aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
authorHongjie Dong <hongjieuf@gmail.com>2017-12-04 00:26:09 -0800
committerSergey M․ <dstftw@gmail.com>2017-12-17 18:37:03 +0700
commit25475dfab356e625ee480e1631601b86403afb5a (patch)
treef13e74510c53350f1b19dfb4316432726583f730 /youtube_dl/extractor
parent3dfa9ec21362f8781d0a2d2eef1c9474b525af79 (diff)
[mailru] Add support for embed URLs
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/mailru.py38
1 files changed, 23 insertions, 15 deletions
diff --git a/youtube_dl/extractor/mailru.py b/youtube_dl/extractor/mailru.py
index f7cc3c832..f1865fd11 100644
--- a/youtube_dl/extractor/mailru.py
+++ b/youtube_dl/extractor/mailru.py
@@ -13,8 +13,7 @@ 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<idv1>(?:[^/]+/){3}\d+)|(?:(?P<idv2prefix>(?:[^/]+/){2})video/(?P<idv2suffix>[^/]+/\d+))\.html)'
-
+ _VALID_URL = r'https?://(?:(?:www|m)\.)?my\.mail\.ru/(?:video/.*#video=/?(?P<idv1>(?:[^/]+/){3}\d+)|(?:(?P<idv2prefix>(?:[^/]+/){2})video/(?P<idv2suffix>[^/]+/\d+))\.html|video/embed/(?P<meta_id>\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
-
- page_config = self._parse_json(self._search_regex(
- r'(?s)<script[^>]+class="sp-video__page-config"[^>]*>(.+?)</script>',
- webpage, 'page config', default='{}'), video_id, fatal=False)
- if page_config:
- meta_url = page_config.get('metaUrl') or page_config.get('video', {}).get('metaUrl')
+ video_id = None
+ if not meta_id:
+ 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)<script[^>]+class="sp-video__page-config"[^>]*>(.+?)</script>',
+ 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)