[comedycentral] Improve regexes

[youtube-dl] / youtube_dl / extractor / francetv.py

diff --git a/youtube_dl/extractor/francetv.py b/youtube_dl/extractor/francetv.py
index 290e650e04eadafd3fe7fe75b152478bf3539a30..b32ff9f867a02147d8ddc145cba685f074e6155c 100644 (file)
--- a/youtube_dl/extractor/francetv.py
+++ b/youtube_dl/extractor/francetv.py
@@ -72,7 +72,7 @@ class FranceTVIE(FranceTVBaseInfoExtractor):
     _VALID_URL = r'''(?x)https?://www\.france[2345o]\.fr/
         (?:
             emissions/.*?/(videos|emissions)/(?P<id>[^/?]+)
-        |   (emission|jt)/(?P<key>[^/?]+)
+        |   (emissions?|jt)/(?P<key>[^/?]+)
         )'''
 
     _TESTS = [
@@ -91,12 +91,12 @@ class FranceTVIE(FranceTVBaseInfoExtractor):
         },
         # france3
         {
-            u'url': u'http://www.france3.fr/emissions/pieces-a-conviction/videos/rhozet_pac_ba_20131204_1933_03122013164521_F3',
+            u'url': u'http://www.france3.fr/emissions/pieces-a-conviction/diffusions/13-11-2013_145575',
             u'info_dict': {
-                u'id': u'rhozet_pac_ba_20131204_1933_03122013164521_F3',
+                u'id': u'000702326_CAPP_PicesconvictionExtrait313022013_120220131722_Au',
                 u'ext': u'flv',
-                u'title': u'Pièces à conviction du 04/12/2013',
-                u'description': u'md5:1cf14ea302ba5f10d992c9eb2bff30dd',
+                u'title': u'Le scandale du prix des médicaments',
+                u'description': u'md5:1384089fbee2f04fc6c9de025ee2e9ce',
             },
             u'params': {
                 # rtmp download
@@ -158,6 +158,7 @@ class FranceTVIE(FranceTVBaseInfoExtractor):
                     class="francetv-video-player">'''),
                 (r'<a id="player_direct" href="http://info\.francetelevisions'
                  '\.fr/\?id-video=([^"/&]+)'),
+                (r'<a class="video" id="ftv_player_(.+?)"'),
             ]
             video_id = self._html_search_regex(id_res, webpage, u'video ID')
         else:
@@ -190,3 +191,29 @@ class GenerationQuoiIE(InfoExtractor):
         info = json.loads(info_json)
         return self.url_result('http://www.dailymotion.com/video/%s' % info['id'],
             ie='Dailymotion')
+
+
+class CultureboxIE(FranceTVBaseInfoExtractor):
+    IE_NAME = u'culturebox.francetvinfo.fr'
+    _VALID_URL = r'https?://culturebox\.francetvinfo\.fr/(?P<name>.*?)(\?|$)'
+
+    _TEST = {
+        u'url': u'http://culturebox.francetvinfo.fr/einstein-on-the-beach-au-theatre-du-chatelet-146813',
+        u'info_dict': {
+            u'id': u'EV_6785',
+            u'ext': u'mp4',
+            u'title': u'Einstein on the beach au Théâtre du Châtelet',
+            u'description': u'md5:9ce2888b1efefc617b5e58b3f6200eeb',
+        },
+        u'params': {
+            # m3u8 download
+            u'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        name = mobj.group('name')
+        webpage = self._download_webpage(url, name)
+        video_id = self._search_regex(r'"http://videos\.francetv\.fr/video/(.*?)"', webpage, u'video id')
+        return self._extract_video(video_id)