diff options
Diffstat (limited to 'hypervideo_dl/extractor/mailru.py')
| -rw-r--r-- | hypervideo_dl/extractor/mailru.py | 25 |
1 files changed, 20 insertions, 5 deletions
diff --git a/hypervideo_dl/extractor/mailru.py b/hypervideo_dl/extractor/mailru.py index 65cc474..5d9f80b 100644 --- a/hypervideo_dl/extractor/mailru.py +++ b/hypervideo_dl/extractor/mailru.py @@ -12,6 +12,7 @@ from ..utils import ( parse_duration, remove_end, try_get, + urljoin, ) @@ -20,10 +21,10 @@ class MailRuIE(InfoExtractor): IE_DESC = 'Видео@Mail.Ru' _VALID_URL = r'''(?x) https?:// - (?:(?:www|m)\.)?my\.mail\.ru/+ + (?:(?:www|m|videoapi)\.)?my\.mail\.ru/+ (?: video/.*\#video=/?(?P<idv1>(?:[^/]+/){3}\d+)| - (?:(?P<idv2prefix>(?:[^/]+/+){2})video/(?P<idv2suffix>[^/]+/\d+))\.html| + (?:videos/embed/)?(?:(?P<idv2prefix>(?:[^/]+/+){2})(?:video/(?:embed/)?)?(?P<idv2suffix>[^/]+/\d+))(?:\.html)?| (?:video/embed|\+/video/meta)/(?P<metaid>\d+) ) ''' @@ -93,11 +94,19 @@ class MailRuIE(InfoExtractor): { 'url': 'https://my.mail.ru//list//sinyutin10/video/_myvideo/4.html', 'only_matching': True, + }, + { + 'url': 'https://my.mail.ru/mail/cloud-strife/video/embed/Games/2009', + 'only_matching': True, + }, + { + 'url': 'https://videoapi.my.mail.ru/videos/embed/mail/cloud-strife/Games/2009.html', + 'only_matching': True, } ] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) + mobj = self._match_valid_url(url) meta_id = mobj.group('metaid') video_id = None @@ -108,15 +117,21 @@ class MailRuIE(InfoExtractor): 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( + page_config = self._parse_json(self._search_regex([ r'(?s)<script[^>]+class="sp-video__page-config"[^>]*>(.+?)</script>', + r'(?s)"video":\s*({.+?}),'], webpage, 'page config', default='{}'), video_id, fatal=False) if page_config: - meta_url = page_config.get('metaUrl') or page_config.get('video', {}).get('metaUrl') + meta_url = page_config.get('metaUrl') or page_config.get('video', {}).get('metaUrl') or page_config.get('metadataUrl') else: meta_url = None video_data = None + + # fix meta_url if missing the host address + if re.match(r'^\/\+\/', meta_url): + meta_url = urljoin('https://my.mail.ru', meta_url) + if meta_url: video_data = self._download_json( meta_url, video_id or meta_id, 'Downloading video meta JSON', |