1
0
Fork 0
mirror of https://github.com/blackjack4494/yt-dlc.git synced 2024-12-22 07:43:08 +00:00

[vk] Add support for rutube embeds (Fixes #4514)

This commit is contained in:
Philipp Hagemeister 2015-01-04 03:15:27 +01:00
parent 2ccd1b10e5
commit 7a1818c99b
3 changed files with 41 additions and 0 deletions

View file

@ -359,6 +359,7 @@ from .ruhd import RUHDIE
from .rutube import (
RutubeIE,
RutubeChannelIE,
RutubeEmbedIE,
RutubeMovieIE,
RutubePersonIE,
)

View file

@ -70,6 +70,37 @@ class RutubeIE(InfoExtractor):
}
class RutubeEmbedIE(InfoExtractor):
IE_NAME = 'rutube:embed'
IE_DESC = 'Rutube embedded videos'
_VALID_URL = 'https?://rutube\.ru/video/embed/(?P<id>[0-9]+)'
_TEST = {
'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=',
'info_dict': {
'id': 'a10e53b86e8f349080f718582ce4c661',
'ext': 'mp4',
'upload_date': '20131223',
'uploader_id': '297833',
'description': 'Видео группы ★http://vk.com/foxkidsreset★ музей Fox Kids и Jetix<br/><br/> восстановлено и сделано в шикоформате subziro89 http://vk.com/subziro89',
'uploader': 'subziro89 ILya',
'title': 'Мистический городок Эйри в Индиан 5 серия озвучка subziro89',
},
'params': {
'skip_download': 'Requires ffmpeg',
},
}
def _real_extract(self, url):
embed_id = self._match_id(url)
webpage = self._download_webpage(url, embed_id)
canonical_url = self._html_search_regex(
r'<link\s+rel="canonical"\s+href="([^"]+?)"', webpage,
'Canonical URL')
return self.url_result(canonical_url, 'Rutube')
class RutubeChannelIE(InfoExtractor):
IE_NAME = 'rutube:channel'
IE_DESC = 'Rutube channels'

View file

@ -164,6 +164,15 @@ class VKIE(InfoExtractor):
self.to_screen('Youtube video detected')
return self.url_result(m_yt.group(1), 'Youtube')
m_rutube = re.search(
r'\ssrc="((?:https?:)?//rutube\.ru\\?/video\\?/embed(?:.*?))\\?"', info_page)
assert m_rutube
if m_rutube is not None:
self.to_screen('rutube video detected')
rutube_url = self._proto_relative_url(
m_rutube.group(1).replace('\\', ''))
return self.url_result(rutube_url)
m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.*?});', info_page)
if m_opts:
m_opts_url = re.search(r"url\s*:\s*'([^']+)", m_opts.group(1))