From 9e6060208430cef6af5e1f6ae24feb65c35fc03c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?= Date: Thu, 5 Dec 2013 20:45:53 +0100 Subject: [PATCH 1/2] =?UTF-8?q?[francetv]=20Add=20support=20for=20more=20c?= =?UTF-8?q?hannels:=203,=204,=205=20and=20=C3=94=20(#1898)?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Rename the France2IE extractor to FranceTVIE --- youtube_dl/extractor/__init__.py | 2 +- youtube_dl/extractor/francetv.py | 103 +++++++++++++++++++++++++------ 2 files changed, 85 insertions(+), 20 deletions(-) diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 2e1a8be14..a78dcad7f 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -56,7 +56,7 @@ from .francetv import ( PluzzIE, FranceTvInfoIE, - France2IE, + FranceTVIE, GenerationQuoiIE ) from .freesound import FreesoundIE diff --git a/youtube_dl/extractor/francetv.py b/youtube_dl/extractor/francetv.py index 66aa3aa0d..290e650e0 100644 --- a/youtube_dl/extractor/francetv.py +++ b/youtube_dl/extractor/francetv.py @@ -21,7 +21,7 @@ def _extract_video(self, video_id): 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), @@ -66,35 +66,100 @@ def _real_extract(self, url): return self._extract_video(video_id) -class France2IE(FranceTVBaseInfoExtractor): - IE_NAME = u'france2.fr' - _VALID_URL = r'''(?x)https?://www\.france2\.fr/ +class FranceTVIE(FranceTVBaseInfoExtractor): + IE_NAME = u'francetv' + IE_DESC = u'France 2, 3, 4, 5 and Ô' + _VALID_URL = r'''(?x)https?://www\.france[2345o]\.fr/ (?: - emissions/.*?/videos/(?P\d+) - | emission/(?P[^/?]+) + emissions/.*?/(videos|emissions)/(?P[^/?]+) + | (emission|jt)/(?P[^/?]+) )''' - _TEST = { - u'url': u'http://www.france2.fr/emissions/13h15-le-samedi-le-dimanche/videos/75540104', - u'file': u'75540104.mp4', - u'info_dict': { - u'title': u'13h15, le samedi...', - u'description': u'md5:2e5b58ba7a2d3692b35c792be081a03d', + _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': { + u'title': u'13h15, le samedi...', + u'description': u'md5:2e5b58ba7a2d3692b35c792be081a03d', + }, + u'params': { + # m3u8 download + u'skip_download': True, + }, }, - u'params': { - 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( - r'''(?x)\s* + id_res = [ + (r'''(?x)\s* ''', - webpage, u'video ID') + class="francetv-video-player">'''), + (r' Date: Thu, 5 Dec 2013 21:26:35 +0100 Subject: [PATCH 2/2] [francetv] Add support for urls in the format http://www.france3.fr/emissions/{program}/diffusions/{date} (fixes #1898) --- youtube_dl/extractor/francetv.py | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/youtube_dl/extractor/francetv.py b/youtube_dl/extractor/francetv.py index 290e650e0..ad85bc16d 100644 --- 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[^/?]+) - | (emission|jt)/(?P[^/?]+) + | (emissions?|jt)/(?P[^/?]+) )''' _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 @@ def _real_extract(self, url): class="francetv-video-player">'''), (r'