Browse Source

Add an extractor for rutube.ru (closes #1136)

It downloads with a m3u8 manifest, requires ffmpeg.
rtmp_test
Jaime Marquínez Ferrándiz 11 years ago
parent
commit
bfd14b1b2f
2 changed files with 59 additions and 0 deletions
  1. +1
    -0
      youtube_dl/extractor/__init__.py
  2. +58
    -0
      youtube_dl/extractor/rutube.py

+ 1
- 0
youtube_dl/extractor/__init__.py View File

@ -102,6 +102,7 @@ from .ro220 import Ro220IE
from .rottentomatoes import RottenTomatoesIE
from .roxwel import RoxwelIE
from .rtlnow import RTLnowIE
from .rutube import RutubeIE
from .sina import SinaIE
from .slashdot import SlashdotIE
from .slideshare import SlideshareIE


+ 58
- 0
youtube_dl/extractor/rutube.py View File

@ -0,0 +1,58 @@
# encoding: utf-8
import re
import json
from .common import InfoExtractor
from ..utils import (
compat_urlparse,
compat_str,
ExtractorError,
)
class RutubeIE(InfoExtractor):
_VALID_URL = r'https?://rutube.ru/video/(?P<long_id>\w+)'
_TEST = {
u'url': u'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',
u'file': u'3eac3b4561676c17df9132a9a1e62e3e.mp4',
u'info_dict': {
u'title': u'Раненный кенгуру забежал в аптеку',
u'uploader': u'NTDRussian',
u'uploader_id': u'29790',
},
u'params': {
# It requires ffmpeg (m3u8 download)
u'skip_download': True,
},
}
def _get_api_response(self, short_id, subpath):
api_url = 'http://rutube.ru/api/play/%s/%s/?format=json' % (subpath, short_id)
response_json = self._download_webpage(api_url, short_id,
u'Downloading %s json' % subpath)
return json.loads(response_json)
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
long_id = mobj.group('long_id')
webpage = self._download_webpage(url, long_id)
og_video = self._og_search_video_url(webpage)
short_id = compat_urlparse.urlparse(og_video).path[1:]
options = self._get_api_response(short_id, 'options')
trackinfo = self._get_api_response(short_id, 'trackinfo')
# Some videos don't have the author field
author = trackinfo.get('author') or {}
m3u8_url = trackinfo['video_balancer'].get('m3u8')
if m3u8_url is None:
raise ExtractorError(u'Couldn\'t find m3u8 manifest url')
return {
'id': trackinfo['id'],
'title': trackinfo['title'],
'url': m3u8_url,
'ext': 'mp4',
'thumbnail': options['thumbnail_url'],
'uploader': author.get('name'),
'uploader_id': compat_str(author['id']) if author else None,
}

Loading…
Cancel
Save