X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/54477c858fa2504360964e675faf953d78ac57e6..47e9e27ec79dc958bb8597e7ce5f4af2517fabac:/youtube_dl/extractor/francetv.py diff --git a/youtube_dl/extractor/francetv.py b/youtube_dl/extractor/francetv.py index 086cafc..f3e0f38 100644 --- a/youtube_dl/extractor/francetv.py +++ b/youtube_dl/extractor/francetv.py @@ -1,6 +1,8 @@ # encoding: utf-8 + +from __future__ import unicode_literals + import re -import xml.etree.ElementTree import json from .common import InfoExtractor @@ -11,11 +13,10 @@ from ..utils import ( class FranceTVBaseInfoExtractor(InfoExtractor): def _extract_video(self, video_id): - xml_desc = self._download_webpage( + info = self._download_xml( 'http://www.francetvinfo.fr/appftv/webservices/video/' 'getInfosOeuvre.php?id-diffusion=' + video_id, video_id, 'Downloading XML config') - info = xml.etree.ElementTree.fromstring(xml_desc.encode('utf-8')) manifest_url = info.find('videos/video/url').text video_url = manifest_url.replace('manifest.f4m', 'index_2_av.m3u8') @@ -23,7 +24,7 @@ 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), @@ -32,7 +33,7 @@ class FranceTVBaseInfoExtractor(InfoExtractor): class PluzzIE(FranceTVBaseInfoExtractor): - IE_NAME = u'pluzz.francetv.fr' + IE_NAME = 'pluzz.francetv.fr' _VALID_URL = r'https?://pluzz\.francetv\.fr/videos/(.*?)\.html' # Can't use tests, videos expire in 7 days @@ -46,77 +47,156 @@ class PluzzIE(FranceTVBaseInfoExtractor): class FranceTvInfoIE(FranceTVBaseInfoExtractor): - IE_NAME = u'francetvinfo.fr' - _VALID_URL = r'https?://www\.francetvinfo\.fr/replay.*/(?P.+).html' - - _TEST = { - u'url': u'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html', - u'file': u'84981923.mp4', - u'info_dict': { - u'title': u'Soir 3', + IE_NAME = 'francetvinfo.fr' + _VALID_URL = r'https?://www\.francetvinfo\.fr/.*/(?P<title>.+)\.html' + + _TESTS = [{ + 'url': 'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html', + 'info_dict': { + 'id': '84981923', + 'ext': 'mp4', + 'title': 'Soir 3', }, - u'params': { - u'skip_download': True, + 'params': { + 'skip_download': True, }, - } + }, { + 'url': 'http://www.francetvinfo.fr/elections/europeennes/direct-europeennes-regardez-le-debat-entre-les-candidats-a-la-presidence-de-la-commission_600639.html', + 'info_dict': { + 'id': 'EV_20019', + 'ext': 'mp4', + 'title': 'Débat des candidats à la Commission européenne', + 'description': 'Débat des candidats à la Commission européenne', + }, + 'params': { + 'skip_download': 'HLS (reqires ffmpeg)' + } + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) page_title = mobj.group('title') webpage = self._download_webpage(url, page_title) - video_id = self._search_regex(r'id-video=(\d+?)"', webpage, u'video id') + video_id = self._search_regex(r'id-video=((?:[^0-9]*?_)?[0-9]+)[@"]', webpage, 'video id') 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 = 'francetv' + IE_DESC = 'France 2, 3, 4, 5 and Ô' + _VALID_URL = r'''(?x)https?://www\.france[2345o]\.fr/ (?: - emissions/.*?/videos/(?P<id>\d+) - | emission/(?P<key>[^/?]+) + emissions/.*?/(videos|emissions)/(?P<id>[^/?]+) + | (emissions?|jt)/(?P<key>[^/?]+) )''' - _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 + { + 'url': 'http://www.france2.fr/emissions/13h15-le-samedi-le-dimanche/videos/75540104', + 'file': '75540104.mp4', + 'info_dict': { + 'title': '13h15, le samedi...', + 'description': 'md5:2e5b58ba7a2d3692b35c792be081a03d', + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, }, - u'params': { - u'skip_download': True, + # france3 + { + 'url': 'http://www.france3.fr/emissions/pieces-a-conviction/diffusions/13-11-2013_145575', + 'info_dict': { + 'id': '000702326_CAPP_PicesconvictionExtrait313022013_120220131722_Au', + 'ext': 'flv', + 'title': 'Le scandale du prix des médicaments', + 'description': 'md5:1384089fbee2f04fc6c9de025ee2e9ce', + }, + 'params': { + # rtmp download + 'skip_download': True, + }, }, - } + # france4 + { + 'url': 'http://www.france4.fr/emissions/hero-corp/videos/rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4', + 'info_dict': { + 'id': 'rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4', + 'ext': 'flv', + 'title': 'Hero Corp Making of - Extrait 1', + 'description': 'md5:c87d54871b1790679aec1197e73d650a', + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, + # france5 + { + 'url': 'http://www.france5.fr/emissions/c-a-dire/videos/92837968', + 'info_dict': { + 'id': '92837968', + 'ext': 'mp4', + 'title': 'C à dire ?!', + 'description': 'md5:fb1db1cbad784dcce7c7a7bd177c8e2f', + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }, + # franceo + { + 'url': 'http://www.franceo.fr/jt/info-afrique/04-12-2013', + 'info_dict': { + 'id': '92327925', + 'ext': 'mp4', + 'title': 'Infô-Afrique', + 'description': 'md5:ebf346da789428841bee0fd2a935ea55', + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + 'skip': '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)<div\s+class="video-player">\s* + id_res = [ + (r'''(?x)<div\s+class="video-player">\s* <a\s+href="http://videos.francetv.fr/video/([0-9]+)"\s+ - class="francetv-video-player">''', - webpage, u'video ID') + 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, 'video ID') else: video_id = mobj.group('id') return self._extract_video(video_id) class GenerationQuoiIE(InfoExtractor): - IE_NAME = u'france2.fr:generation-quoi' + IE_NAME = 'france2.fr:generation-quoi' _VALID_URL = r'https?://generation-quoi\.france2\.fr/portrait/(?P<name>.*)(\?|$)' _TEST = { - u'url': u'http://generation-quoi.france2.fr/portrait/garde-a-vous', - u'file': u'k7FJX8VBcvvLmX4wA5Q.mp4', - u'info_dict': { - u'title': u'Génération Quoi - Garde à Vous', - u'uploader': u'Génération Quoi', + 'url': 'http://generation-quoi.france2.fr/portrait/garde-a-vous', + 'file': 'k7FJX8VBcvvLmX4wA5Q.mp4', + 'info_dict': { + 'title': 'Génération Quoi - Garde à Vous', + 'uploader': 'Génération Quoi', }, - u'params': { + 'params': { # It uses Dailymotion - u'skip_download': True, + 'skip_download': True, }, + 'skip': 'Only available from France', } def _real_extract(self, url): @@ -127,3 +207,29 @@ class GenerationQuoiIE(InfoExtractor): info = json.loads(info_json) return self.url_result('http://www.dailymotion.com/video/%s' % info['id'], ie='Dailymotion') + + +class CultureboxIE(FranceTVBaseInfoExtractor): + IE_NAME = 'culturebox.francetvinfo.fr' + _VALID_URL = r'https?://culturebox\.francetvinfo\.fr/(?P<name>.*?)(\?|$)' + + _TEST = { + 'url': 'http://culturebox.francetvinfo.fr/einstein-on-the-beach-au-theatre-du-chatelet-146813', + 'info_dict': { + 'id': 'EV_6785', + 'ext': 'mp4', + 'title': 'Einstein on the beach au Théâtre du Châtelet', + 'description': 'md5:9ce2888b1efefc617b5e58b3f6200eeb', + }, + 'params': { + # m3u8 download + '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, 'video id') + return self._extract_video(video_id)