Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/trilulilu.py

   1 from __future__ import unicode_literals
   2
   3 import json
   4
   5 from .common import InfoExtractor
   6
   7
   8 class TriluliluIE(InfoExtractor):
   9     _VALID_URL = r'https?://(?:www\.)?trilulilu\.ro/video-[^/]+/(?P<id>[^/]+)'
  10     _TEST = {
  11         'url': 'http://www.trilulilu.ro/video-animatie/big-buck-bunny-1',
  12         'info_dict': {
  13             'id': 'big-buck-bunny-1',
  14             'ext': 'mp4',
  15             'title': 'Big Buck Bunny',
  16             'description': ':) pentru copilul din noi',
  17         },
  18         # Server ignores Range headers (--test)
  19         'params': {
  20             'skip_download': True
  21         }
  22     }
  23
  24     def _real_extract(self, url):
  25         video_id = self._match_id(url)
  26         webpage = self._download_webpage(url, video_id)
  27
  28         title = self._og_search_title(webpage)
  29         thumbnail = self._og_search_thumbnail(webpage)
  30         description = self._og_search_description(webpage)
  31
  32         log_str = self._search_regex(
  33             r'block_flash_vars[ ]=[ ]({[^}]+})', webpage, 'log info')
  34         log = json.loads(log_str)
  35
  36         format_url = ('http://fs%(server)s.trilulilu.ro/%(hash)s/'
  37                       'video-formats2' % log)
  38         format_doc = self._download_xml(
  39             format_url, video_id,
  40             note='Downloading formats',
  41             errnote='Error while downloading formats')
  42
  43         video_url_template = (
  44             'http://fs%(server)s.trilulilu.ro/stream.php?type=video'
  45             '&source=site&hash=%(hash)s&username=%(userid)s&'
  46             'key=ministhebest&format=%%s&sig=&exp=' %
  47             log)
  48         formats = [
  49             {
  50                 'format': fnode.text,
  51                 'url': video_url_template % fnode.text,
  52                 'ext': fnode.text.partition('-')[0]
  53             }
  54
  55             for fnode in format_doc.findall('./formats/format')
  56         ]
  57
  58         return {
  59             '_type': 'video',
  60             'id': video_id,
  61             'formats': formats,
  62             'title': title,
  63             'description': description,
  64             'thumbnail': thumbnail,
  65         }