From ae1c585cee3eb183cddf7c30a09b75d887307dee Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 28 Apr 2018 02:48:20 +0700 Subject: [PATCH] [vimeo] Extract JSON LD (closes #16295) --- youtube_dl/extractor/vimeo.py | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index 08257147e..a026526b2 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -16,6 +16,7 @@ ExtractorError, InAdvancePagedList, int_or_none, + merge_dicts, NO_DEFAULT, RegexNotFoundError, sanitized_Request, @@ -639,16 +640,18 @@ def is_rented(): '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 @@ def is_rented(): '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