X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Farte.py;h=ffc321821cd3a4a0ba9a62ad97b6f443d8ecacb3;hb=77d95677b7ab4a9840ef142b14627b07a9a31120;hp=69a23e88c5b08738a3ce66cce47215fe58e4fcc0;hpb=fb27d0ce5e91216296e3406d461fe5b7af78c477;p=youtube-dl diff --git a/youtube_dl/extractor/arte.py b/youtube_dl/extractor/arte.py index 69a23e88c..ffc321821 100644 --- a/youtube_dl/extractor/arte.py +++ b/youtube_dl/extractor/arte.py @@ -6,15 +6,18 @@ import re from .common import InfoExtractor from ..compat import ( compat_parse_qs, + compat_str, compat_urllib_parse_urlparse, ) from ..utils import ( + ExtractorError, find_xpath_attr, - unified_strdate, get_element_by_attribute, int_or_none, NO_DEFAULT, qualities, + try_get, + unified_strdate, ) # There are different sources of video in arte.tv, the extraction process @@ -79,6 +82,16 @@ class ArteTVBaseIE(InfoExtractor): info = self._download_json(json_url, video_id) player_info = info['videoJsonPlayer'] + vsr = try_get(player_info, lambda x: x['VSR'], dict) + if not vsr: + error = None + if try_get(player_info, lambda x: x['custom_msg']['type']) == 'error': + error = try_get( + player_info, lambda x: x['custom_msg']['msg'], compat_str) + if not error: + error = 'Video %s is not available' % player_info.get('VID') or video_id + raise ExtractorError(error, expected=True) + upload_date_str = player_info.get('shootingDate') if not upload_date_str: upload_date_str = (player_info.get('VRA') or player_info.get('VDA') or '').split(' ')[0] @@ -107,7 +120,7 @@ class ArteTVBaseIE(InfoExtractor): langcode = LANGS.get(lang, lang) formats = [] - for format_id, format_dict in player_info['VSR'].items(): + for format_id, format_dict in vsr.items(): f = dict(format_dict) versionCode = f.get('versionCode') l = re.escape(langcode) @@ -180,7 +193,7 @@ class ArteTVBaseIE(InfoExtractor): class ArteTVPlus7IE(ArteTVBaseIE): IE_NAME = 'arte.tv:+7' - _VALID_URL = r'https?://(?:(?:www|sites)\.)?arte\.tv/[^/]+/(?Pfr|de|en|es)/(?:[^/]+/)*(?P[^/?#&]+)' + _VALID_URL = r'https?://(?:(?:www|sites)\.)?arte\.tv/(?:[^/]+/)?(?Pfr|de|en|es)/(?:videos/)?(?:[^/]+/)*(?P[^/?#&]+)' _TESTS = [{ 'url': 'http://www.arte.tv/guide/de/sendungen/XEN/xenius/?vid=055918-015_PLUS7-D', @@ -188,6 +201,9 @@ class ArteTVPlus7IE(ArteTVBaseIE): }, { 'url': 'http://sites.arte.tv/karambolage/de/video/karambolage-22', 'only_matching': True, + }, { + 'url': 'http://www.arte.tv/de/videos/048696-000-A/der-kluge-bauch-unser-zweites-gehirn', + 'only_matching': True, }] @classmethod