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 ..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     _TESTS = [{
  15         'url': 'http://www.cracked.com/video_19070_if-animal-actors-got-e21-true-hollywood-stories.html',
  16         'md5': '89b90b9824e3806ca95072c4d78f13f7',
  17         'info_dict': {
  18             'id': '19070',
  19             'ext': 'mp4',
  20             'title': 'If Animal Actors Got E! True Hollywood Stories',
  21             'timestamp': 1404954000,
  22             'upload_date': '20140710',
  23         }
  24     }, {
  25         # youtube embed
  26         'url': 'http://www.cracked.com/video_19006_4-plot-holes-you-didnt-notice-in-your-favorite-movies.html',
  27         'md5': 'ccd52866b50bde63a6ef3b35016ba8c7',
  28         'info_dict': {
  29             'id': 'EjI00A3rZD0',
  30             'ext': 'mp4',
  31             'title': "4 Plot Holes You Didn't Notice in Your Favorite Movies - The Spit Take",
  32             'description': 'md5:c603708c718b796fe6079e2b3351ffc7',
  33             'upload_date': '20140725',
  34             'uploader_id': 'Cracked',
  35             'uploader': 'Cracked',
  36         }
  37     }]
  38
  39     def _real_extract(self, url):
  40         video_id = self._match_id(url)
  41
  42         webpage = self._download_webpage(url, video_id)
  43
  44         youtube_url = self._search_regex(
  45             r'<iframe[^>]+src="((?:https?:)?//www\.youtube\.com/embed/[^"]+)"',
  46             webpage, 'youtube url', default=None)
  47         if youtube_url:
  48             return self.url_result(youtube_url, 'Youtube')
  49
  50         video_url = self._html_search_regex(
  51             [r'var\s+CK_vidSrc\s*=\s*"([^"]+)"', r'<video\s+src="([^"]+)"'],
  52             webpage, 'video URL')
  53
  54         title = self._search_regex(
  55             [r'property="?og:title"?\s+content="([^"]+)"', r'class="?title"?>([^<]+)'],
  56             webpage, 'title')
  57
  58         description = self._search_regex(
  59             r'name="?(?:og:)?description"?\s+content="([^"]+)"',
  60             webpage, 'description', default=None)
  61
  62         timestamp = self._html_search_regex(
  63             r'"date"\s*:\s*"([^"]+)"', webpage, 'upload date', fatal=False)
  64         if timestamp:
  65             timestamp = parse_iso8601(timestamp[:-6])
  66
  67         view_count = str_to_int(self._html_search_regex(
  68             r'<span\s+class="?views"? id="?viewCounts"?>([\d,\.]+) Views</span>',
  69             webpage, 'view count', fatal=False))
  70         comment_count = str_to_int(self._html_search_regex(
  71             r'<span\s+id="?commentCounts"?>([\d,\.]+)</span>',
  72             webpage, 'comment count', fatal=False))
  73
  74         m = re.search(r'_(?P<width>\d+)X(?P<height>\d+)\.mp4$', video_url)
  75         if m:
  76             width = int(m.group('width'))
  77             height = int(m.group('height'))
  78         else:
  79             width = height = None
  80
  81         return {
  82             'id': video_id,
  83             'url': video_url,
  84             'title': title,
  85             'description': description,
  86             'timestamp': timestamp,
  87             'view_count': view_count,
  88             'comment_count': comment_count,
  89             'height': height,
  90             'width': width,
  91         }