Merge pull request #971 from JackDandy/feature/AddProvMDL

Add MagnetDL torrent provider.

CHANGES.md

@@ -50,6 +50,7 @@
 * Add option to limit WebDL propers to original release group under Config/Search/Media Search
 * Change add IPv4 config option when enabling IPv6.
 * Add autoProcessTV/onTxComplete.bat to improve Windows clients Deluge, qBittorrent, Tranmission, and uTorrent
+* Add MagnetDL torrent provider
 * Add Skytorrents torrent provider
 * Change do not have shows checked by default on import page. To re-enable import shows checked by default,
   1) On config page 'Save' 2) Stop SG 3) Find 'import_default_checked_shows' in config.ini and set '1' 4) Start SG

sickbeard/helpers.py

@@ -1103,46 +1103,58 @@ def proxy_setting(proxy_setting, request_url, force=False):
 def getURL(url, post_data=None, params=None, headers=None, timeout=30, session=None, json=False,
            raise_status_code=False, raise_exceptions=False, **kwargs):
     """
-    Returns a byte-string retrieved from the url provider.
+    Either
+    1) Returns a byte-string retrieved from the url provider.
+    2) Return True/False if success after using kwargs 'savefile' set to file pathname.
     """
 
-    # request session
+    # download and save file or simply fetch url
+    savename = None
+    if 'savename' in kwargs:
+        # session streaming
+        session.stream = True
+        savename = kwargs.pop('savename')
+
+    # selectively mute some errors
+    mute = []
+    for muted in filter(
+            lambda x: kwargs.get(x, False), ['mute_connect_err', 'mute_read_timeout', 'mute_connect_timeout']):
+        mute += [muted]
+        del kwargs[muted]
+
+    # reuse or instantiate request session
     if None is session:
         session = CloudflareScraper.create_scraper()
 
-    if not kwargs.get('nocache'):
+    if 'nocache' in kwargs:
+        del kwargs['nocache']
+    else:
         cache_dir = sickbeard.CACHE_DIR or _getTempDir()
         session = CacheControl(sess=session, cache=caches.FileCache(ek.ek(os.path.join, cache_dir, 'sessions')))
-    else:
-        del(kwargs['nocache'])
 
-    # request session headers
+    # session master headers
-    req_headers = {'User-Agent': USER_AGENT, 'Accept-Encoding': 'gzip,deflate'}
+    req_headers = {'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
+                   'Accept-Encoding': 'gzip,deflate', 'User-Agent': USER_AGENT}
     if headers:
         req_headers.update(headers)
     if hasattr(session, 'reserved') and 'headers' in session.reserved:
         req_headers.update(session.reserved['headers'] or {})
     session.headers.update(req_headers)
 
-    mute = []
+    # session paramaters
-    for muted in filter(
+    session.params = params
-            lambda x: kwargs.get(x, False), ['mute_connect_err', 'mute_read_timeout', 'mute_connect_timeout']):
-        mute += [muted]
-        del kwargs[muted]
 
-    # request session ssl verify
+    # session ssl verify
     session.verify = False
 
-    # request session paramaters
+    response = None
-    session.params = params
-
     try:
-        # Remove double-slashes from url
+        # sanitise url
         parsed = list(urlparse.urlparse(url))
-        parsed[2] = re.sub("/{2,}", "/", parsed[2])  # replace two or more / with one
+        parsed[2] = re.sub('/{2,}', '/', parsed[2])  # replace two or more / with one
         url = urlparse.urlunparse(parsed)
 
-        # request session proxies
+        # session proxies
         if sickbeard.PROXY_SETTING:
             (proxy_address, pac_found) = proxy_setting(sickbeard.PROXY_SETTING, url)
             msg = '%sproxy for url: %s' % (('', 'PAC parsed ')[pac_found], url)
@@ -1151,46 +1163,45 @@ def getURL(url, post_data=None, params=None, headers=None, timeout=30, session=N
                 return
             elif proxy_address:
                 logger.log('Using %s' % msg, logger.DEBUG)
-                session.proxies = {
+                session.proxies = {'http': proxy_address, 'https': proxy_address}
-                    'http': proxy_address,
-                    'https': proxy_address
-                }
 
         # decide if we get or post data to server
         if 'post_json' in kwargs:
-            kwargs.setdefault('json', kwargs.get('post_json'))
+            kwargs.setdefault('json', kwargs.pop('post_json'))
-            del(kwargs['post_json'])
+
         if post_data:
             kwargs.setdefault('data', post_data)
+
         if 'data' in kwargs or 'json' in kwargs:
-            resp = session.post(url, timeout=timeout, **kwargs)
+            response = session.post(url, timeout=timeout, **kwargs)
         else:
-            resp = session.get(url, timeout=timeout, **kwargs)
+            response = session.get(url, timeout=timeout, **kwargs)
-            if resp.ok and not resp.content and 'url=' in resp.headers.get('Refresh', '').lower():
+            if response.ok and not response.content and 'url=' in response.headers.get('Refresh', '').lower():
-                url = resp.headers.get('Refresh').lower().split('url=')[1].strip('/')
+                url = response.headers.get('Refresh').lower().split('url=')[1].strip('/')
                 if not url.startswith('http'):
                     parsed[2] = '/%s' % url
                     url = urlparse.urlunparse(parsed)
-                resp = session.get(url, timeout=timeout, **kwargs)
+                response = session.get(url, timeout=timeout, **kwargs)
 
         if raise_status_code:
-            resp.raise_for_status()
+            response.raise_for_status()
-
+
-        if not resp.ok:
+        if not response.ok:
-            http_err_text = 'CloudFlare Ray ID' in resp.content and 'CloudFlare reports, "Website is offline"; ' or ''
+            http_err_text = 'CloudFlare Ray ID' in response.content and \
-            if resp.status_code in clients.http_error_code:
+                            'CloudFlare reports, "Website is offline"; ' or ''
-                http_err_text += clients.http_error_code[resp.status_code]
+            if response.status_code in clients.http_error_code:
-            elif resp.status_code in range(520, 527):
+                http_err_text += clients.http_error_code[response.status_code]
+            elif response.status_code in range(520, 527):
                 http_err_text += 'Origin server connection failure'
             else:
                 http_err_text = 'Custom HTTP error code'
             logger.log(u'Response not ok. %s: %s from requested url %s'
-                       % (resp.status_code, http_err_text, url), logger.DEBUG)
+                       % (response.status_code, http_err_text, url), logger.DEBUG)
             return
 
     except requests.exceptions.HTTPError as e:
         if raise_status_code:
-            resp.raise_for_status()
+            response.raise_for_status()
         logger.log(u'HTTP error %s while loading URL%s' % (
             e.errno, _maybe_request_url(e)), logger.WARNING)
         return
@@ -1228,7 +1239,7 @@ def getURL(url, post_data=None, params=None, headers=None, timeout=30, session=N
 
     if json:
         try:
-            data_json = resp.json()
+            data_json = response.json()
             return ({}, data_json)[isinstance(data_json, (dict, list))]
         except (TypeError, Exception) as e:
             logger.log(u'JSON data issue from URL %s\r\nDetail... %s' % (url, e.message), logger.WARNING)
@@ -1236,81 +1247,36 @@ def getURL(url, post_data=None, params=None, headers=None, timeout=30, session=N
                 raise e
             return None
 
-    return resp.content
+    if savename:
-
+        try:
-
+            with open(savename, 'wb') as fp:
-def _maybe_request_url(e, def_url=''):
+                for chunk in response.iter_content(chunk_size=1024):
-    return hasattr(e, 'request') and hasattr(e.request, 'url') and ' ' + e.request.url or def_url
+                    if chunk:
+                        fp.write(chunk)
+                        fp.flush()
+                ek.ek(os.fsync, fp.fileno())
 
+            chmodAsParent(savename)
 
-def download_file(url, filename, session=None):
+        except EnvironmentError as e:
-    # create session
+            logger.log(u'Unable to save the file: ' + ex(e), logger.ERROR)
-    if None is session:
+            if raise_exceptions:
-        session = CloudflareScraper.create_scraper()
+                raise e
-    cache_dir = sickbeard.CACHE_DIR or _getTempDir()
+            return
-    session = CacheControl(sess=session, cache=caches.FileCache(ek.ek(os.path.join, cache_dir, 'sessions')))
+        return True
 
-    # request session headers
+    return response.content
-    session.headers.update({'User-Agent': USER_AGENT, 'Accept-Encoding': 'gzip,deflate'})
-    if hasattr(session, 'reserved') and 'headers' in session.reserved:
-        session.headers.update(session.reserved['headers'] or {})
 
-    # request session ssl verify
-    session.verify = False
 
-    # request session streaming
+def _maybe_request_url(e, def_url=''):
-    session.stream = True
+    return hasattr(e, 'request') and hasattr(e.request, 'url') and ' ' + e.request.url or def_url
-
-    # request session proxies
-    if sickbeard.PROXY_SETTING:
-        (proxy_address, pac_found) = proxy_setting(sickbeard.PROXY_SETTING, url)
-        msg = '%sproxy for url: %s' % (('', 'PAC parsed ')[pac_found], url)
-        if None is proxy_address:
-            logger.log('Proxy error, aborted the request using %s' % msg, logger.DEBUG)
-            return
-        elif proxy_address:
-            logger.log('Using %s' % msg, logger.DEBUG)
-            session.proxies = {
-                'http': proxy_address,
-                'https': proxy_address
-            }
 
-    try:
-        resp = session.get(url)
-        if not resp.ok:
-            logger.log(u"Requested url " + url + " returned status code is " + str(
-                resp.status_code) + ': ' + clients.http_error_code[resp.status_code], logger.DEBUG)
-            return False
 
-        with open(filename, 'wb') as fp:
+def download_file(url, filename, session=None, **kwargs):
-            for chunk in resp.iter_content(chunk_size=1024):
-                if chunk:
-                    fp.write(chunk)
-                    fp.flush()
-            ek.ek(os.fsync, fp.fileno())
 
-        chmodAsParent(filename)
+    if None is getURL(url, session=session, savename=filename, **kwargs):
-    except requests.exceptions.HTTPError as e:
-        remove_file_failed(filename)
-        logger.log(u"HTTP error " + str(e.errno) + " while loading URL " + url, logger.WARNING)
-        return False
-    except requests.exceptions.ConnectionError as e:
-        remove_file_failed(filename)
-        logger.log(u"Connection error " + str(e.message) + " while loading URL " + url, logger.WARNING)
-        return False
-    except requests.exceptions.Timeout as e:
         remove_file_failed(filename)
-        logger.log(u"Connection timed out " + str(e.message) + " while loading URL " + url, logger.WARNING)
         return False
-    except EnvironmentError as e:
-        remove_file_failed(filename)
-        logger.log(u"Unable to save the file: " + ex(e), logger.ERROR)
-        return False
-    except Exception:
-        remove_file_failed(filename)
-        logger.log(u"Unknown exception while loading URL " + url + ": " + traceback.format_exc(), logger.WARNING)
-        return False
-
     return True
 
 

sickbeard/providers/__init__.py

@@ -28,7 +28,7 @@ from . import newznab, omgwtfnzbs
 # torrent
 from . import alpharatio, beyondhd, bithdtv, bitmetv, btn, btscene, dh, \
     fano, filelist, funfile, gftracker, grabtheinfo, hd4free, hdbits, hdspace, hdtorrents, \
-    iptorrents, limetorrents, morethan, nebulance, ncore, nyaa, pisexy, pretome, privatehd, ptf, \
+    iptorrents, limetorrents, magnetdl, morethan, nebulance, ncore, nyaa, pisexy, pretome, privatehd, ptf, \
     rarbg, revtt, scenetime, shazbat, skytorrents, speedcd, \
     thepiratebay, torlock, torrentday, torrenting, torrentleech, \
     torrentz2, tvchaosuk, zooqle
@@ -37,7 +37,7 @@ from . import anizb, tokyotoshokan
 # custom
 try:
     from . import custom01
-except:
+except (StandardError, Exception):
     pass
 
 __all__ = ['omgwtfnzbs',
@@ -61,6 +61,7 @@ __all__ = ['omgwtfnzbs',
            'hdtorrents',
            'iptorrents',
            'limetorrents',
+           'magnetdl',
            'morethan',
            'nebulance',
            'ncore',

sickbeard/providers/magnetdl.py

@@ -0,0 +1,103 @@
+# coding=utf-8
+#
+# This file is part of SickGear.
+#
+# SickGear 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.
+#
+# SickGear 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 SickGear.  If not, see <http://www.gnu.org/licenses/>.
+
+import re
+import traceback
+
+from . import generic
+from sickbeard import logger
+from sickbeard.bs4_parser import BS4Parser
+from sickbeard.helpers import tryInt
+from lib.unidecode import unidecode
+
+
+class MagnetDLProvider(generic.TorrentProvider):
+
+    def __init__(self):
+
+        generic.TorrentProvider.__init__(self, 'MagnetDL', cache_update_freq=6)
+
+        self.url_base = 'http://www.magnetdl.com/'
+
+        self.urls = {'config_provider_home_uri': self.url_base,
+                     'browse': self.url_base + 'download/tv/', 'search': self.url_base + 'search/?m=1&q=%s'}
+
+        self.minseed, self.minleech = 2 * [None]
+
+    def _search_provider(self, search_params, **kwargs):
+
+        results = []
+
+        items = {'Cache': [], 'Season': [], 'Episode': [], 'Propers': []}
+
+        rc = dict((k, re.compile('(?i)' + v)) for (k, v) in {'info': '^/file/', 'get': '^magnet:'}.items())
+
+        for mode in search_params.keys():
+            for search_string in search_params[mode]:
+                search_url = self.urls['browse']
+                if 'Cache' != mode:
+                    search_string = isinstance(search_string, unicode) and unidecode(search_string) or search_string
+                    search_url = self.urls['search'] % re.sub('[.\s]+', ' ', search_string)
+
+                html = self.get_url(search_url)
+
+                cnt = len(items[mode])
+                try:
+                    if not html or self._has_no_results(html):
+                        raise generic.HaltParseException
+
+                    with BS4Parser(html, features=['html5lib', 'permissive']) as soup:
+                        torrent_table = soup.find('table', attrs={'class': 'download'})
+                        torrent_rows = [] if not torrent_table else torrent_table.find_all('tr')
+
+                        if 2 > len(torrent_rows):
+                            raise generic.HaltParseException
+
+                        head = None
+                        for tr in torrent_rows[1:]:
+                            cells = tr.find_all('td')
+                            if 5 > len(cells):
+                                continue
+                            try:
+                                head = head if None is not head else self._header_row(tr)
+                                seeders, leechers, size = [tryInt(n, n) for n in [
+                                    cells[head[x]].get_text().strip() for x in 'seed', 'leech', 'size']]
+                                if self._peers_fail(mode, seeders, leechers):
+                                    continue
+
+                                info = tr.find('a', href=rc['info'])
+                                title = (info.attrs.get('title') or info.get_text()).strip()
+                                download_url = self._link(tr.find('a', href=rc['get'])['href'])
+                            except (AttributeError, TypeError, ValueError, KeyError):
+                                continue
+
+                            if title and download_url:
+                                items[mode].append((title, download_url, seeders, self._bytesizer(size)))
+
+                except generic.HaltParseException:
+                    pass
+                except (StandardError, Exception):
+                    logger.log(u'Failed to parse. Traceback: %s' % traceback.format_exc(), logger.ERROR)
+
+                self._log_search(mode, len(items[mode]) - cnt, search_url)
+
+            results = self._sort_seeding(mode, results + items[mode])
+
+        return results
+
+
+provider = MagnetDLProvider()