8df12eec0d44c371d99b536b55694cfd2211f9d0
[youtube-dl] / 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     ExtractorError,
8     int_or_none,
9     js_to_json,
10 )
11
12
13 class PornHdIE(InfoExtractor):
14     _VALID_URL = r'https?://(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P<id>\d+)(?:/(?P<display_id>.+))?'
15     _TESTS = [{
16         'url': 'http://www.pornhd.com/videos/9864/selfie-restroom-masturbation-fun-with-chubby-cutie-hd-porn-video',
17         'md5': 'c8b964b1f0a4b5f7f28ae3a5c9f86ad5',
18         'info_dict': {
19             'id': '9864',
20             'display_id': 'selfie-restroom-masturbation-fun-with-chubby-cutie-hd-porn-video',
21             'ext': 'mp4',
22             'title': 'Restroom selfie masturbation',
23             'description': 'md5:3748420395e03e31ac96857a8f125b2b',
24             'thumbnail': 're:^https?://.*\.jpg',
25             'view_count': int,
26             'age_limit': 18,
27         }
28     }, {
29         # removed video
30         'url': 'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
31         'md5': '956b8ca569f7f4d8ec563e2c41598441',
32         'info_dict': {
33             'id': '1962',
34             'display_id': 'sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
35             'ext': 'mp4',
36             'title': 'Sierra loves doing laundry',
37             'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294',
38             'thumbnail': 're:^https?://.*\.jpg',
39             'view_count': int,
40             'age_limit': 18,
41         },
42         'skip': 'Not available anymore',
43     }]
44
45     def _real_extract(self, url):
46         mobj = re.match(self._VALID_URL, url)
47         video_id = mobj.group('id')
48         display_id = mobj.group('display_id')
49
50         webpage = self._download_webpage(url, display_id or video_id)
51
52         title = self._html_search_regex(
53             [r'<span[^>]+class=["\']video-name["\'][^>]*>([^<]+)',
54              r'<title>(.+?) - .*?[Pp]ornHD.*?</title>'], webpage, 'title')
55
56         sources = self._parse_json(js_to_json(self._search_regex(
57             r"(?s)'sources'\s*:\s*(\{.+?\})\s*\}[;,)]",
58             webpage, 'sources', default='{}')), video_id)
59
60         if not sources:
61             message = self._html_search_regex(
62                 r'(?s)<(div|p)[^>]+class="no-video"[^>]*>(?P<value>.+?)</\1',
63                 webpage, 'error message', group='value')
64             raise ExtractorError('%s said: %s' % (self.IE_NAME, message), expected=True)
65
66         formats = []
67         for format_id, video_url in sources.items():
68             if not video_url:
69                 continue
70             height = int_or_none(self._search_regex(
71                 r'^(\d+)[pP]', format_id, 'height', default=None))
72             formats.append({
73                 'url': video_url,
74                 'format_id': format_id,
75                 'height': height,
76             })
77         self._sort_formats(formats)
78
79         description = self._html_search_regex(
80             r'<(div|p)[^>]+class="description"[^>]*>(?P<value>[^<]+)</\1',
81             webpage, 'description', fatal=False, group='value')
82         view_count = int_or_none(self._html_search_regex(
83             r'(\d+) views\s*<', webpage, 'view count', fatal=False))
84         thumbnail = self._search_regex(
85             r"'poster'\s*:\s*'([^']+)'", webpage, 'thumbnail', fatal=False)
86
87         return {
88             'id': video_id,
89             'display_id': display_id,
90             'title': title,
91             'description': description,
92             'thumbnail': thumbnail,
93             'view_count': view_count,
94             'formats': formats,
95             'age_limit': 18,
96         }