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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from .youtube import YoutubeIE
   7 from ..utils import (
   8     parse_iso8601,
   9     str_to_int,
  10 )
  11
  12
  13 class CrackedIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?cracked\.com/video_(?P<id>\d+)_[\da-z-]+\.html'
  15     _TESTS = [{
  16         'url': 'http://www.cracked.com/video_19070_if-animal-actors-got-e21-true-hollywood-stories.html',
  17         'md5': '89b90b9824e3806ca95072c4d78f13f7',
  18         'info_dict': {
  19             'id': '19070',
  20             'ext': 'mp4',
  21             'title': 'If Animal Actors Got E! True Hollywood Stories',
  22             'timestamp': 1404954000,
  23             'upload_date': '20140710',
  24         }
  25     }, {
  26         # youtube embed
  27         'url': 'http://www.cracked.com/video_19006_4-plot-holes-you-didnt-notice-in-your-favorite-movies.html',
  28         'md5': 'ccd52866b50bde63a6ef3b35016ba8c7',
  29         'info_dict': {
  30             'id': 'EjI00A3rZD0',
  31             'ext': 'mp4',
  32             'title': "4 Plot Holes You Didn't Notice in Your Favorite Movies - The Spit Take",
  33             'description': 'md5:c603708c718b796fe6079e2b3351ffc7',
  34             'upload_date': '20140725',
  35             'uploader_id': 'Cracked',
  36             'uploader': 'Cracked',
  37         }
  38     }]
  39
  40     def _real_extract(self, url):
  41         video_id = self._match_id(url)
  42
  43         webpage = self._download_webpage(url, video_id)
  44
  45         youtube_url = YoutubeIE._extract_url(webpage)
  46         if youtube_url:
  47             return self.url_result(youtube_url, ie=YoutubeIE.ie_key())
  48
  49         video_url = self._html_search_regex(
  50             [r'var\s+CK_vidSrc\s*=\s*"([^"]+)"', r'<video\s+src="([^"]+)"'],
  51             webpage, 'video URL')
  52
  53         title = self._search_regex(
  54             [r'property="?og:title"?\s+content="([^"]+)"', r'class="?title"?>([^<]+)'],
  55             webpage, 'title')
  56
  57         description = self._search_regex(
  58             r'name="?(?:og:)?description"?\s+content="([^"]+)"',
  59             webpage, 'description', default=None)
  60
  61         timestamp = self._html_search_regex(
  62             r'"date"\s*:\s*"([^"]+)"', webpage, 'upload date', fatal=False)
  63         if timestamp:
  64             timestamp = parse_iso8601(timestamp[:-6])
  65
  66         view_count = str_to_int(self._html_search_regex(
  67             r'<span\s+class="?views"? id="?viewCounts"?>([\d,\.]+) Views</span>',
  68             webpage, 'view count', fatal=False))
  69         comment_count = str_to_int(self._html_search_regex(
  70             r'<span\s+id="?commentCounts"?>([\d,\.]+)</span>',
  71             webpage, 'comment count', fatal=False))
  72
  73         m = re.search(r'_(?P<width>\d+)X(?P<height>\d+)\.mp4$', video_url)
  74         if m:
  75             width = int(m.group('width'))
  76             height = int(m.group('height'))
  77         else:
  78             width = height = None
  79
  80         return {
  81             'id': video_id,
  82             'url': video_url,
  83             'title': title,
  84             'description': description,
  85             'timestamp': timestamp,
  86             'view_count': view_count,
  87             'comment_count': comment_count,
  88             'height': height,
  89             'width': width,
  90         }