youtube_dl/extractor/mitele.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4 import json
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     compat_urllib_parse,
   9     get_element_by_attribute,
  10     parse_duration,
  11     strip_jsonp,
  12 )
  13
  14
  15 class MiTeleIE(InfoExtractor):
  16     IE_NAME = 'mitele.es'
  17     _VALID_URL = r'http://www\.mitele\.es/[^/]+/[^/]+/[^/]+/(?P<episode>[^/]+)/'
  18
  19     _TEST = {
  20         'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/',
  21         'md5': '6a75fe9d0d3275bead0cb683c616fddb',
  22         'info_dict': {
  23             'id': '0fce117d',
  24             'ext': 'mp4',
  25             'title': 'Programa 144 - Tor, la web invisible',
  26             'description': 'md5:3b6fce7eaa41b2d97358726378d9369f',
  27             'display_id': 'programa-144',
  28             'duration': 2913,
  29         },
  30     }
  31
  32     def _real_extract(self, url):
  33         mobj = re.match(self._VALID_URL, url)
  34         episode = mobj.group('episode')
  35         webpage = self._download_webpage(url, episode)
  36         embed_data_json = self._search_regex(
  37             r'MSV\.embedData\[.*?\]\s*=\s*({.*?});', webpage, 'embed data',
  38             flags=re.DOTALL
  39         ).replace('\'', '"')
  40         embed_data = json.loads(embed_data_json)
  41
  42         info_url = embed_data['flashvars']['host']
  43         info_el = self._download_xml(info_url, episode).find('./video/info')
  44
  45         video_link = info_el.find('videoUrl/link').text
  46         token_query = compat_urllib_parse.urlencode({'id': video_link})
  47         token_info = self._download_json(
  48             'http://token.mitele.es/?' + token_query, episode,
  49             transform_source=strip_jsonp
  50         )
  51
  52         return {
  53             'id': embed_data['videoId'],
  54             'display_id': episode,
  55             'title': info_el.find('title').text,
  56             'url': token_info['tokenizedUrl'],
  57             'description': get_element_by_attribute('class', 'text', webpage),
  58             'thumbnail': info_el.find('thumb').text,
  59             'duration': parse_duration(info_el.find('duration').text),
  60         }