]> gitweb @ CieloNegro.org - youtube-dl.git/blob - youtube_dl/extractor/pornhd.py
[ard] Improve _VALID_URL (closes #25134) (#25198)
[youtube-dl.git] / youtube_dl / extractor / pornhd.py
1 from __future__ import unicode_literals
2
3 import re
4
5 from .common import InfoExtractor
6 from ..utils import (
7     determine_ext,
8     ExtractorError,
9     int_or_none,
10     js_to_json,
11     merge_dicts,
12     urljoin,
13 )
14
15
16 class PornHdIE(InfoExtractor):
17     _VALID_URL = r'https?://(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P<id>\d+)(?:/(?P<display_id>.+))?'
18     _TESTS = [{
19         'url': 'http://www.pornhd.com/videos/9864/selfie-restroom-masturbation-fun-with-chubby-cutie-hd-porn-video',
20         'md5': '87f1540746c1d32ec7a2305c12b96b25',
21         'info_dict': {
22             'id': '9864',
23             'display_id': 'selfie-restroom-masturbation-fun-with-chubby-cutie-hd-porn-video',
24             'ext': 'mp4',
25             'title': 'Restroom selfie masturbation',
26             'description': 'md5:3748420395e03e31ac96857a8f125b2b',
27             'thumbnail': r're:^https?://.*\.jpg',
28             'view_count': int,
29             'like_count': int,
30             'age_limit': 18,
31         },
32         'skip': 'HTTP Error 404: Not Found',
33     }, {
34         'url': 'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
35         'md5': '1b7b3a40b9d65a8e5b25f7ab9ee6d6de',
36         'info_dict': {
37             'id': '1962',
38             'display_id': 'sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
39             'ext': 'mp4',
40             'title': 'md5:98c6f8b2d9c229d0f0fde47f61a1a759',
41             'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294',
42             'thumbnail': r're:^https?://.*\.jpg',
43             'view_count': int,
44             'like_count': int,
45             'age_limit': 18,
46         },
47     }]
48
49     def _real_extract(self, url):
50         mobj = re.match(self._VALID_URL, url)
51         video_id = mobj.group('id')
52         display_id = mobj.group('display_id')
53
54         webpage = self._download_webpage(url, display_id or video_id)
55
56         title = self._html_search_regex(
57             [r'<span[^>]+class=["\']video-name["\'][^>]*>([^<]+)',
58              r'<title>(.+?) - .*?[Pp]ornHD.*?</title>'], webpage, 'title')
59
60         sources = self._parse_json(js_to_json(self._search_regex(
61             r"(?s)sources'?\s*[:=]\s*(\{.+?\})",
62             webpage, 'sources', default='{}')), video_id)
63
64         info = {}
65         if not sources:
66             entries = self._parse_html5_media_entries(url, webpage, video_id)
67             if entries:
68                 info = entries[0]
69
70         if not sources and not info:
71             message = self._html_search_regex(
72                 r'(?s)<(div|p)[^>]+class="no-video"[^>]*>(?P<value>.+?)</\1',
73                 webpage, 'error message', group='value')
74             raise ExtractorError('%s said: %s' % (self.IE_NAME, message), expected=True)
75
76         formats = []
77         for format_id, video_url in sources.items():
78             video_url = urljoin(url, video_url)
79             if not video_url:
80                 continue
81             height = int_or_none(self._search_regex(
82                 r'^(\d+)[pP]', format_id, 'height', default=None))
83             formats.append({
84                 'url': video_url,
85                 'ext': determine_ext(video_url, 'mp4'),
86                 'format_id': format_id,
87                 'height': height,
88             })
89         if formats:
90             info['formats'] = formats
91         self._sort_formats(info['formats'])
92
93         description = self._html_search_regex(
94             (r'(?s)<section[^>]+class=["\']video-description[^>]+>(?P<value>.+?)</section>',
95              r'<(div|p)[^>]+class="description"[^>]*>(?P<value>[^<]+)</\1'),
96             webpage, 'description', fatal=False,
97             group='value') or self._html_search_meta(
98             'description', webpage, default=None) or self._og_search_description(webpage)
99         view_count = int_or_none(self._html_search_regex(
100             r'(\d+) views\s*<', webpage, 'view count', fatal=False))
101         thumbnail = self._search_regex(
102             r"poster'?\s*:\s*([\"'])(?P<url>(?:(?!\1).)+)\1", webpage,
103             'thumbnail', default=None, group='url')
104
105         like_count = int_or_none(self._search_regex(
106             (r'(\d+)</span>\s*likes',
107              r'(\d+)\s*</11[^>]+>(?:&nbsp;|\s)*\blikes',
108              r'class=["\']save-count["\'][^>]*>\s*(\d+)'),
109             webpage, 'like count', fatal=False))
110
111         return merge_dicts(info, {
112             'id': video_id,
113             'display_id': display_id,
114             'title': title,
115             'description': description,
116             'thumbnail': thumbnail,
117             'view_count': view_count,
118             'like_count': like_count,
119             'formats': formats,
120             'age_limit': 18,
121         })