Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/tvigle.py

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     unified_strdate,
   9     clean_html,
  10     int_or_none,
  11 )
  12
  13
  14 class TvigleIE(InfoExtractor):
  15     IE_NAME = 'tvigle'
  16     IE_DESC = 'Интернет-телевидение Tvigle.ru'
  17     _VALID_URL = r'http://(?:www\.)?tvigle\.ru/category/.+?[\?&]v(?:ideo)?=(?P<id>\d+)'
  18
  19     _TESTS = [
  20         {
  21             'url': 'http://www.tvigle.ru/category/cinema/1608/?video=503081',
  22             'md5': '09afba4616666249f087efc6dcf83cb3',
  23             'info_dict': {
  24                 'id': '503081',
  25                 'ext': 'flv',
  26                 'title': 'Брат 2 ',
  27                 'description': 'md5:f5a42970f50648cee3d7ad740f3ae769',
  28                 'upload_date': '20110919',
  29             },
  30         },
  31         {
  32             'url': 'http://www.tvigle.ru/category/men/vysotskiy_vospominaniya02/?flt=196&v=676433',
  33             'md5': 'e7efe5350dd5011d0de6550b53c3ba7b',
  34             'info_dict': {
  35                 'id': '676433',
  36                 'ext': 'flv',
  37                 'title': 'Ведущий телепрограммы «60 минут» (США) о Владимире Высоцком',
  38                 'description': 'md5:027f7dc872948f14c96d19b4178428a4',
  39                 'upload_date': '20121218',
  40             },
  41         },
  42     ]
  43
  44     def _real_extract(self, url):
  45         mobj = re.match(self._VALID_URL, url)
  46         video_id = mobj.group('id')
  47
  48         video_data = self._download_xml(
  49             'http://www.tvigle.ru/xml/single.php?obj=%s' % video_id, video_id, 'Downloading video XML')
  50
  51         video = video_data.find('./video')
  52
  53         title = video.get('name')
  54         description = video.get('anons')
  55         if description:
  56             description = clean_html(description)
  57         thumbnail = video_data.get('img')
  58         upload_date = unified_strdate(video.get('date'))
  59         like_count = int_or_none(video.get('vtp'))
  60
  61         formats = []
  62         for num, (format_id, format_note) in enumerate([['low_file', 'SQ'], ['file', 'HQ'], ['hd', 'HD 720']]):
  63             video_url = video.get(format_id)
  64             if not video_url:
  65                 continue
  66             formats.append({
  67                 'url': video_url,
  68                 'format_id': format_id,
  69                 'format_note': format_note,
  70                 'quality': num,
  71             })
  72
  73         self._sort_formats(formats)
  74
  75         return {
  76             'id': video_id,
  77             'title': title,
  78             'description': description,
  79             'thumbnail': thumbnail,
  80             'upload_date': upload_date,
  81             'like_count': like_count,
  82             'age_limit': 18,
  83             'formats': formats,
  84         }