Merge pull request #2273 from dstftw/crunchyroll

[crunchyroll] Add support for mobile URLs and use unicode literals

diff --git a/youtube_dl/extractor/comedycentral.py b/youtube_dl/extractor/comedycentral.py
index 3333d433bc42f89c0dc8dc7ff264010ef5bda9a6..ed3986f313a149f0db4a69dc92762730297ced1a 100644 (file)
--- a/youtube_dl/extractor/comedycentral.py
+++ b/youtube_dl/extractor/comedycentral.py
@@ -14,7 +14,7 @@ from ..utils import (
 
 
 class ComedyCentralIE(MTVServicesInfoExtractor):
-    _VALID_URL = r'''(?x)https?://(?:www.)?comedycentral.com/
+    _VALID_URL = r'''(?x)https?://(?:www\.)?comedycentral\.com/
         (video-clips|episodes|cc-studios|video-collections)
         /(?P<title>.*)'''
     _FEED_URL = 'http://comedycentral.com/feeds/mrss/'
@@ -86,7 +86,7 @@ class ComedyCentralShowsIE(InfoExtractor):
 
     @staticmethod
     def _transform_rtmp_url(rtmp_video_url):
-        m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp.comedystor/.*)$', rtmp_video_url)
+        m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp\.comedystor/.*)$', rtmp_video_url)
         if not m:
             raise ExtractorError('Cannot transform RTMP url')
         base = 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=1+_pxI0=Ripod-h264+_pxL0=undefined+_pxM0=+_pxK=18639+_pxE=mp4/44620/mtvnorigin/'

diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index 48de379b723741ed826e19bc1d4db308cf7bed8e..e0d51996ded5f1604bebe5d0c03c1dbc815f31ce 100644 (file)
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -254,7 +254,7 @@ class GenericIE(InfoExtractor):
 
         # Look for embedded (iframe) Vimeo player
         mobj = re.search(
-            r'<iframe[^>]+?src="((?:https?:)?//player.vimeo.com/video/.+?)"', webpage)
+            r'<iframe[^>]+?src="((?:https?:)?//player\.vimeo\.com/video/.+?)"', webpage)
         if mobj:
             player_url = unescapeHTML(mobj.group(1))
             surl = smuggle_url(player_url, {'Referer': url})
@@ -262,7 +262,7 @@ class GenericIE(InfoExtractor):
 
         # Look for embedded (swf embed) Vimeo player
         mobj = re.search(
-            r'<embed[^>]+?src="(https?://(?:www\.)?vimeo.com/moogaloop.swf.+?)"', webpage)
+            r'<embed[^>]+?src="(https?://(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage)
         if mobj:
             return self.url_result(mobj.group(1), 'Vimeo')
 
@@ -332,7 +332,7 @@ class GenericIE(InfoExtractor):
             return self.url_result(mobj.group(1), 'Aparat')
 
         # Look for MPORA videos
-        mobj = re.search(r'<iframe .*?src="(http://mpora\.com/videos/[^"]+)"', webpage)
+        mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
         if mobj is not None:
             return self.url_result(mobj.group(1), 'Mpora')
 
@@ -350,7 +350,7 @@ class GenericIE(InfoExtractor):
 
         # Look for embedded Huffington Post player
         mobj = re.search(
-            r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live.huffingtonpost\.com/.+?)\1', webpage)
+            r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
         if mobj is not None:
             return self.url_result(mobj.group('url'), 'HuffPost')
 

diff --git a/youtube_dl/extractor/liveleak.py b/youtube_dl/extractor/liveleak.py
index d01fd01e3a5413b8b98305c94507ce25d8dab44e..a571fa742e32433c3a5ba0591958d4d87237d0c7 100644 (file)
--- a/youtube_dl/extractor/liveleak.py
+++ b/youtube_dl/extractor/liveleak.py
@@ -1,5 +1,6 @@
 from __future__ import unicode_literals
 
+import json
 import re
 
 from .common import InfoExtractor
@@ -26,8 +27,16 @@ class LiveLeakIE(InfoExtractor):
 
         video_id = mobj.group('video_id')
         webpage = self._download_webpage(url, video_id)
-        video_url = self._search_regex(
-            r'file: "(.*?)",', webpage, 'video URL')
+        sources_raw = self._search_regex(
+            r'(?s)sources:\s*(\[.*?\]),', webpage, 'video URLs')
+        sources_json = re.sub(r'\s([a-z]+):\s', r'"\1": ', sources_raw)
+        sources = json.loads(sources_json)
+
+        formats = [{
+            'format_note': s.get('label'),
+            'url': s['file'],
+        } for s in sources]
+        self._sort_formats(formats)
 
         video_title = self._og_search_title(webpage).replace('LiveLeak.com -', '').strip()
         video_description = self._og_search_description(webpage)
@@ -36,9 +45,8 @@ class LiveLeakIE(InfoExtractor):
 
         return {
             'id': video_id,
-            'url': video_url,
-            'ext': 'mp4',
             'title': video_title,
             'description': video_description,
-            'uploader': video_uploader
+            'uploader': video_uploader,
+            'formats': formats,
         }

diff --git a/youtube_dl/version.py b/youtube_dl/version.py
index 7158105c2af7863af2cc3bf99f03cddafae757d0..b9b0ca31294d57641f954d1e8e982f30720f0eeb 100644 (file)
--- a/youtube_dl/version.py
+++ b/youtube_dl/version.py
@@ -1,2 +1,2 @@
 
-__version__ = '2014.01.29'
+__version__ = '2014.01.30'