X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/1270059fa7cf720bc0533c2cdfe6370923ae4e20..b0b67c374528aca7bc76a9476d554a1d3ab96a9e:/youtube_dl/extractor/vimeo.py diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index 0825714..3baa2d0 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -16,6 +16,7 @@ from ..utils import ( ExtractorError, InAdvancePagedList, int_or_none, + merge_dicts, NO_DEFAULT, RegexNotFoundError, sanitized_Request, @@ -36,7 +37,7 @@ class VimeoBaseInfoExtractor(InfoExtractor): _LOGIN_URL = 'https://vimeo.com/log_in' def _login(self): - (username, password) = self._get_login_info() + username, password = self._get_login_info() if username is None: if self._LOGIN_REQUIRED: raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True) @@ -639,16 +640,18 @@ class VimeoIE(VimeoBaseInfoExtractor): 'preference': 1, }) - info_dict = self._parse_config(config, video_id) - formats.extend(info_dict['formats']) + info_dict_config = self._parse_config(config, video_id) + formats.extend(info_dict_config['formats']) self._vimeo_sort_formats(formats) + json_ld = self._search_json_ld(webpage, video_id, default={}) + if not cc_license: cc_license = self._search_regex( r']+rel=["\']license["\'][^>]+href=(["\'])(?P(?:(?!\1).)+)\1', webpage, 'license', default=None, group='license') - info_dict.update({ + info_dict = { 'id': video_id, 'formats': formats, 'timestamp': unified_timestamp(timestamp), @@ -658,7 +661,9 @@ class VimeoIE(VimeoBaseInfoExtractor): 'like_count': like_count, 'comment_count': comment_count, 'license': cc_license, - }) + } + + info_dict = merge_dicts(info_dict, info_dict_config, json_ld) return info_dict @@ -984,10 +989,10 @@ class VimeoWatchLaterIE(VimeoChannelIE): class VimeoLikesIE(InfoExtractor): - _VALID_URL = r'https://(?:www\.)?vimeo\.com/user(?P[0-9]+)/likes/?(?:$|[?#]|sort:)' + _VALID_URL = r'https://(?:www\.)?vimeo\.com/(?P[^/]+)/likes/?(?:$|[?#]|sort:)' IE_NAME = 'vimeo:likes' IE_DESC = 'Vimeo user likes' - _TEST = { + _TESTS = [{ 'url': 'https://vimeo.com/user755559/likes/', 'playlist_mincount': 293, 'info_dict': { @@ -995,7 +1000,10 @@ class VimeoLikesIE(InfoExtractor): 'description': 'See all the videos urza likes', 'title': 'Videos urza likes', }, - } + }, { + 'url': 'https://vimeo.com/stormlapse/likes', + 'only_matching': True, + }] def _real_extract(self, url): user_id = self._match_id(url) @@ -1004,7 +1012,7 @@ class VimeoLikesIE(InfoExtractor): self._search_regex( r'''(?x)
  • .*?
  • \s* - ''', webpage, 'page count'), + ''', webpage, 'page count', default=1), 'page count', fatal=True) PAGE_SIZE = 12 title = self._html_search_regex( @@ -1012,7 +1020,7 @@ class VimeoLikesIE(InfoExtractor): description = self._html_search_meta('description', webpage) def _get_page(idx): - page_url = 'https://vimeo.com/user%s/likes/page:%d/sort:date' % ( + page_url = 'https://vimeo.com/%s/likes/page:%d/sort:date' % ( user_id, idx + 1) webpage = self._download_webpage( page_url, user_id, @@ -1032,7 +1040,7 @@ class VimeoLikesIE(InfoExtractor): return { '_type': 'playlist', - 'id': 'user%s_likes' % user_id, + 'id': '%s_likes' % user_id, 'title': title, 'description': description, 'entries': pl,