1
0
Fork 0
mirror of https://gitlab.com/dstftw/youtube-dl.git synced 2020-11-16 09:42:26 +00:00
youtube-dl/youtube_dl/extractor/rutube.py

124 lines
4.1 KiB
Python
Raw Normal View History

# encoding: utf-8
from __future__ import unicode_literals
import re
import itertools
from .common import InfoExtractor
from ..utils import (
compat_str,
2014-01-28 01:19:45 +00:00
unified_strdate,
ExtractorError,
)
class RutubeIE(InfoExtractor):
IE_NAME = 'rutube'
2014-01-28 02:32:07 +00:00
IE_DESC = 'Rutube videos'
2014-01-28 01:47:17 +00:00
_VALID_URL = r'https?://rutube\.ru/video/(?P<id>[\da-z]{32})'
_TEST = {
'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',
'info_dict': {
2014-03-30 08:35:07 +00:00
'id': '3eac3b4561676c17df9132a9a1e62e3e',
'ext': 'mp4',
'title': 'Раненный кенгуру забежал в аптеку',
2014-01-28 02:31:14 +00:00
'description': 'http://www.ntdtv.ru ',
'duration': 80,
'uploader': 'NTDRussian',
'uploader_id': '29790',
2014-01-28 02:31:14 +00:00
'upload_date': '20131016',
},
'params': {
# It requires ffmpeg (m3u8 download)
'skip_download': True,
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
2014-01-28 01:47:17 +00:00
video_id = mobj.group('id')
2014-03-30 09:26:35 +00:00
video = self._download_json(
2014-03-30 08:35:07 +00:00
'http://rutube.ru/api/video/%s/?format=json' % video_id,
video_id, 'Downloading video JSON')
2014-03-30 09:26:35 +00:00
# Some videos don't have the author field
2014-04-19 08:59:12 +00:00
author = video.get('author') or {}
options = self._download_json(
2014-04-21 12:04:11 +00:00
'http://rutube.ru/api/play/options/%s/?format=json' % video_id,
2014-04-19 08:59:12 +00:00
video_id, 'Downloading options JSON')
m3u8_url = options['video_balancer'].get('m3u8')
if m3u8_url is None:
raise ExtractorError('Couldn\'t find m3u8 manifest url')
return {
2014-01-28 01:19:45 +00:00
'id': video['id'],
'title': video['title'],
'description': video['description'],
'duration': video['duration'],
'view_count': video['hits'],
'url': m3u8_url,
'ext': 'mp4',
2014-01-28 01:19:45 +00:00
'thumbnail': video['thumbnail_url'],
'uploader': author.get('name'),
'uploader_id': compat_str(author['id']) if author else None,
2014-01-28 01:19:45 +00:00
'upload_date': unified_strdate(video['created_ts']),
'age_limit': 18 if video['is_adult'] else 0,
}
class RutubeChannelIE(InfoExtractor):
IE_NAME = 'rutube:channel'
2014-01-28 02:32:07 +00:00
IE_DESC = 'Rutube channels'
_VALID_URL = r'http://rutube\.ru/tags/video/(?P<id>\d+)'
_PAGE_TEMPLATE = 'http://rutube.ru/api/tags/video/%s/?page=%s&format=json'
def _extract_videos(self, channel_id, channel_title=None):
entries = []
for pagenum in itertools.count(1):
2014-03-30 09:26:35 +00:00
page = self._download_json(
2014-01-28 02:32:07 +00:00
self._PAGE_TEMPLATE % (channel_id, pagenum),
channel_id, 'Downloading page %s' % pagenum)
results = page['results']
2014-01-28 02:32:07 +00:00
if not results:
break
2014-01-28 01:19:45 +00:00
entries.extend(self.url_result(result['video_url'], 'Rutube') for result in results)
2014-01-28 02:32:07 +00:00
if not page['has_next']:
break
return self.playlist_result(entries, channel_id, channel_title)
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
channel_id = mobj.group('id')
return self._extract_videos(channel_id)
class RutubeMovieIE(RutubeChannelIE):
IE_NAME = 'rutube:movie'
2014-01-28 02:32:07 +00:00
IE_DESC = 'Rutube movies'
_VALID_URL = r'http://rutube\.ru/metainfo/tv/(?P<id>\d+)'
_MOVIE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/?format=json'
_PAGE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
movie_id = mobj.group('id')
2014-03-30 09:26:35 +00:00
movie = self._download_json(
2014-01-28 02:32:07 +00:00
self._MOVIE_TEMPLATE % movie_id, movie_id,
'Downloading movie JSON')
movie_name = movie['name']
2014-01-28 01:47:17 +00:00
return self._extract_videos(movie_id, movie_name)
class RutubePersonIE(RutubeChannelIE):
IE_NAME = 'rutube:person'
IE_DESC = 'Rutube person videos'
_VALID_URL = r'http://rutube\.ru/video/person/(?P<id>\d+)'
2014-01-28 02:32:07 +00:00
_PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'