_ Git - youtube-dl/blob - youtube_dl/extractor/tv2hu.py

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7
   8 class TV2HUIE(InfoExtractor):
   9     IE_NAME = 'tv2.hu'
  10     _VALID_URL = r'https?://(?:www\.)?tv2\.hu/(?:musoraink/)?(?P<uploader>[^/]+)/(?:teljes_adasok/)?(?P<id>[0-9]+)_(.+?)\.html'
  11     _JSON_URL = r'(?P<json_url>https?://.+?\.tv2\.hu/vod/(?P<upload_date>\d+)/id_(?P<upload_id>\d+).+?&type=json)'
  12
  13     _TESTS = [{
  14         'url': 'http://tv2.hu/ezek_megorultek/217679_ezek-megorultek---1.-adas-1.-resz.html',
  15         'info_dict': {
  16             'id': '217679',
  17             'ext': 'mp4',
  18             'title': 'Ezek megőrültek! - 1. adás 1. rész',
  19             'upload_id': '220289',
  20             'upload_date': '20160826',
  21             'uploader': 'ezek_megorultek',
  22             'thumbnail': 're:^https?://.*\.jpg$'
  23         },
  24         'params': {
  25             # m3u8 download
  26             'skip_download': True,
  27         }
  28     }, {
  29         'url': 'http://tv2.hu/ezek_megorultek/teljes_adasok/217677_ezek-megorultek---1.-adas-2.-resz.html',
  30         'only_matching': True
  31     }, {
  32         'url': 'http://tv2.hu/musoraink/aktiv/aktiv_teljes_adas/217963_aktiv-teljes-adas---2016.08.30..html',
  33         'only_matching': True
  34     }]
  35
  36     def _real_extract(self, url):
  37         video_id = self._match_id(url)
  38         webpage = self._download_webpage(
  39             url, video_id, 'Downloading info page')
  40
  41         json_url = re.search(self._JSON_URL, webpage)
  42
  43         json_data = self._download_json(
  44             json_url.group('json_url'), video_id, 'Downloading video info')
  45
  46         manifest_url = json_data['bitrates']['hls']
  47
  48         formats = self._extract_m3u8_formats(
  49             manifest_url, video_id, 'mp4', entry_protocol='m3u8_native')
  50
  51         for i in range(len(json_data['bitrates']['mp4'])):
  52             quality = json_data.get('mp4Labels')[i]
  53
  54             if quality.lower() == 'auto':
  55                 continue
  56
  57             formats.append({
  58                 'protocol': 'http',
  59                 'url': json_data['bitrates']['mp4'][i],
  60                 'height': int(quality[:-1]),
  61                 'width': int(quality[:-1])/9*16,
  62                 'ext': 'mp4',
  63                 'format_id': quality,
  64                 'format_note': 'HTTP',
  65                 'preference': int(quality[:-1])
  66             })
  67
  68         self._sort_formats(formats)
  69
  70         return {
  71             'id': video_id,
  72             'title': self._og_search_title(webpage).strip(),
  73             'thumbnail': self._og_search_property('image', webpage),
  74             'uploader': self._search_regex(self._VALID_URL, url, 'uploader'),
  75             'upload_id': json_url.group('upload_id'),
  76             'upload_date': json_url.group('upload_date'),
  77             'formats': formats
  78         }