diff options
| author | Sergey M․ <dstftw@gmail.com> | 2015-07-18 22:41:34 +0600 |
|---|---|---|
| committer | Sergey M․ <dstftw@gmail.com> | 2015-07-18 22:41:34 +0600 |
| commit | 3f5c6d0c1b955f9312b83fb0e1f3ae59d1230c82 (patch) | |
| tree | e7d444d20d37f524986e7a6a4ad5a566056812f8 /youtube_dl | |
| parent | e58066e244bf9a04c2853e8829f7939bdefc9084 (diff) | |
[francetv] Add support for embeds and clean up _VALID_URL
Diffstat (limited to 'youtube_dl')
| -rw-r--r-- | youtube_dl/extractor/francetv.py | 44 |
1 files changed, 36 insertions, 8 deletions
diff --git a/youtube_dl/extractor/francetv.py b/youtube_dl/extractor/francetv.py index b2c984bf2..827400172 100644 --- a/youtube_dl/extractor/francetv.py +++ b/youtube_dl/extractor/francetv.py @@ -160,11 +160,19 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor): class FranceTVIE(FranceTVBaseInfoExtractor): IE_NAME = 'francetv' IE_DESC = 'France 2, 3, 4, 5 and Ô' - _VALID_URL = r'''(?x)https?://www\.france[2345o]\.fr/ - (?: - emissions/.*?/(videos|emissions)/(?P<id>[^/?]+) - | (emissions?|jt)/(?P<key>[^/?]+) - )''' + _VALID_URL = r'''(?x) + https?:// + (?: + (?:www\.)?france[2345o]\.fr/ + (?: + emissions/[^/]+/(?:videos|diffusions)?| + videos + ) + /| + embed\.francetv\.fr/\?ue= + ) + (?P<id>[^/?]+) + ''' _TESTS = [ # france2 @@ -232,13 +240,33 @@ class FranceTVIE(FranceTVBaseInfoExtractor): 'timestamp': 1410822000, }, }, + { + # francetv embed + 'url': 'http://embed.francetv.fr/?ue=8d7d3da1e3047c42ade5a5d7dfd3fc87', + 'info_dict': { + 'id': 'EV_30231', + 'ext': 'flv', + 'title': 'Alcaline, le concert avec Calogero', + 'description': 'md5:', + 'upload_date': '20150226', + 'timestamp': 1424989860, + }, + }, + { + 'url': 'http://www.france4.fr/emission/highlander/diffusion-du-17-07-2015-04h05', + 'only_matching': True, + }, + { + 'url': 'http://www.franceo.fr/videos/125377617', + 'only_matching': True, + } ] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - webpage = self._download_webpage(url, mobj.group('key') or mobj.group('id')) + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) video_id, catalogue = self._html_search_regex( - r'href="http://videos\.francetv\.fr/video/([^@]+@[^"]+)"', + r'href="http://videos?\.francetv\.fr/video/([^@]+@[^"]+)"', webpage, 'video ID').split('@') return self._extract_video(video_id, catalogue) |