Raphaël G. Git Repositories - youtubedl/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_xpath
   6 from ..utils import (
   7     int_or_none,
   8     qualities,
   9     unified_strdate,
  10     xpath_attr,
  11     xpath_element,
  12     xpath_text,
  13     xpath_with_ns,
  14 )
  15
  16
  17 class FirstTVIE(InfoExtractor):
  18     IE_NAME = '1tv'
  19     IE_DESC = 'Первый канал'
  20     _VALID_URL = r'https?://(?:www\.)?1tv\.ru/(?:[^/]+/)+p?(?P<id>\d+)'
  21
  22     _TESTS = [{
  23         # single format via video_materials.json API
  24         'url': 'http://www.1tv.ru/prj/inprivate/vypusk/35930',
  25         'md5': '82a2777648acae812d58b3f5bd42882b',
  26         'info_dict': {
  27             'id': '35930',
  28             'ext': 'mp4',
  29             'title': 'Гость Людмила Сенчина. Наедине со всеми. Выпуск от 12.02.2015',
  30             'description': 'md5:357933adeede13b202c7c21f91b871b2',
  31             'thumbnail': 're:^https?://.*\.(?:jpg|JPG)$',
  32             'upload_date': '20150212',
  33             'duration': 2694,
  34         },
  35     }, {
  36         # multiple formats via video_materials.json API
  37         'url': 'http://www.1tv.ru/video_archive/projects/dobroeutro/p113641',
  38         'info_dict': {
  39             'id': '113641',
  40             'ext': 'mp4',
  41             'title': 'Весенняя аллергия. Доброе утро. Фрагмент выпуска от 07.04.2016',
  42             'description': 'md5:8dcebb3dded0ff20fade39087fd1fee2',
  43             'thumbnail': 're:^https?://.*\.(?:jpg|JPG)$',
  44             'upload_date': '20160407',
  45             'duration': 179,
  46             'formats': 'mincount:3',
  47         },
  48         'params': {
  49             'skip_download': True,
  50         },
  51     }, {
  52         # single format only available via ONE_ONLINE_VIDEOS.archive_single_xml API
  53         'url': 'http://www.1tv.ru/video_archive/series/f7552/p47038',
  54         'md5': '519d306c5b5669761fd8906c39dbee23',
  55         'info_dict': {
  56             'id': '47038',
  57             'ext': 'mp4',
  58             'title': '"Побег". Второй сезон. 3 серия',
  59             'description': 'md5:3abf8f6b9bce88201c33e9a3d794a00b',
  60             'thumbnail': 're:^https?://.*\.(?:jpg|JPG)$',
  61             'upload_date': '20120516',
  62             'duration': 3080,
  63         },
  64     }, {
  65         'url': 'http://www.1tv.ru/videoarchive/9967',
  66         'only_matching': True,
  67     }]
  68
  69     def _real_extract(self, url):
  70         video_id = self._match_id(url)
  71
  72         # Videos with multiple formats only available via this API
  73         video = self._download_json(
  74             'http://www.1tv.ru/video_materials.json?legacy_id=%s' % video_id,
  75             video_id, fatal=False)
  76
  77         description, thumbnail, upload_date, duration = [None] * 4
  78
  79         if video:
  80             item = video[0]
  81             title = item['title']
  82             quality = qualities(('ld', 'sd', 'hd', ))
  83             formats = [{
  84                 'url': f['src'],
  85                 'format_id': f.get('name'),
  86                 'quality': quality(f.get('name')),
  87             } for f in item['mbr'] if f.get('src')]
  88             thumbnail = item.get('poster')
  89         else:
  90             # Some videos are not available via video_materials.json
  91             video = self._download_xml(
  92                 'http://www.1tv.ru/owa/win/ONE_ONLINE_VIDEOS.archive_single_xml?pid=%s' % video_id,
  93                 video_id)
  94
  95             NS_MAP = {
  96                 'media': 'http://search.yahoo.com/mrss/',
  97             }
  98
  99             item = xpath_element(video, './channel/item', fatal=True)
 100             title = xpath_text(item, './title', fatal=True)
 101             formats = [{
 102                 'url': content.attrib['url'],
 103             } for content in item.findall(
 104                 compat_xpath(xpath_with_ns('./media:content', NS_MAP))) if content.attrib.get('url')]
 105             thumbnail = xpath_attr(
 106                 item, xpath_with_ns('./media:thumbnail', NS_MAP), 'url')
 107
 108         self._sort_formats(formats)
 109
 110         webpage = self._download_webpage(url, video_id, 'Downloading page', fatal=False)
 111         if webpage:
 112             title = self._html_search_regex(
 113                 (r'<div class="tv_translation">\s*<h1><a href="[^"]+">([^<]*)</a>',
 114                  r"'title'\s*:\s*'([^']+)'"),
 115                 webpage, 'title', default=None) or title
 116             description = self._html_search_regex(
 117                 r'<div class="descr">\s*<div>&nbsp;</div>\s*<p>([^<]*)</p></div>',
 118                 webpage, 'description', default=None) or self._html_search_meta(
 119                 'description', webpage, 'description')
 120             thumbnail = thumbnail or self._og_search_thumbnail(webpage)
 121             duration = int_or_none(self._html_search_meta(
 122                 'video:duration', webpage, 'video duration', fatal=False))
 123             upload_date = unified_strdate(self._html_search_meta(
 124                 'ya:ovs:upload_date', webpage, 'upload date', fatal=False))
 125
 126         return {
 127             'id': video_id,
 128             'thumbnail': thumbnail,
 129             'title': title,
 130             'description': description,
 131             'upload_date': upload_date,
 132             'duration': int_or_none(duration),
 133             'formats': formats
 134         }