From 25475dfab356e625ee480e1631601b86403afb5a Mon Sep 17 00:00:00 2001 From: Hongjie Dong Date: Mon, 4 Dec 2017 00:26:09 -0800 Subject: [PATCH] [mailru] Add support for embed URLs --- youtube_dl/extractor/mailru.py | 36 +++++++++++++++++++++------------- 1 file changed, 22 insertions(+), 14 deletions(-) diff --git a/youtube_dl/extractor/mailru.py b/youtube_dl/extractor/mailru.py index f7cc3c8328..f1865fd115 100644 --- a/youtube_dl/extractor/mailru.py +++ b/youtube_dl/extractor/mailru.py @@ -13,8 +13,7 @@ class MailRuIE(InfoExtractor): IE_NAME = 'mailru' IE_DESC = 'Видео@Mail.Ru' - _VALID_URL = r'https?://(?:(?:www|m)\.)?my\.mail\.ru/(?:video/.*#video=/?(?P(?:[^/]+/){3}\d+)|(?:(?P(?:[^/]+/){2})video/(?P[^/]+/\d+))\.html)' - + _VALID_URL = r'https?://(?:(?:www|m)\.)?my\.mail\.ru/(?:video/.*#video=/?(?P(?:[^/]+/){3}\d+)|(?:(?P(?:[^/]+/){2})video/(?P[^/]+/\d+))\.html|video/embed/(?P\d+))' _TESTS = [ { 'url': 'http://my.mail.ru/video/top#video=/mail/sonypicturesrus/75/76', @@ -65,25 +64,34 @@ class MailRuIE(InfoExtractor): { 'url': 'http://m.my.mail.ru/mail/3sktvtr/video/_myvideo/138.html', 'only_matching': True, + }, + { + 'url': 'https://my.mail.ru/video/embed/7949340477499637815', + 'only_matching': True, } ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('idv1') - - if not video_id: - video_id = mobj.group('idv2prefix') + mobj.group('idv2suffix') - - webpage = self._download_webpage(url, video_id) - + meta_id = mobj.group('meta_id') + page_config = None video_data = None + video_id = None + if not meta_id: + video_id = mobj.group('idv1') + if not video_id: + video_id = mobj.group('idv2prefix') + mobj.group('idv2suffix') - page_config = self._parse_json(self._search_regex( - r'(?s)]+class="sp-video__page-config"[^>]*>(.+?)', - webpage, 'page config', default='{}'), video_id, fatal=False) - if page_config: - meta_url = page_config.get('metaUrl') or page_config.get('video', {}).get('metaUrl') + webpage = self._download_webpage(url, video_id) + + page_config = self._parse_json(self._search_regex( + r'(?s)]+class="sp-video__page-config"[^>]*>(.+?)', + webpage, 'page config', default='{}'), video_id, fatal=False) + if page_config or meta_id: + if page_config: + meta_url = page_config.get('metaUrl') or page_config.get('video', {}).get('metaUrl') + elif meta_id: + meta_url = 'https://my.mail.ru/+/video/meta/' + meta_id if meta_url: video_data = self._download_json( meta_url, video_id, 'Downloading video meta JSON', fatal=False)