X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/7ceb2ec430c3363e0140a0519402428f36dc472e..c91254967656b8722087896c531ed6d815cbe670:/youtube_dl/extractor/francetv.py diff --git a/youtube_dl/extractor/francetv.py b/youtube_dl/extractor/francetv.py index b1530e5..6e19710 100644 --- a/youtube_dl/extractor/francetv.py +++ b/youtube_dl/extractor/francetv.py @@ -1,6 +1,5 @@ # encoding: utf-8 import re -import xml.etree.ElementTree import json from .common import InfoExtractor @@ -11,11 +10,10 @@ 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') @@ -70,7 +68,11 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor): class France2IE(FranceTVBaseInfoExtractor): IE_NAME = u'france2.fr' - _VALID_URL = r'https?://www\.france2\.fr/emissions/.*?/videos/(?P\d+)' + _VALID_URL = r'''(?x)https?://www\.france2\.fr/ + (?: + emissions/.*?/videos/(?P\d+) + | emission/(?P[^/?]+) + )''' _TEST = { u'url': u'http://www.france2.fr/emissions/13h15-le-samedi-le-dimanche/videos/75540104', @@ -86,12 +88,20 @@ class France2IE(FranceTVBaseInfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + if mobj.group('key'): + webpage = self._download_webpage(url, mobj.group('key')) + video_id = self._html_search_regex( + r'''(?x)\s* + ''', + webpage, u'video ID') + else: + video_id = mobj.group('id') return self._extract_video(video_id) class GenerationQuoiIE(InfoExtractor): - IE_NAME = u'http://generation-quoi.france2.fr' + IE_NAME = u'france2.fr:generation-quoi' _VALID_URL = r'https?://generation-quoi\.france2\.fr/portrait/(?P.*)(\?|$)' _TEST = {