Working TV correctRelease function with quality, identifier and show title checking.

couchpotato/core/helpers/variable.py

@@ -146,9 +146,9 @@ def getImdb(txt, check_inside = False, multiple = False):
 
     return False
 
-def tryInt(s):
+def tryInt(s, default=0):
     try: return int(s)
-    except: return 0
+    except: return default
 
 def tryFloat(s):
     try:

couchpotato/core/media/show/searcher/main.py

@@ -1,11 +1,14 @@
 import pprint
+import re
 from couchpotato import get_session, Env
 from couchpotato.core.event import addEvent, fireEvent
-from couchpotato.core.helpers.variable import getTitle
+from couchpotato.core.helpers.encoding import simplifyString
+from couchpotato.core.helpers.variable import getTitle, tryInt, possibleTitles
 from couchpotato.core.logger import CPLog
 from couchpotato.core.media._base.searcher.main import SearchSetupError
 from couchpotato.core.plugins.base import Plugin
-from couchpotato.core.settings.model import Media
+from couchpotato.core.settings.model import Media, Library
+from caper import Caper
 
 log = CPLog(__name__)
 
@@ -14,6 +17,15 @@ class ShowSearcher(Plugin):
 
     in_progress = False
 
+    # TODO come back to this later, think this could be handled better
+    quality_map = {
+        'webdl_1080p': {'resolution': ['1080p'], 'source': ['webdl']},
+        'webdl_720p': {'resolution': ['720p'], 'source': ['webdl']},
+
+        'hdtv_720p': {'resolution': ['720p'], 'source': ['hdtv']},
+        'hdtv_sd': {'resolution': ['480p', None], 'source': ['hdtv']},
+    }
+
     def __init__(self):
         super(ShowSearcher, self).__init__()
 
@@ -21,10 +33,12 @@ class ShowSearcher(Plugin):
         addEvent('searcher.correct_release', self.correctRelease)
         addEvent('searcher.get_search_title', self.getSearchTitle)
 
+        self.caper = Caper()
+
     def _lookupMedia(self, media):
         db = get_session()
 
-        media_library = db.query(Media).filter_by(id = media['id']).first().library
+        media_library = db.query(Library).filter_by(id = media['library_id']).first()
 
         show = None
         season = None
@@ -45,6 +59,8 @@ class ShowSearcher(Plugin):
         return show, season, episode
 
     def single(self, media, search_protocols = None):
+        pprint.pprint(media)
+
         if media['type'] == 'show':
             # TODO handle show searches (scan all seasons)
             return
@@ -70,7 +86,7 @@ class ShowSearcher(Plugin):
         found_releases = []
         too_early_to_search = []
 
-        default_title = getTitle(media['library'])
+        default_title = self.getSearchTitle(media['library'])
         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)
@@ -126,14 +142,118 @@ class ShowSearcher(Plugin):
         if not fireEvent('searcher.correct_words', release['name'], media, single = True):
             return False
 
-        preferred_quality = fireEvent('quality.single', identifier = quality['identifier'], single = True)
+        #pprint.pprint(release)
+
+        show, season, episode = self._lookupMedia(media)
+        if show is None or season is None:
+            log.error('Unable to find show or season library in database, missing required data for searching')
+            return
+
+        release_info = self.caper.parse(release['name'])
+        if len(release_info.chains) < 1:
+            log.info2('Wrong: %s, unable to parse release name (no chains)', release['name'])
+            return False
+
+        # TODO look at all chains
+        chain = release_info.chains[0]
+
+        if not self.correctQuality(chain, quality['identifier']):
+            log.info('Wrong: %s, quality does not match', release['name'])
+            return False
+
+        if not self.correctIdentifier(chain, media):
+            log.info('Wrong: %s, identifier does not match', release['name'])
+            return False
+
+        #print chain.weight
+        #pprint.pprint(chain.info)
+
+        if 'show_name' not in chain.info or not len(chain.info['show_name']):
+            log.info('Wrong: %s, missing show name in parsed result', release['name'])
+            return False
+
+        chain_words = [x.lower() for x in chain.info['show_name']]
+        chain_title = ' '.join(chain_words)
+
+        library_title = None
+
+        # Check show titles match
+        for raw_title in show.titles:
+            for valid_words in [x.split(' ') for x in possibleTitles(raw_title.title)]:
+                if not library_title:
+                    library_title = ' '.join(valid_words)
+
+                if valid_words == chain_words:
+                    return True
+
+        log.info("Wrong: title '%s', undetermined show naming. Looking for '%s (%s)'", (chain_title, library_title, media['library']['year']))
+        return False
 
-        # Contains lower quality string
-        if fireEvent('searcher.contains_other_quality', release, preferred_quality = preferred_quality, single = True):
-            log.info2('Wrong: %s, looking for %s', (release['name'], quality['label']))
+    def correctQuality(self, chain, quality_identifier):
+        if quality_identifier not in self.quality_map:
+            log.info2('Wrong: unknown preferred quality %s for TV searching', quality_identifier)
             return False
 
-        pprint.pprint(release)
+        if 'video' not in chain.info:
+            log.info2('Wrong: no video tags found')
+            return False
+
+        video_tags = self.quality_map[quality_identifier]
+
+        if not self.chainMatches(chain, 'video', video_tags):
+            log.info2('Wrong: %s tags not in chain', video_tags)
+            return False
+
+        return True
+
+    def correctIdentifier(self, chain, media):
+        required_id = self.getIdentifier(media['library'], 'season_number', 'episode_number')
+
+        if 'identifier' not in chain.info:
+            return False
+
+        # TODO could be handled better?
+        if len(chain.info['identifier']) != 1:
+            return False
+        identifier = chain.info['identifier'][0]
+
+        # TODO air by date episodes
+        release_id = self.getIdentifier(identifier, 'season', 'episode')
+
+        if required_id != release_id:
+            log.info2('Wrong: required identifier %s does not match release identifier %s', (str(required_id), str(release_id)))
+            return False
+
+        return True
+
+    def getIdentifier(self, d, episode_key, season_key):
+        return (
+            tryInt(d.get(season_key), None) if season_key in d else None,
+            tryInt(d.get(episode_key), None) if episode_key in d else None
+        )
+
+    def chainMatches(self, chain, group, tags):
+        found_tags = []
+
+        for match in chain.info[group]:
+            for ck, cv in match.items():
+                if ck in tags and self.cleanMatchValue(cv) in tags[ck]:
+                    found_tags.append(ck)
+
+
+        if set(tags.keys()) == set(found_tags):
+            return True
+
+        return set([key for key, value in tags.items() if value]) == set(found_tags)
+
+    def cleanMatchValue(self, value):
+        value = value.lower()
+        value = value.strip()
+
+        for ch in [' ', '-', '.']:
+            value = value.replace(ch, '')
+
+        return value
 
     def getSearchTitle(self, media):
         show, season, episode = self._lookupMedia(media)

couchpotato/core/plugins/quality/main.py

@@ -26,7 +26,15 @@ class QualityPlugin(Plugin):
         {'identifier': 'r5', 'size': (600, 1000), 'label': 'R5', 'alternative': ['r6'], 'allow': ['dvdr'], 'ext':['avi', 'mpg', 'mpeg']},
         {'identifier': 'tc', 'size': (600, 1000), 'label': 'TeleCine', 'alternative': ['telecine'], 'allow': [], 'ext':['avi', 'mpg', 'mpeg']},
         {'identifier': 'ts', 'size': (600, 1000), 'label': 'TeleSync', 'alternative': ['telesync', 'hdts'], 'allow': [], 'ext':['avi', 'mpg', 'mpeg']},
-        {'identifier': 'cam', 'size': (600, 1000), 'label': 'Cam', 'alternative': ['camrip', 'hdcam'], 'allow': [], 'ext':['avi', 'mpg', 'mpeg']}
+        {'identifier': 'cam', 'size': (600, 1000), 'label': 'Cam', 'alternative': ['camrip', 'hdcam'], 'allow': [], 'ext':['avi', 'mpg', 'mpeg']},
+
+        # TODO come back to this later, think this could be handled better
+        # WEB-DL
+        {'identifier': 'webdl_1080p', 'hd': True, 'size': (800, 5000), 'label': 'WEB-DL - 1080p', 'width': 1920, 'height': 1080, 'alternative': [], 'allow': [], 'ext':['mkv']},
+        {'identifier': 'webdl_720p', 'hd': True, 'size': (800, 5000), 'label': 'WEB-DL - 720p', 'width': 1280, 'height': 720, 'alternative': [], 'allow': [], 'ext':['mkv']},
+        # HDTV
+        {'identifier': 'hdtv_720p', 'hd': True, 'size': (800, 5000), 'label': 'HDTV - 720p', 'width': 1280, 'height': 720, 'alternative': [], 'allow': [], 'ext':['mkv']},
+        {'identifier': 'hdtv_sd', 'hd': False, 'size': (100, 1000), 'label': 'HDTV - SD', 'width': 720, 'alternative': [], 'allow': [], 'ext':['mkv', 'mp4', 'avi']},
     ]
     pre_releases = ['cam', 'ts', 'tc', 'r5', 'scr']
 

couchpotato/core/providers/torrent/iptorrents/main.py

@@ -36,21 +36,22 @@ class Base(TorrentProvider):
             log.warning('Unable to find category for quality %s', quality_identifier)
             return
 
-        return self.urls['search'] % (cat_id, tryUrlencode(query))
+        return self.urls['search'] % (cat_id, tryUrlencode(query).replace('%', '%%'))
 
     def _searchOnTitle(self, title, media, quality, results):
 
         freeleech = '' if not self.conf('freeleech') else '&free=on'
 
+        base_url = self.buildUrl(title, media, quality)
+        if not base_url: return
+
         pages = 1
         current_page = 1
         while current_page <= pages and not self.shuttingDown():
-            url = self.buildUrl(title, media, quality)
-            if not url: return
-
-            url = url  % (freeleech, current_page)
-
-            data = self.getHTMLData(url, opener = self.login_opener)
+            data = self.getHTMLData(
+                base_url  % (freeleech, current_page),
+                opener = self.login_opener
+            )
 
             if data:
                 html = BeautifulSoup(data)
@@ -135,12 +136,12 @@ class Show(ShowProvider, Base):
 
     cat_ids = [
         ('season', [
-            ([65], ['hdtv', '480p', '720p', '1080p']),
+            ([65], ['hdtv_sd', 'hdtv_720p', 'webdl_720p', 'webdl_1080p']),
         ]),
         ('episode', [
-            ([5], ['720p', '1080p']),
-            ([78], ['480p']),
-            ([4, 79], ['hdtv'])
+            ([5], ['hdtv_720p', 'webdl_720p', 'webdl_1080p']),
+            ([78], ['hdtv_sd']),
+            ([4, 79], ['hdtv_sd'])
         ])
     ]