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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import ExtractorError
   8
   9
  10 class TriluliluIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.)?trilulilu\.ro/(?:video-[^/]+/)?(?P<id>[^/#\?]+)'
  12     _TEST = {
  13         'url': 'http://www.trilulilu.ro/video-animatie/big-buck-bunny-1',
  14         'md5': 'c1450a00da251e2769b74b9005601cac',
  15         'info_dict': {
  16             'id': 'ae2899e124140b',
  17             'ext': 'mp4',
  18             'title': 'Big Buck Bunny',
  19             'description': ':) pentru copilul din noi',
  20         },
  21     }
  22
  23     def _real_extract(self, url):
  24         display_id = self._match_id(url)
  25         webpage = self._download_webpage(url, display_id)
  26
  27         if re.search(r'Fişierul nu este disponibil pentru vizionare în ţara dumneavoastră', webpage):
  28             raise ExtractorError(
  29                 'This video is not available in your country.', expected=True)
  30         elif re.search('Fişierul poate fi accesat doar de către prietenii lui', webpage):
  31             raise ExtractorError('This video is private.', expected=True)
  32
  33         flashvars_str = self._search_regex(
  34             r'block_flash_vars\s*=\s*(\{[^\}]+\})', webpage, 'flashvars', fatal=False, default=None)
  35
  36         if flashvars_str:
  37             flashvars = self._parse_json(flashvars_str, display_id)
  38         else:
  39             raise ExtractorError(
  40                 'This page does not contain videos', expected=True)
  41
  42         if flashvars['isMP3'] == 'true':
  43             raise ExtractorError(
  44                 'Audio downloads are currently not supported', expected=True)
  45
  46         video_id = flashvars['hash']
  47         title = self._og_search_title(webpage)
  48         thumbnail = self._og_search_thumbnail(webpage)
  49         description = self._og_search_description(webpage, default=None)
  50
  51         format_url = ('http://fs%(server)s.trilulilu.ro/%(hash)s/'
  52                       'video-formats2' % flashvars)
  53         format_doc = self._download_xml(
  54             format_url, video_id,
  55             note='Downloading formats',
  56             errnote='Error while downloading formats')
  57
  58         video_url_template = (
  59             'http://fs%(server)s.trilulilu.ro/stream.php?type=video'
  60             '&source=site&hash=%(hash)s&username=%(userid)s&'
  61             'key=ministhebest&format=%%s&sig=&exp=' %
  62             flashvars)
  63         formats = [
  64             {
  65                 'format_id': fnode.text.partition('-')[2],
  66                 'url': video_url_template % fnode.text,
  67                 'ext': fnode.text.partition('-')[0]
  68             }
  69
  70             for fnode in format_doc.findall('./formats/format')
  71         ]
  72
  73         return {
  74             'id': video_id,
  75             'display_id': display_id,
  76             'formats': formats,
  77             'title': title,
  78             'description': description,
  79             'thumbnail': thumbnail,
  80         }