youtube-dl

commit 0954cd8aa4421b1844a30e99702c364f1fffc15f
parent da55dac047d63d48fd12247369b2fb858c4210ef
Author: Yen Chi Hsuan <yan12125@gmail.com>
Date:   Tue, 21 Apr 2015 13:48:02 +0800

[Cinemassacre] Add detection for videos from blip.tv

Diffstat:
M
youtube_dl/extractor/bliptv.py
 | 
9
+++++++++
M
youtube_dl/extractor/generic.py
 | 
10
++++------
M
youtube_dl/extractor/screenwavemedia.py
 | 
23
++++++++++++++++++++++-

3 files changed, 35 insertions(+), 7 deletions(-)
diff --git a/youtube_dl/extractor/bliptv.py b/youtube_dl/extractor/bliptv.py
@@ -102,6 +102,15 @@ class BlipTVIE(InfoExtractor):
         },
     ]
 
+    @staticmethod
+    def _extract_url(webpage):
+        mobj = re.search(r'<meta\s[^>]*https?://api\.blip\.tv/\w+/redirect/\w+/(\d+)', webpage)
+        if mobj:
+            return 'http://blip.tv/a/a-' + mobj.group(1)
+        mobj = re.search(r'<(?:iframe|embed|object)\s[^>]*(https?://(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)[a-zA-Z0-9_]+)', webpage)
+        if mobj:
+            return mobj.group(1)
+
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         lookup_id = mobj.group('lookup_id')
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
@@ -36,6 +36,7 @@ from .smotri import SmotriIE
 from .condenast import CondeNastIE
 from .udn import UDNEmbedIE
 from .senateisvp import SenateISVPIE
+from .bliptv import BlipTVIE
 
 
 class GenericIE(InfoExtractor):
@@ -1073,12 +1074,9 @@ class GenericIE(InfoExtractor):
             }
 
         # Look for embedded blip.tv player
-        mobj = re.search(r'<meta\s[^>]*https?://api\.blip\.tv/\w+/redirect/\w+/(\d+)', webpage)
-        if mobj:
-            return self.url_result('http://blip.tv/a/a-' + mobj.group(1), 'BlipTV')
-        mobj = re.search(r'<(?:iframe|embed|object)\s[^>]*(https?://(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)[a-zA-Z0-9_]+)', webpage)
-        if mobj:
-            return self.url_result(mobj.group(1), 'BlipTV')
+        bliptv_url = BlipTVIE._extract_url(webpage)
+        if bliptv_url:
+            return self.url_result(bliptv_url, 'BlipTV')
 
         # Look for embedded condenast player
         matches = re.findall(
diff --git a/youtube_dl/extractor/screenwavemedia.py b/youtube_dl/extractor/screenwavemedia.py
@@ -7,7 +7,9 @@ from .common import InfoExtractor
 from ..utils import (
     int_or_none,
     unified_strdate,
+    ExtractorError
 )
+from .bliptv import BlipTVIE
 
 
 class ScreenwaveMediaIE(InfoExtractor):
@@ -104,6 +106,20 @@ class CinemassacreIE(InfoExtractor):
                 'upload_date': '20131002',
                 'title': 'The Mummy’s Hand (1940)',
             },
+        },
+        {
+            'url': 'http://cinemassacre.com/2006/12/07/chronologically-confused-about-bad-movie-and-video-game-sequel-titles/',
+            'md5': 'ca9b3c8dd5a66f9375daeb5135f5a3de',
+            'info_dict': {
+                'id': '4065369',
+                'ext': 'flv',
+                'title': 'AVGN: Chronologically Confused about Bad Movie and Video Game Sequel Titles',
+                'upload_date': '20061207',
+                'uploader': 'cinemassacre',
+                'uploader_id': '250778',
+                'timestamp': 1283233867,
+                'description': 'md5:0a108c78d130676b207d0f6d029ecffd',
+            }
         }
     ]
 
@@ -116,7 +132,12 @@ class CinemassacreIE(InfoExtractor):
 
         playerdata_url = self._search_regex(
             r'src="(http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=.+?)"',
-            webpage, 'player data URL')
+            webpage, 'player data URL', default=None)
+        if not playerdata_url:
+            playerdata_url = BlipTVIE._extract_url(webpage)
+        if not playerdata_url:
+            raise ExtractorError('Unable to find player data')
+
         video_title = self._html_search_regex(
             r'<title>(?P<title>.+?)\|', webpage, 'title')
         video_description = self._html_search_regex(