]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/cracked.py
[ie/orf:on] Improve extraction (#9677)
[yt-dlp.git] / yt_dlp / extractor / cracked.py
CommitLineData
43f0537c 1import re
2
3from .common import InfoExtractor
5113b691 4from .youtube import YoutubeIE
e0942e37
S
5from ..utils import (
6 parse_iso8601,
7 str_to_int,
8)
9
43f0537c 10
11class CrackedIE(InfoExtractor):
e0942e37 12 _VALID_URL = r'https?://(?:www\.)?cracked\.com/video_(?P<id>\d+)_[\da-z-]+\.html'
c610f38b
S
13 _TESTS = [{
14 'url': 'http://www.cracked.com/video_19070_if-animal-actors-got-e21-true-hollywood-stories.html',
15 'md5': '89b90b9824e3806ca95072c4d78f13f7',
16 'info_dict': {
17 'id': '19070',
18 'ext': 'mp4',
19 'title': 'If Animal Actors Got E! True Hollywood Stories',
20 'timestamp': 1404954000,
21 'upload_date': '20140710',
22 }
23 }, {
24 # youtube embed
e0942e37 25 'url': 'http://www.cracked.com/video_19006_4-plot-holes-you-didnt-notice-in-your-favorite-movies.html',
c610f38b 26 'md5': 'ccd52866b50bde63a6ef3b35016ba8c7',
43f0537c 27 'info_dict': {
c610f38b 28 'id': 'EjI00A3rZD0',
43f0537c 29 'ext': 'mp4',
c610f38b
S
30 'title': "4 Plot Holes You Didn't Notice in Your Favorite Movies - The Spit Take",
31 'description': 'md5:c603708c718b796fe6079e2b3351ffc7',
32 'upload_date': '20140725',
33 'uploader_id': 'Cracked',
34 'uploader': 'Cracked',
43f0537c 35 }
c610f38b 36 }]
43f0537c 37
38 def _real_extract(self, url):
d7403332 39 video_id = self._match_id(url)
43f0537c 40
41 webpage = self._download_webpage(url, video_id)
43f0537c 42
5113b691 43 youtube_url = YoutubeIE._extract_url(webpage)
6447353f 44 if youtube_url:
5113b691 45 return self.url_result(youtube_url, ie=YoutubeIE.ie_key())
6447353f 46
e0942e37 47 video_url = self._html_search_regex(
6447353f
S
48 [r'var\s+CK_vidSrc\s*=\s*"([^"]+)"', r'<video\s+src="([^"]+)"'],
49 webpage, 'video URL')
43f0537c 50
b46ed499
S
51 title = self._search_regex(
52 [r'property="?og:title"?\s+content="([^"]+)"', r'class="?title"?>([^<]+)'],
53 webpage, 'title')
43f0537c 54
b46ed499
S
55 description = self._search_regex(
56 r'name="?(?:og:)?description"?\s+content="([^"]+)"',
57 webpage, 'description', default=None)
58
59 timestamp = self._html_search_regex(
60 r'"date"\s*:\s*"([^"]+)"', webpage, 'upload date', fatal=False)
e0942e37
S
61 if timestamp:
62 timestamp = parse_iso8601(timestamp[:-6])
43f0537c 63
e0942e37 64 view_count = str_to_int(self._html_search_regex(
b46ed499
S
65 r'<span\s+class="?views"? id="?viewCounts"?>([\d,\.]+) Views</span>',
66 webpage, 'view count', fatal=False))
e0942e37 67 comment_count = str_to_int(self._html_search_regex(
b46ed499
S
68 r'<span\s+id="?commentCounts"?>([\d,\.]+)</span>',
69 webpage, 'comment count', fatal=False))
43f0537c 70
e0942e37
S
71 m = re.search(r'_(?P<width>\d+)X(?P<height>\d+)\.mp4$', video_url)
72 if m:
73 width = int(m.group('width'))
74 height = int(m.group('height'))
75 else:
76 width = height = None
43f0537c 77
e0942e37
S
78 return {
79 'id': video_id,
5f6a1245 80 'url': video_url,
e0942e37
S
81 'title': title,
82 'description': description,
83 'timestamp': timestamp,
84 'view_count': view_count,
85 'comment_count': comment_count,
86 'height': height,
87 'width': width,
5f6a1245 88 }