Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/kontrtube.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     int_or_none,
   9     parse_duration,
  10 )
  11
  12
  13 class KontrTubeIE(InfoExtractor):
  14     IE_NAME = 'kontrtube'
  15     IE_DESC = 'KontrTube.ru - Труба зовёт'
  16     _VALID_URL = r'https?://(?:www\.)?kontrtube\.ru/videos/(?P<id>\d+)/(?P<display_id>[^/]+)/'
  17
  18     _TEST = {
  19         'url': 'http://www.kontrtube.ru/videos/2678/nad-olimpiyskoy-derevney-v-sochi-podnyat-rossiyskiy-flag/',
  20         'md5': '975a991a4926c9a85f383a736a2e6b80',
  21         'info_dict': {
  22             'id': '2678',
  23             'display_id': 'nad-olimpiyskoy-derevney-v-sochi-podnyat-rossiyskiy-flag',
  24             'ext': 'mp4',
  25             'title': 'Над олимпийской деревней в Сочи поднят российский флаг',
  26             'description': 'md5:80edc4c613d5887ae8ccf1d59432be41',
  27             'thumbnail': 'http://www.kontrtube.ru/contents/videos_screenshots/2000/2678/preview.mp4.jpg',
  28             'duration': 270,
  29         }
  30     }
  31
  32     def _real_extract(self, url):
  33         mobj = re.match(self._VALID_URL, url)
  34         video_id = mobj.group('id')
  35         display_id = mobj.group('display_id')
  36
  37         webpage = self._download_webpage(
  38             url, display_id, 'Downloading page')
  39
  40         video_url = self._search_regex(
  41             r"video_url\s*:\s*'(.+?)/?',", webpage, 'video URL')
  42         thumbnail = self._search_regex(
  43             r"preview_url\s*:\s*'(.+?)/?',", webpage, 'thumbnail', fatal=False)
  44         title = self._html_search_regex(
  45             r'(?s)<h2>(.+?)</h2>', webpage, 'title')
  46         description = self._html_search_meta(
  47             'description', webpage, 'description')
  48
  49         duration = self._search_regex(
  50             r'Длительность: <em>([^<]+)</em>', webpage, 'duration', fatal=False)
  51         if duration:
  52             duration = parse_duration(duration.replace('мин', 'min').replace('сек', 'sec'))
  53
  54         view_count = self._search_regex(
  55             r'Просмотров: <em>([^<]+)</em>',
  56             webpage, 'view count', fatal=False)
  57         if view_count:
  58             view_count = int_or_none(view_count.replace(' ', ''))
  59
  60         comment_count = int_or_none(self._search_regex(
  61             r'Комментарии \((\d+)\)<', webpage, ' comment count', fatal=False))
  62
  63         return {
  64             'id': video_id,
  65             'display_id': display_id,
  66             'url': video_url,
  67             'thumbnail': thumbnail,
  68             'title': title,
  69             'description': description,
  70             'duration': duration,
  71             'view_count': int_or_none(view_count),
  72             'comment_count': int_or_none(comment_count),
  73         }