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

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import compat_urlparse
   6 from ..utils import (
   7     int_or_none,
   8     qualities,
   9     unified_strdate,
  10 )
  11
  12
  13 class FirstTVIE(InfoExtractor):
  14     IE_NAME = '1tv'
  15     IE_DESC = 'Первый канал'
  16     _VALID_URL = r'https?://(?:www\.)?1tv\.ru/(?:[^/]+/)+(?P<id>[^/?#]+)'
  17
  18     _TESTS = [{
  19         'url': 'http://www.1tv.ru/shows/naedine-so-vsemi/vypuski/gost-lyudmila-senchina-naedine-so-vsemi-vypusk-ot-12-02-2015',
  20         'md5': 'a1b6b60d530ebcf8daacf4565762bbaf',
  21         'info_dict': {
  22             'id': '40049',
  23             'ext': 'mp4',
  24             'title': 'Гость Людмила Сенчина. Наедине со всеми. Выпуск от 12.02.2015',
  25             'description': 'md5:36a39c1d19618fec57d12efe212a8370',
  26             'thumbnail': 're:^https?://.*\.(?:jpg|JPG)$',
  27             'upload_date': '20150212',
  28             'duration': 2694,
  29         },
  30     }, {
  31         'url': 'http://www.1tv.ru/shows/dobroe-utro/pro-zdorove/vesennyaya-allergiya-dobroe-utro-fragment-vypuska-ot-07042016',
  32         'only_matching': 'true',
  33     }]
  34
  35     def _real_extract(self, url):
  36         display_id = self._match_id(url)
  37
  38         webpage = self._download_webpage(url, display_id)
  39         playlist_url = compat_urlparse.urljoin(url, self._search_regex(
  40             r'data-playlist-url="([^"]+)', webpage, 'playlist url'))
  41
  42         item = self._download_json(playlist_url, display_id)[0]
  43         video_id = item['id']
  44         quality = qualities(('ld', 'sd', 'hd', ))
  45         formats = []
  46         for f in item.get('mbr', []):
  47             src = f.get('src')
  48             if not src:
  49                 continue
  50             fname = f.get('name')
  51             formats.append({
  52                 'url': src,
  53                 'format_id': fname,
  54                 'quality': quality(fname),
  55             })
  56         self._sort_formats(formats)
  57
  58         title = self._html_search_regex(
  59             (r'<div class="tv_translation">\s*<h1><a href="[^"]+">([^<]*)</a>',
  60              r"'title'\s*:\s*'([^']+)'"),
  61             webpage, 'title', default=None) or item['title']
  62         description = self._html_search_regex(
  63             r'<div class="descr">\s*<div>&nbsp;</div>\s*<p>([^<]*)</p></div>',
  64             webpage, 'description', default=None) or self._html_search_meta(
  65             'description', webpage, 'description')
  66         duration = int_or_none(self._html_search_meta(
  67             'video:duration', webpage, 'video duration', fatal=False))
  68         upload_date = unified_strdate(self._html_search_meta(
  69             'ya:ovs:upload_date', webpage, 'upload date', fatal=False))
  70
  71         return {
  72             'id': video_id,
  73             'thumbnail': item.get('poster') or self._og_search_thumbnail(webpage),
  74             'title': title,
  75             'description': description,
  76             'upload_date': upload_date,
  77             'duration': int_or_none(duration),
  78             'formats': formats
  79         }