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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     parse_iso8601,
   8     str_to_int,
   9 )
  10
  11
  12 class CrackedIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:www\.)?cracked\.com/video_(?P<id>\d+)_[\da-z-]+\.html'
  14     _TEST = {
  15         'url': 'http://www.cracked.com/video_19006_4-plot-holes-you-didnt-notice-in-your-favorite-movies.html',
  16         'md5': '4b29a5eeec292cd5eca6388c7558db9e',
  17         'info_dict': {
  18             'id': '19006',
  19             'ext': 'mp4',
  20             'title': '4 Plot Holes You Didn\'t Notice in Your Favorite Movies',
  21             'description': 'md5:3b909e752661db86007d10e5ec2df769',
  22             'timestamp': 1405659600,
  23             'upload_date': '20140718',
  24         }
  25     }
  26
  27     def _real_extract(self, url):
  28         mobj = re.match(self._VALID_URL, url)
  29         video_id = mobj.group('id')
  30
  31         webpage = self._download_webpage(url, video_id)
  32
  33         video_url = self._html_search_regex(
  34             [r'var\s+CK_vidSrc\s*=\s*"([^"]+)"', r'<video\s+src="([^"]+)"'], webpage, 'video URL')
  35
  36         title = self._search_regex(
  37             [r'property="?og:title"?\s+content="([^"]+)"', r'class="?title"?>([^<]+)'],
  38             webpage, 'title')
  39
  40         description = self._search_regex(
  41             r'name="?(?:og:)?description"?\s+content="([^"]+)"',
  42             webpage, 'description', default=None)
  43
  44         timestamp = self._html_search_regex(
  45             r'"date"\s*:\s*"([^"]+)"', webpage, 'upload date', fatal=False)
  46         if timestamp:
  47             timestamp = parse_iso8601(timestamp[:-6])
  48
  49         view_count = str_to_int(self._html_search_regex(
  50             r'<span\s+class="?views"? id="?viewCounts"?>([\d,\.]+) Views</span>',
  51             webpage, 'view count', fatal=False))
  52         comment_count = str_to_int(self._html_search_regex(
  53             r'<span\s+id="?commentCounts"?>([\d,\.]+)</span>',
  54             webpage, 'comment count', fatal=False))
  55
  56         m = re.search(r'_(?P<width>\d+)X(?P<height>\d+)\.mp4$', video_url)
  57         if m:
  58             width = int(m.group('width'))
  59             height = int(m.group('height'))
  60         else:
  61             width = height = None
  62
  63         return {
  64             'id': video_id,
  65             'url': video_url,
  66             'title': title,
  67             'description': description,
  68             'timestamp': timestamp,
  69             'view_count': view_count,
  70             'comment_count': comment_count,
  71             'height': height,
  72             'width': width,
  73         }