add direct screenwavemedia.com URL support

youtube_dl/extractor/__init__.py

@@ -50,7 +50,6 @@ from .cbsnews import CBSNewsIE
 from .ceskatelevize import CeskaTelevizeIE
 from .channel9 import Channel9IE
 from .chilloutzone import ChilloutzoneIE
-from .cinemassacre import CinemassacreIE
 from .clipfish import ClipfishIE
 from .cliphunter import CliphunterIE
 from .clipsyndicate import ClipsyndicateIE
@@ -335,6 +334,7 @@ from .savefrom import SaveFromIE
 from .sbs import SBSIE
 from .scivee import SciVeeIE
 from .screencast import ScreencastIE
+from .screenwavemedia import ScreenwaveMediaIE
 from .servingsys import ServingSysIE
 from .sexu import SexuIE
 from .sexykarma import SexyKarmaIE

youtube_dl/extractor/screenwavemedia.py

@@ -9,15 +9,18 @@ from ..utils import (
     int_or_none,
 )
 
+class ScreenwaveMediaIE(InfoExtractor):
+    _VALID_URL = r'(?:http://)?(?' \
+        r':(?P<generic>player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=(?P<video_id>.+))' \
+        r'|(?P<cinemassacre>(?:www\.)?cinemassacre\.com/(?P<cm_date_Y>[0-9]{4})/(?P<cm_date_m>[0-9]{2})/(?P<cm_date_d>[0-9]{2})/(?P<cm_display_id>[^?#/]+))' \
+        r')'
 
-class CinemassacreIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?cinemassacre\.com/(?P<date_Y>[0-9]{4})/(?P<date_m>[0-9]{2})/(?P<date_d>[0-9]{2})/(?P<display_id>[^?#/]+)'
     _TESTS = [
         {
             'url': 'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/',
             'md5': 'fde81fbafaee331785f58cd6c0d46190',
             'info_dict': {
-                'id': '19911',
+                'id': 'Cinemasssacre-19911',
                 'ext': 'mp4',
                 'upload_date': '20121110',
                 'title': '“Angry Video Game Nerd: The Movie” – Trailer',
@@ -28,7 +31,7 @@ class CinemassacreIE(InfoExtractor):
             'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940',
             'md5': 'd72f10cd39eac4215048f62ab477a511',
             'info_dict': {
-                'id': '521be8ef82b16',
+                'id': 'Cinemasssacre-521be8ef82b16',
                 'ext': 'mp4',
                 'upload_date': '20131002',
                 'title': 'The Mummy’s Hand (1940)',
@@ -36,18 +39,16 @@ class CinemassacreIE(InfoExtractor):
         }
     ]
 
-    def _real_extract(self, url):
+    def _cinemassacre_get_info(self, url):
         mobj = re.match(self._VALID_URL, url)
-        display_id = mobj.group('display_id')
+        display_id = mobj.group('cm_display_id')
 
         webpage = self._download_webpage(url, display_id)
-        video_date = mobj.group('date_Y') + mobj.group('date_m') + mobj.group('date_d')
-        mobj = re.search(r'src="(?P<embed_url>http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=(?P<full_video_id>(?:Cinemassacre-)?(?P<video_id>.+?)))"', webpage)
+        video_date = mobj.group('cm_date_Y') + mobj.group('cm_date_m') + mobj.group('cm_date_d')
+        mobj = re.search(r'src="(?P<embed_url>http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=.+?)"', webpage)
         if not mobj:
             raise ExtractorError('Can\'t extract embed url and video id')
         playerdata_url = mobj.group('embed_url')
-        video_id = mobj.group('video_id')
-        full_video_id = mobj.group('full_video_id')
 
         video_title = self._html_search_regex(
             r'<title>(?P<title>.+?)\|', webpage, 'title')
@@ -56,10 +57,28 @@ class CinemassacreIE(InfoExtractor):
             webpage, 'description', flags=re.DOTALL, fatal=False)
         video_thumbnail = self._og_search_thumbnail(webpage)
 
-        playerdata = self._download_webpage(playerdata_url, video_id, 'Downloading player webpage')
+        return {
+            'title': video_title,
+            'description': video_description,
+            'upload_date': video_date,
+            'thumbnail': video_thumbnail,
+            '_embed_url': playerdata_url,
+        }
 
+    def _screenwavemedia_get_info(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        if not mobj:
+            raise ExtractorError('Can\'t extract embed url and video id')
+        video_id = mobj.group('video_id')
+
+        playerdata = self._download_webpage(url, video_id, 'Downloading player webpage')
+
+        vidtitle = self._search_regex(
+            r'\'vidtitle\'\s*:\s*"([^\']+)"', playerdata, 'vidtitle').replace('\\/', '/')
         vidurl = self._search_regex(
             r'\'vidurl\'\s*:\s*"([^\']+)"', playerdata, 'vidurl').replace('\\/', '/')
+        pageurl = self._search_regex(
+            r'\'pageurl\'\s*:\s*"([^\']+)"', playerdata, 'pageurl', fatal=False).replace('\\/', '/')
 
         videolist_url = None
 
@@ -67,7 +86,7 @@ class CinemassacreIE(InfoExtractor):
         if mobj:
             videoserver = mobj.group('videoserver')
             mobj = re.search(r'\'vidid\'\s*:\s*"(?P<vidid>[^\']+)"', playerdata)
-            vidid = mobj.group('vidid') if mobj else full_video_id
+            vidid = mobj.group('vidid') if mobj else video_id
             videolist_url = 'http://%s/vod/smil:%s.smil/jwplayer.smil' % (videoserver, vidid)
         else:
             mobj = re.search(r"file\s*:\s*'(?P<smil>http.+?/jwplayer\.smil)'", playerdata)
@@ -110,9 +129,34 @@ class CinemassacreIE(InfoExtractor):
 
         return {
             'id': video_id,
-            'title': video_title,
+            'title': vidtitle,
             'formats': formats,
-            'description': video_description,
-            'upload_date': video_date,
-            'thumbnail': video_thumbnail,
+            '_episode_page': pageurl,
         }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+
+        swm_info = None
+        site_info = None
+
+        if mobj.group('generic'):
+            swm_info = self._screenwavemedia_get_info(url)
+            url = swm_info['_episode_page']
+            mobj = re.match(self._VALID_URL, url)
+
+        if mobj:
+            if mobj.group('cinemassacre'):
+                site_info = self._cinemassacre_get_info(url)
+
+        if not swm_info:
+            if site_info:
+                swm_info = self._screenwavemedia_get_info(site_info['_embed_url'])
+
+        if not swm_info:
+            raise ExtractorError("Failed to extract metadata for this URL")
+
+        if site_info:
+            swm_info.update(site_info)
+
+        return swm_info