X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Ffrancetv.py;h=81b468c7d1e030f7ba67fed2a7ef2562c8164c76;hb=a6211d237b4e7051ca018cc09440502561fedaa7;hp=c02cd03de1c59452ac1ff2432f9e5ea54134e7de;hpb=49702e366923798ba31436b52874555be0063cec;p=youtube-dl diff --git a/youtube_dl/extractor/francetv.py b/youtube_dl/extractor/francetv.py index c02cd03de..81b468c7d 100644 --- a/youtube_dl/extractor/francetv.py +++ b/youtube_dl/extractor/francetv.py @@ -16,6 +16,7 @@ from ..utils import ( int_or_none, parse_duration, try_get, + url_or_none, ) from .dailymotion import DailymotionIE @@ -115,14 +116,13 @@ class FranceTVIE(InfoExtractor): def sign(manifest_url, manifest_id): for host in ('hdfauthftv-a.akamaihd.net', 'hdfauth.francetv.fr'): - signed_url = self._download_webpage( + signed_url = url_or_none(self._download_webpage( 'https://%s/esi/TA' % host, video_id, 'Downloading signed %s manifest URL' % manifest_id, fatal=False, query={ 'url': manifest_url, - }) - if (signed_url and isinstance(signed_url, compat_str) and - re.search(r'^(?:https?:)?//', signed_url)): + })) + if signed_url: return signed_url return manifest_url @@ -143,7 +143,7 @@ class FranceTVIE(InfoExtractor): ext = determine_ext(video_url) if ext == 'f4m': if georestricted: - # See https://github.com/rg3/youtube-dl/issues/3963 + # See https://github.com/ytdl-org/youtube-dl/issues/3963 # m3u8 urls work fine continue formats.extend(self._extract_f4m_formats( @@ -215,7 +215,7 @@ class FranceTVSiteIE(FranceTVBaseInfoExtractor): _TESTS = [{ 'url': 'https://www.france.tv/france-2/13h15-le-dimanche/140921-les-mysteres-de-jesus.html', 'info_dict': { - 'id': '162311093', + 'id': 'ec217ecc-0733-48cf-ac06-af1347b849d1', 'ext': 'mp4', 'title': '13h15, le dimanche... - Les mystères de Jésus', 'description': 'md5:75efe8d4c0a8205e5904498ffe1e1a42', @@ -271,7 +271,7 @@ class FranceTVSiteIE(FranceTVBaseInfoExtractor): catalogue = None video_id = self._search_regex( - r'data-main-video=(["\'])(?P(?:(?!\1).)+)\1', + r'(?:data-main-video\s*=|videoId["\']?\s*[:=])\s*(["\'])(?P(?:(?!\1).)+)\1', webpage, 'video id', default=None, group='id') if not video_id: @@ -371,12 +371,38 @@ class FranceTVInfoIE(FranceTVBaseInfoExtractor): self.url_result(dailymotion_url, DailymotionIE.ie_key()) for dailymotion_url in dailymotion_urls]) - video_id, catalogue = self._search_regex( - (r'id-video=([^@]+@[^"]+)', + video_id = self._search_regex( + (r'player\.load[^;]+src:\s*["\']([^"\']+)', + r'id-video=([^@]+@[^"]+)', r']+href="(?:https?:)?//videos\.francetv\.fr/video/([^@]+@[^"]+)"'), - webpage, 'video id').split('@') + webpage, 'video id') - return self._make_url_result(video_id, catalogue) + return self._make_url_result(video_id) + + +class FranceTVInfoSportIE(FranceTVBaseInfoExtractor): + IE_NAME = 'sport.francetvinfo.fr' + _VALID_URL = r'https?://sport\.francetvinfo\.fr/(?:[^/]+/)*(?P[^/?#&]+)' + _TESTS = [{ + 'url': 'https://sport.francetvinfo.fr/les-jeux-olympiques/retour-sur-les-meilleurs-moments-de-pyeongchang-2018', + 'info_dict': { + 'id': '6e49080e-3f45-11e8-b459-000d3a2439ea', + 'ext': 'mp4', + 'title': 'Retour sur les meilleurs moments de Pyeongchang 2018', + 'timestamp': 1523639962, + 'upload_date': '20180413', + }, + 'params': { + 'skip_download': True, + }, + 'add_ie': [FranceTVIE.ie_key()], + }] + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + video_id = self._search_regex(r'data-video="([^"]+)"', webpage, 'video_id') + return self._make_url_result(video_id, 'Sport-web') class GenerationWhatIE(InfoExtractor):