |
|||
|
|||
# Parse show information |
|||
log().debug('Getting all series data for %s' % (sid)) |
|||
seriesInfoEt = self._getetsrc( |
|||
self.config['url_seriesInfo'] % (sid, getShowInLanguage) |
|||
) |
|||
for curInfo in seriesInfoEt.findall("Series")[0]: |
|||
tag = curInfo.tag.lower() |
|||
value = curInfo.text |
|||
|
|||
if value is not None: |
|||
if tag in ['banner', 'fanart', 'poster']: |
|||
value = self.config['url_artworkPrefix'] % (value) |
|||
else: |
|||
value = self._cleanData(value) |
|||
|
|||
self._setShowData(sid, tag, value) |
|||
|
|||
# Parse banners |
|||
if self.config['banners_enabled']: |
|||
self._parseBanners(sid) |
|||
|
|||
# Parse actors |
|||
if self.config['actors_enabled']: |
|||
self._parseActors(sid) |
|||
|
|||
# Parse episode data |
|||
log().debug('Getting all episodes of %s' % (sid)) |
|||
|
|||
if self.config['useZip']: |
|||
url = self.config['url_epInfo_zip'] % (sid, language) |
|||
else: |
|||
url = self.config['url_epInfo'] % (sid, language) |
|||
|
|||
epsEt = self._getetsrc( url, language=language) |
|||
|
|||
for cur_ep in epsEt.findall("Episode"): |
|||
seas_no = int(cur_ep.find('SeasonNumber').text) |
|||
ep_no = int(cur_ep.find('EpisodeNumber').text) |
|||
for cur_item in cur_ep.getchildren(): |
|||
tag = cur_item.tag.lower() |
|||
value = cur_item.text |
|||
if value is not None: |
|||
if tag == 'filename': |
|||
value = self.config['url_artworkPrefix'] % (value) |
|||
else: |
|||
value = self._cleanData(value) |
|||
self._setItem(sid, seas_no, ep_no, tag, value) |
|||
|
|||
def _nameToSid(self, name): |
|||
"""Takes show name, returns the correct series ID (if the show has |
|||
already been grabbed), or grabs all episodes and returns |
|||
the correct SID. |
|||
""" |
|||
if name in self.corrections: |
|||
log().debug('Correcting %s to %s' % (name, self.corrections[name]) ) |
|||
sid = self.corrections[name] |
|||
else: |
|||
log().debug('Getting show %s' % (name)) |
|||
selected_series = self._getSeries( name ) |
|||
sname, sid = selected_series['seriesname'], selected_series['id'] |
|||
log().debug('Got %(seriesname)s, id %(id)s' % selected_series) |
|||
|
|||
self.corrections[name] = sid |
|||
self._getShowData(selected_series['id'], selected_series['language']) |
|||
|
|||
return sid |
|||
|
|||
def __getitem__(self, key): |
|||
"""Handles tvdb_instance['seriesname'] calls. |
|||
The dict index should be the show id |
|||
""" |
|||
if isinstance(key, (int, long)): |
|||
# Item is integer, treat as show id |
|||
if key not in self.shows: |
|||
self._getShowData(key, self.config['language']) |
|||
return self.shows[key] |
|||
|
|||
key = key.lower() # make key lower case |
|||
sid = self._nameToSid(key) |
|||
log().debug('Got series id %s' % (sid)) |
|||
return self.shows[sid] |
|||
|
|||
def __repr__(self): |
|||
return str(self.shows) |
|||
|
|||
|
|||
def main(): |
|||
"""Simple example of using tvdb_api - it just |
|||
grabs an episode name interactively. |
|||
""" |
|||
import logging |
|||
logging.basicConfig(level=logging.DEBUG) |
|||
|
|||
tvdb_instance = Tvdb(interactive=True, cache=False) |
|||
print tvdb_instance['Lost']['seriesname'] |
|||
print tvdb_instance['Lost'][1][4]['episodename'] |
|||
|
|||
if __name__ == '__main__': |
|||
main() |
@ -0,0 +1,251 @@ |
|||
#!/usr/bin/env python |
|||
#encoding:utf-8 |
|||
#author:dbr/Ben |
|||
#project:tvdb_api |
|||
#repository:http://github.com/dbr/tvdb_api |
|||
#license:unlicense (http://unlicense.org/) |
|||
|
|||
""" |
|||
urllib2 caching handler |
|||
Modified from http://code.activestate.com/recipes/491261/ |
|||
""" |
|||
from __future__ import with_statement |
|||
|
|||
__author__ = "dbr/Ben" |
|||
__version__ = "1.8.2" |
|||
|
|||
import os |
|||
import time |
|||
import errno |
|||
import httplib |
|||
import urllib2 |
|||
import StringIO |
|||
from hashlib import md5 |
|||
from threading import RLock |
|||
|
|||
cache_lock = RLock() |
|||
|
|||
def locked_function(origfunc): |
|||
"""Decorator to execute function under lock""" |
|||
def wrapped(*args, **kwargs): |
|||
cache_lock.acquire() |
|||
try: |
|||
return origfunc(*args, **kwargs) |
|||
finally: |
|||
cache_lock.release() |
|||
return wrapped |
|||
|
|||
def calculate_cache_path(cache_location, url): |
|||
"""Checks if [cache_location]/[hash_of_url].headers and .body exist |
|||
""" |
|||
thumb = md5(url).hexdigest() |
|||
header = os.path.join(cache_location, thumb + ".headers") |
|||
body = os.path.join(cache_location, thumb + ".body") |
|||
return header, body |
|||
|
|||
def check_cache_time(path, max_age): |
|||
"""Checks if a file has been created/modified in the [last max_age] seconds. |
|||
False means the file is too old (or doesn't exist), True means it is |
|||
up-to-date and valid""" |
|||
if not os.path.isfile(path): |
|||
return False |
|||
cache_modified_time = os.stat(path).st_mtime |
|||
time_now = time.time() |
|||
if cache_modified_time < time_now - max_age: |
|||
# Cache is old |
|||
return False |
|||
else: |
|||
return True |
|||
|
|||
@locked_function |
|||
def exists_in_cache(cache_location, url, max_age): |
|||
"""Returns if header AND body cache file exist (and are up-to-date)""" |
|||
hpath, bpath = calculate_cache_path(cache_location, url) |
|||
if os.path.exists(hpath) and os.path.exists(bpath): |
|||
return( |
|||
check_cache_time(hpath, max_age) |
|||
and check_cache_time(bpath, max_age) |
|||
) |
|||
else: |
|||
# File does not exist |
|||
return False |
|||
|
|||
@locked_function |
|||
def store_in_cache(cache_location, url, response): |
|||
"""Tries to store response in cache.""" |
|||
hpath, bpath = calculate_cache_path(cache_location, url) |
|||
try: |
|||
outf = open(hpath, "wb") |
|||
headers = str(response.info()) |
|||
outf.write(headers) |
|||
outf.close() |
|||
|
|||
outf = open(bpath, "wb") |
|||
outf.write(response.read()) |
|||
outf.close() |
|||
except IOError: |
|||
return True |
|||
else: |
|||
return False |
|||
|
|||
@locked_function |
|||
def delete_from_cache(cache_location, url): |
|||
"""Deletes a response in cache.""" |
|||
hpath, bpath = calculate_cache_path(cache_location, url) |
|||
try: |
|||
if os.path.exists(hpath): |
|||
os.remove(hpath) |
|||
if os.path.exists(bpath): |
|||
os.remove(bpath) |
|||
except IOError: |
|||
return True |
|||
else: |
|||
return False |
|||
|
|||
class CacheHandler(urllib2.BaseHandler): |
|||
"""Stores responses in a persistant on-disk cache. |
|||
|
|||
If a subsequent GET request is made for the same URL, the stored |
|||
response is returned, saving time, resources and bandwidth |
|||
""" |
|||
@locked_function |
|||
def __init__(self, cache_location, max_age = 21600): |
|||
"""The location of the cache directory""" |
|||
self.max_age = max_age |
|||
self.cache_location = cache_location |
|||
if not os.path.exists(self.cache_location): |
|||
try: |
|||
os.mkdir(self.cache_location) |
|||
except OSError, e: |
|||
if e.errno == errno.EEXIST and os.path.isdir(self.cache_location): |
|||
# File exists, and it's a directory, |
|||
# another process beat us to creating this dir, that's OK. |
|||
pass |
|||
else: |
|||
# Our target dir is already a file, or different error, |
|||
# relay the error! |
|||
raise |
|||
|
|||
def default_open(self, request): |
|||
"""Handles GET requests, if the response is cached it returns it |
|||
""" |
|||
if request.get_method() is not "GET": |
|||
return None # let the next handler try to handle the request |
|||
|
|||
if exists_in_cache( |
|||
self.cache_location, request.get_full_url(), self.max_age |
|||
): |
|||
return CachedResponse( |
|||
self.cache_location, |
|||
request.get_full_url(), |
|||
set_cache_header = True |
|||
) |
|||
else: |
|||
return None |
|||
|
|||
def http_response(self, request, response): |
|||
"""Gets a HTTP response, if it was a GET request and the status code |
|||
starts with 2 (200 OK etc) it caches it and returns a CachedResponse |
|||
""" |
|||
if (request.get_method() == "GET" |
|||
and str(response.code).startswith("2") |
|||
): |
|||
if 'x-local-cache' not in response.info(): |
|||
# Response is not cached |
|||
set_cache_header = store_in_cache( |
|||
self.cache_location, |
|||
request.get_full_url(), |
|||
response |
|||
) |
|||
else: |
|||
set_cache_header = True |
|||
|
|||
return CachedResponse( |
|||
self.cache_location, |
|||
request.get_full_url(), |
|||
set_cache_header = set_cache_header |
|||
) |
|||
else: |
|||
return response |
|||
|
|||
class CachedResponse(StringIO.StringIO): |
|||
"""An urllib2.response-like object for cached responses. |
|||
|
|||
To determine if a response is cached or coming directly from |
|||
the network, check the x-local-cache header rather than the object type. |
|||
""" |
|||
|
|||
@locked_function |
|||
def __init__(self, cache_location, url, set_cache_header=True): |
|||
self.cache_location = cache_location |
|||
hpath, bpath = calculate_cache_path(cache_location, url) |
|||
|
|||
StringIO.StringIO.__init__(self, file(bpath, "rb").read()) |
|||
|
|||
self.url = url |
|||
self.code = 200 |
|||
self.msg = "OK" |
|||
headerbuf = file(hpath, "rb").read() |
|||
if set_cache_header: |
|||
headerbuf += "x-local-cache: %s\r\n" % (bpath) |
|||
self.headers = httplib.HTTPMessage(StringIO.StringIO(headerbuf)) |
|||
|
|||
def info(self): |
|||
"""Returns headers |
|||
""" |
|||
return self.headers |
|||
|
|||
def geturl(self): |
|||
"""Returns original URL |
|||
""" |
|||
return self.url |
|||
|
|||
@locked_function |
|||
def recache(self): |
|||
new_request = urllib2.urlopen(self.url) |
|||
set_cache_header = store_in_cache( |
|||
self.cache_location, |
|||
new_request.url, |
|||
new_request |
|||
) |
|||
CachedResponse.__init__(self, self.cache_location, self.url, True) |
|||
|
|||
@locked_function |
|||
def delete_cache(self): |
|||
delete_from_cache( |
|||
self.cache_location, |
|||
self.url |
|||
) |
|||
|
|||
|
|||
if __name__ == "__main__": |
|||
def main(): |
|||
"""Quick test/example of CacheHandler""" |
|||
opener = urllib2.build_opener(CacheHandler("/tmp/")) |
|||
response = opener.open("http://google.com") |
|||
print response.headers |
|||
print "Response:", response.read() |
|||
|
|||
response.recache() |
|||
print response.headers |
|||
print "After recache:", response.read() |
|||
|
|||
# Test usage in threads |
|||
from threading import Thread |
|||
class CacheThreadTest(Thread): |
|||
lastdata = None |
|||
def run(self): |
|||
req = opener.open("http://google.com") |
|||
newdata = req.read() |
|||
if self.lastdata is None: |
|||
self.lastdata = newdata |
|||
assert self.lastdata == newdata, "Data was not consistent, uhoh" |
|||
req.recache() |
|||
threads = [CacheThreadTest() for x in range(50)] |
|||
print "Starting threads" |
|||
[t.start() for t in threads] |
|||
print "..done" |
|||
print "Joining threads" |
|||
[t.join() for t in threads] |
|||
print "..done" |
|||
main() |
@ -0,0 +1,52 @@ |
|||
#!/usr/bin/env python |
|||
#encoding:utf-8 |
|||
#author:dbr/Ben |
|||
#project:tvdb_api |
|||
#repository:http://github.com/dbr/tvdb_api |
|||
#license:unlicense (http://unlicense.org/) |
|||
|
|||
"""Custom exceptions used or raised by tvdb_api |
|||
""" |
|||
|
|||
__author__ = "dbr/Ben" |
|||
__version__ = "1.8.2" |
|||
|
|||
__all__ = ["tvdb_error", "tvdb_userabort", "tvdb_shownotfound", |
|||
"tvdb_seasonnotfound", "tvdb_episodenotfound", "tvdb_attributenotfound"] |
|||
|
|||
class tvdb_exception(Exception): |
|||
"""Any exception generated by tvdb_api |
|||
""" |
|||
pass |
|||
|
|||
class tvdb_error(tvdb_exception): |
|||
"""An error with thetvdb.com (Cannot connect, for example) |
|||
""" |
|||
pass |
|||
|
|||
class tvdb_userabort(tvdb_exception): |
|||
"""User aborted the interactive selection (via |
|||
the q command, ^c etc) |
|||
""" |
|||
pass |
|||
|
|||
class tvdb_shownotfound(tvdb_exception): |
|||
"""Show cannot be found on thetvdb.com (non-existant show) |
|||
""" |
|||
pass |
|||
|
|||
class tvdb_seasonnotfound(tvdb_exception): |
|||
"""Season cannot be found on thetvdb.com |
|||
""" |
|||
pass |
|||
|
|||
class tvdb_episodenotfound(tvdb_exception): |
|||
"""Episode cannot be found on thetvdb.com |
|||
""" |
|||
pass |
|||
|
|||
class tvdb_attributenotfound(tvdb_exception): |
|||
"""Raised if an episode does not have the requested |
|||
attribute (such as a episode name) |
|||
""" |
|||
pass |
Some files were not shown because too many files changed in this diff
Loading…
Reference in new issue