From c38a67bcd5df639b9d7e7faa8685e76446803527 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 1 Feb 2017 00:49:28 +0700 Subject: [PATCH] [vimeo] Extract license (closes #11880) --- youtube_dl/extractor/vimeo.py | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index 8b6a5cc3c..32179e915 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -218,6 +218,7 @@ class VimeoIE(VimeoBaseInfoExtractor): 'uploader_id': 'user7108434', 'uploader': 'Filippo Valsorda', 'duration': 10, + 'license': 'by-sa', }, }, { @@ -486,6 +487,8 @@ class VimeoIE(VimeoBaseInfoExtractor): '%s said: %s' % (self.IE_NAME, seed_status['title']), expected=True) + cc_license = None + # Extract the config JSON try: try: @@ -499,8 +502,9 @@ class VimeoIE(VimeoBaseInfoExtractor): vimeo_clip_page_config = self._search_regex( r'vimeo\.clip_page_config\s*=\s*({.+?});', webpage, 'vimeo clip page config') - config_url = self._parse_json( - vimeo_clip_page_config, video_id)['player']['config_url'] + page_config = self._parse_json(vimeo_clip_page_config, video_id) + config_url = page_config['player']['config_url'] + cc_license = page_config.get('cc_license') config_json = self._download_webpage(config_url, video_id) config = json.loads(config_json) except RegexNotFoundError: @@ -609,6 +613,12 @@ class VimeoIE(VimeoBaseInfoExtractor): info_dict = self._parse_config(config, video_id) formats.extend(info_dict['formats']) self._vimeo_sort_formats(formats) + + 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({ 'id': video_id, 'formats': formats, @@ -618,6 +628,7 @@ class VimeoIE(VimeoBaseInfoExtractor): 'view_count': view_count, 'like_count': like_count, 'comment_count': comment_count, + 'license': cc_license, }) return info_dict