From 549bb416f5a9d15c03749a98abd582d0e40418ac Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 17 Dec 2017 18:36:19 +0700 Subject: [mailru] Fix issues and improve (closes #14904) --- youtube_dl/extractor/mailru.py | 43 +++++++++++++++++++++++++++--------------- 1 file changed, 28 insertions(+), 15 deletions(-) diff --git a/youtube_dl/extractor/mailru.py b/youtube_dl/extractor/mailru.py index f1865fd..6b7c5e3 100644 --- a/youtube_dl/extractor/mailru.py +++ b/youtube_dl/extractor/mailru.py @@ -13,7 +13,15 @@ from ..utils import ( 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|video/embed/(?P\d+))' + _VALID_URL = r'''(?x) + https?:// + (?:(?:www|m)\.)?my\.mail\.ru/ + (?: + video/.*\#video=/?(?P(?:[^/]+/){3}\d+)| + (?:(?P(?:[^/]+/){2})video/(?P[^/]+/\d+))\.html| + (?:video/embed|\+/video/meta)/(?P\d+) + ) + ''' _TESTS = [ { 'url': 'http://my.mail.ru/video/top#video=/mail/sonypicturesrus/75/76', @@ -22,7 +30,7 @@ class MailRuIE(InfoExtractor): 'id': '46301138_76', 'ext': 'mp4', 'title': 'Новый Человек-Паук. Высокое напряжение. Восстание Электро', - 'timestamp': 1393232740, + 'timestamp': 1393235077, 'upload_date': '20140224', 'uploader': 'sonypicturesrus', 'uploader_id': 'sonypicturesrus@mail.ru', @@ -39,7 +47,7 @@ class MailRuIE(InfoExtractor): 'title': 'Samsung Galaxy S5 Hammer Smash Fail Battery Explosion', 'timestamp': 1397039888, 'upload_date': '20140409', - 'uploader': 'hitech@corp.mail.ru', + 'uploader': 'hitech', 'uploader_id': 'hitech@corp.mail.ru', 'duration': 245, }, @@ -68,33 +76,38 @@ class MailRuIE(InfoExtractor): { 'url': 'https://my.mail.ru/video/embed/7949340477499637815', 'only_matching': True, + }, + { + 'url': 'http://my.mail.ru/+/video/meta/7949340477499637815', + 'only_matching': True, } ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - meta_id = mobj.group('meta_id') - page_config = None - video_data = None + meta_id = mobj.group('metaid') + video_id = None - if not meta_id: + if meta_id: + meta_url = 'https://my.mail.ru/+/video/meta/%s' % meta_id + else: video_id = mobj.group('idv1') if not video_id: video_id = mobj.group('idv2prefix') + mobj.group('idv2suffix') - 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) + else: + meta_url = None + + video_data = None + if meta_url: + video_data = self._download_json( + meta_url, video_id or meta_id, 'Downloading video meta JSON', + fatal=not video_id) # Fallback old approach if not video_data: -- cgit v1.1