[generic] Add support for vzaar embeds

This commit is contained in:
tetra-eder 2017-08-11 17:00:39 +02:00 committed by Sergey M
parent 6ed99754bb
commit 41918eaa5c
2 changed files with 25 additions and 0 deletions

View file

@ -98,6 +98,7 @@
from .mediaset import MediasetIE from .mediaset import MediasetIE
from .joj import JojIE from .joj import JojIE
from .megaphone import MegaphoneIE from .megaphone import MegaphoneIE
from .vzaar import VzaarIE
class GenericIE(InfoExtractor): class GenericIE(InfoExtractor):
@ -1840,6 +1841,16 @@ class GenericIE(InfoExtractor):
'title': 'Стас Намин: «Мы нарушили девственность Кремля»', 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
}, },
}, },
{
# vzaar embed
'url': 'http://www.xruniversity.com/bdsm-lets-begin-melissa-moore/',
'md5': 'cddc9fb8a8644a0a7742149eee95080b',
'info_dict': {
'id': '11002506',
'ext': 'mp4',
'title': 'XR-U SHOW: Ready Player Fuck - EP. 61',
},
},
# { # {
# # TODO: find another test # # TODO: find another test
# # http://schema.org/VideoObject # # http://schema.org/VideoObject
@ -2781,6 +2792,12 @@ def _real_extract(self, url):
return self.playlist_from_matches( return self.playlist_from_matches(
videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key()) videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
# Look for vzaar embeds
vzaar_urls = VzaarIE._extract_urls(webpage)
if vzaar_urls:
return self.playlist_from_matches(
vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
# Look for Rutube embeds # Look for Rutube embeds
rutube_urls = RutubeIE._extract_urls(webpage) rutube_urls = RutubeIE._extract_urls(webpage)
if rutube_urls: if rutube_urls:

View file

@ -1,6 +1,8 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
int_or_none, int_or_none,
@ -28,6 +30,12 @@ class VzaarIE(InfoExtractor):
}, },
}] }]
@staticmethod
def _extract_urls(webpage):
return re.findall(
r'<iframe[^>]+src=["\']((?:https?:)?//(?:view\.vzaar\.com)/[0-9]+)',
webpage)
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
video_data = self._download_json( video_data = self._download_json(