_ Git - youtube-dl/blob - youtube_dl/extractor/wat.py

   1 # coding: utf-8
   2
   3 import json
   4 import re
   5
   6 from .common import InfoExtractor
   7
   8 from ..utils import (
   9     compat_urllib_parse,
  10 )
  11
  12
  13 class WatIE(InfoExtractor):
  14     _VALID_URL=r'http://www.wat.tv/.*-(?P<shortID>.*?)_.*?.html'
  15     IE_NAME = 'wat.tv'
  16     _TEST = {
  17         u'url': u'http://www.wat.tv/video/world-war-philadelphia-vost-6bv55_2fjr7_.html',
  18         u'file': u'6bv55.mp4',
  19         u'md5': u'0a4fe7870f31eaeabb5e25fd8da8414a',
  20         u'info_dict': {
  21             u"title": u"World War Z - Philadelphia VOST"
  22         }
  23     }
  24
  25     def _real_extract(self, url):
  26         mobj = re.match(self._VALID_URL, url)
  27         short_id = mobj.group('shortID')
  28
  29         player_data = compat_urllib_parse.urlencode({'shortVideoId': short_id,
  30                                                      'html5': '1'})
  31         player_info = self._download_webpage('http://www.wat.tv/player?' + player_data,
  32                                              short_id, u'Downloading player info')
  33         player = json.loads(player_info)['player']
  34         html5_player = self._html_search_regex(r'iframe src="(.*?)"', player,
  35                                                'html5 player')
  36         player_webpage = self._download_webpage(html5_player, short_id,
  37                                                 u'Downloading player webpage')
  38
  39         video_url = self._search_regex(r'urlhtml5 : "(.*?)"', player_webpage,
  40                                        'video url')
  41         title = self._search_regex(r'contentTitle : "(.*?)"', player_webpage,
  42                                    'title')
  43         thumbnail = self._search_regex(r'previewMedia : "(.*?)"', player_webpage,
  44                                        'thumbnail')
  45         return {'id': short_id,
  46                 'url': video_url,
  47                 'ext': 'mp4',
  48                 'title': title,
  49                 'thumbnail': thumbnail,
  50                 }
  51
  52 class TF1IE(InfoExtractor):
  53     """
  54     TF1 uses the wat.tv player, currently it can only download videos with the
  55     html5 player enabled, it cannot download HD videos or the news.
  56     """
  57     _VALID_URL = r'http://videos.tf1.fr/.*-(.*?).html'
  58     _TEST = {
  59         u'url': u'http://videos.tf1.fr/auto-moto/citroen-grand-c4-picasso-2013-presentation-officielle-8062060.html',
  60         u'file': u'6bysb.mp4',
  61         u'md5': u'66789d3e91278d332f75e1feb7aea327',
  62         u'info_dict': {
  63             u"title": u"Citroën Grand C4 Picasso 2013 : présentation officielle"
  64         }
  65     }
  66
  67     def _real_extract(self, url):
  68         mobj = re.match(self._VALID_URL, url)
  69         id = mobj.group(1)
  70         webpage = self._download_webpage(url, id)
  71         embed_url = self._html_search_regex(r'"(https://www.wat.tv/embedframe/.*?)"',
  72                                 webpage, 'embed url')
  73         embed_page = self._download_webpage(embed_url, id, u'Downloading embed player page')
  74         wat_id = self._search_regex(r'UVID=(.*?)&', embed_page, 'wat id')
  75         wat_info = self._download_webpage('http://www.wat.tv/interface/contentv3/%s' % wat_id, id, u'Downloading Wat info')
  76         wat_info = json.loads(wat_info)['media']
  77         wat_url = wat_info['url']
  78         return self.url_result(wat_url, 'Wat')