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

   1 from __future__ import unicode_literals
   2
   3 import json
   4
   5 from .common import InfoExtractor
   6 from ..compat import (
   7     compat_urllib_parse,
   8     compat_urllib_parse_unquote,
   9     compat_urlparse,
  10 )
  11 from ..utils import (
  12     get_element_by_attribute,
  13     parse_duration,
  14     strip_jsonp,
  15 )
  16
  17
  18 class MiTeleIE(InfoExtractor):
  19     IE_NAME = 'mitele.es'
  20     _VALID_URL = r'http://www\.mitele\.es/[^/]+/[^/]+/[^/]+/(?P<id>[^/]+)/'
  21
  22     _TESTS = [{
  23         'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/',
  24         'info_dict': {
  25             'id': '0fce117d',
  26             'ext': 'mp4',
  27             'title': 'Programa 144 - Tor, la web invisible',
  28             'description': 'md5:3b6fce7eaa41b2d97358726378d9369f',
  29             'display_id': 'programa-144',
  30             'duration': 2913,
  31         },
  32         'params': {
  33             # m3u8 download
  34             'skip_download': True,
  35         },
  36     }]
  37
  38     def _real_extract(self, url):
  39         episode = self._match_id(url)
  40         webpage = self._download_webpage(url, episode)
  41         embed_data_json = self._search_regex(
  42             r'(?s)MSV\.embedData\[.*?\]\s*=\s*({.*?});', webpage, 'embed data',
  43         ).replace('\'', '"')
  44         embed_data = json.loads(embed_data_json)
  45
  46         domain = embed_data['mediaUrl']
  47         if not domain.startswith('http'):
  48             # only happens in telecinco.es videos
  49             domain = 'http://' + domain
  50         info_url = compat_urlparse.urljoin(
  51             domain,
  52             compat_urllib_parse_unquote(embed_data['flashvars']['host'])
  53         )
  54         info_el = self._download_xml(info_url, episode).find('./video/info')
  55
  56         video_link = info_el.find('videoUrl/link').text
  57         token_query = compat_urllib_parse.urlencode({'id': video_link})
  58         token_info = self._download_json(
  59             embed_data['flashvars']['ov_tk'] + '?' + token_query,
  60             episode,
  61             transform_source=strip_jsonp
  62         )
  63         formats = self._extract_m3u8_formats(
  64             token_info['tokenizedUrl'], episode, ext='mp4')
  65
  66         return {
  67             'id': embed_data['videoId'],
  68             'display_id': episode,
  69             'title': info_el.find('title').text,
  70             'formats': formats,
  71             'description': get_element_by_attribute('class', 'text', webpage),
  72             'thumbnail': info_el.find('thumb').text,
  73             'duration': parse_duration(info_el.find('duration').text),
  74         }