[francetv] Add support for more channels: 3, 4, 5 and Ô (#1898)

Rename the France2IE extractor to FranceTVIE

youtube_dl/extractor/__init__.py

@@ -56,7 +56,7 @@ from .flickr import FlickrIE
 from .francetv import (
     PluzzIE,
     FranceTvInfoIE,
-    France2IE,
+    FranceTVIE,
     GenerationQuoiIE
 )
 from .freesound import FreesoundIE

youtube_dl/extractor/francetv.py

@@ -21,7 +21,7 @@ class FranceTVBaseInfoExtractor(InfoExtractor):
         thumbnail_path = info.find('image').text
 
         return {'id': video_id,
-                'ext': 'mp4',
+                'ext': 'flv' if video_url.startswith('rtmp') else 'mp4',
                 'url': video_url,
                 'title': info.find('titre').text,
                 'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', thumbnail_path),
@@ -66,15 +66,18 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor):
         return self._extract_video(video_id)
 
 
-class France2IE(FranceTVBaseInfoExtractor):
+class FranceTVIE(FranceTVBaseInfoExtractor):
-    IE_NAME = u'france2.fr'
+    IE_NAME = u'francetv'
-    _VALID_URL = r'''(?x)https?://www\.france2\.fr/
+    IE_DESC = u'France 2, 3, 4, 5 and Ô'
+    _VALID_URL = r'''(?x)https?://www\.france[2345o]\.fr/
         (?:
-            emissions/.*?/videos/(?P<id>\d+)
+            emissions/.*?/(videos|emissions)/(?P<id>[^/?]+)
-        |   emission/(?P<key>[^/?]+)
+        |   (emission|jt)/(?P<key>[^/?]+)
         )'''
 
-    _TEST = {
+    _TESTS = [
+        # france2
+        {
             u'url': u'http://www.france2.fr/emissions/13h15-le-samedi-le-dimanche/videos/75540104',
             u'file': u'75540104.mp4',
             u'info_dict': {
@@ -82,19 +85,81 @@ class France2IE(FranceTVBaseInfoExtractor):
                 u'description': u'md5:2e5b58ba7a2d3692b35c792be081a03d',
             },
             u'params': {
+                # m3u8 download
                 u'skip_download': True,
             },
-    }
+        },
+        # france3
+        {
+            u'url': u'http://www.france3.fr/emissions/pieces-a-conviction/videos/rhozet_pac_ba_20131204_1933_03122013164521_F3',
+            u'info_dict': {
+                u'id': u'rhozet_pac_ba_20131204_1933_03122013164521_F3',
+                u'ext': u'flv',
+                u'title': u'Pièces à conviction du 04/12/2013',
+                u'description': u'md5:1cf14ea302ba5f10d992c9eb2bff30dd',
+            },
+            u'params': {
+                # rtmp download
+                u'skip_download': True,
+            },
+        },
+        # france4
+        {
+            u'url': u'http://www.france4.fr/emissions/hero-corp/videos/rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
+            u'info_dict': {
+                u'id': u'rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
+                u'ext': u'flv',
+                u'title': u'Hero Corp Making of - Extrait 1',
+                u'description': u'md5:c87d54871b1790679aec1197e73d650a',
+            },
+            u'params': {
+                # rtmp download
+                u'skip_download': True,
+            },
+        },
+        # france5
+        {
+            u'url': u'http://www.france5.fr/emissions/c-a-dire/videos/92837968',
+            u'info_dict': {
+                u'id': u'92837968',
+                u'ext': u'mp4',
+                u'title': u'C à dire ?!',
+                u'description': u'md5:fb1db1cbad784dcce7c7a7bd177c8e2f',
+            },
+            u'params': {
+                # m3u8 download
+                u'skip_download': True,
+            },
+        },
+        # franceo
+        {
+            u'url': u'http://www.franceo.fr/jt/info-afrique/04-12-2013',
+            u'info_dict': {
+                u'id': u'92327925',
+                u'ext': u'mp4',
+                u'title': u'Infô-Afrique',
+                u'description': u'md5:ebf346da789428841bee0fd2a935ea55',
+            },
+            u'params': {
+                # m3u8 download
+                u'skip_download': True,
+            },
+            u'skip': u'The id changes frequently',
+        },
+    ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         if mobj.group('key'):
             webpage = self._download_webpage(url, mobj.group('key'))
-            video_id = self._html_search_regex(
+            id_res = [
-                r'''(?x)<div\s+class="video-player">\s*
+                (r'''(?x)<div\s+class="video-player">\s*
                     <a\s+href="http://videos.francetv.fr/video/([0-9]+)"\s+
-                    class="francetv-video-player">''',
+                    class="francetv-video-player">'''),
-                webpage, u'video ID')
+                (r'<a id="player_direct" href="http://info\.francetelevisions'
+                 '\.fr/\?id-video=([^"/&]+)'),
+            ]
+            video_id = self._html_search_regex(id_res, webpage, u'video ID')
         else:
             video_id = mobj.group('id')
         return self._extract_video(video_id)