aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/pornhub.py
blob: 913995044c34171e038991b7b0e59029126bb3c0 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
from __future__ import unicode_literals

import os
import re

from .common import InfoExtractor
from ..compat import (
    compat_urllib_parse,
    compat_urllib_parse_urlparse,
    compat_urllib_request,
)
from ..utils import (
    ExtractorError,
    str_to_int,
)
from ..aes import (
    aes_decrypt_text
)


class PornHubIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?pornhub\.com/view_video\.php\?viewkey=(?P<id>[0-9a-f]+)'
    _TEST = {
        'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
        'md5': '882f488fa1f0026f023f33576004a2ed',
        'info_dict': {
            'id': '648719015',
            'ext': 'mp4',
            "uploader": "Babes",
            "title": "Seductive Indian beauty strips down and fingers her pink pussy",
            "age_limit": 18
        }
    }

    def _extract_count(self, pattern, webpage, name):
        count = self._html_search_regex(pattern, webpage, '%s count' % name, fatal=False)
        if count:
            count = str_to_int(count)
        return count

    def _real_extract(self, url):
        video_id = self._match_id(url)

        req = compat_urllib_request.Request(url)
        req.add_header('Cookie', 'age_verified=1')
        webpage = self._download_webpage(req, video_id)

        error_msg = self._html_search_regex(
            r'(?s)<div class="userMessageSection[^"]*".*?>(.*?)</div>',
            webpage, 'error message', default=None)
        if error_msg:
            error_msg = re.sub(r'\s+', ' ', error_msg)
            raise ExtractorError(
                'PornHub said: %s' % error_msg,
                expected=True, video_id=video_id)

        video_title = self._html_search_regex(r'<h1 [^>]+>([^<]+)', webpage, 'title')
        video_uploader = self._html_search_regex(
            r'(?s)From:&nbsp;.+?<(?:a href="/users/|a href="/channels/|<span class="username)[^>]+>(.+?)<',
            webpage, 'uploader', fatal=False)
        thumbnail = self._html_search_regex(r'"image_url":"([^"]+)', webpage, 'thumbnail', fatal=False)
        if thumbnail:
            thumbnail = compat_urllib_parse.unquote(thumbnail)

        view_count = self._extract_count(r'<span class="count">([\d,\.]+)</span> views', webpage, 'view')
        like_count = self._extract_count(r'<span class="votesUp">([\d,\.]+)</span>', webpage, 'like')
        dislike_count = self._extract_count(r'<span class="votesDown">([\d,\.]+)</span>', webpage, 'dislike')
        comment_count = self._extract_count(
            r'All comments \(<var class="videoCommentCount">([\d,\.]+)</var>', webpage, 'comment')

        video_urls = list(map(compat_urllib_parse.unquote, re.findall(r'"quality_[0-9]{3}p":"([^"]+)', webpage)))
        if webpage.find('"encrypted":true') != -1:
            password = compat_urllib_parse.unquote_plus(self._html_search_regex(r'"video_title":"([^"]+)', webpage, 'password'))
            video_urls = list(map(lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), video_urls))

        formats = []
        for video_url in video_urls:
            path = compat_urllib_parse_urlparse(video_url).path
            extension = os.path.splitext(path)[1][1:]
            format = path.split('/')[5].split('_')[:2]
            format = "-".join(format)

            m = re.match(r'^(?P<height>[0-9]+)P-(?P<tbr>[0-9]+)K$', format)
            if m is None:
                height = None
                tbr = None
            else:
                height = int(m.group('height'))
                tbr = int(m.group('tbr'))

            formats.append({
                'url': video_url,
                'ext': extension,
                'format': format,
                'format_id': format,
                'tbr': tbr,
                'height': height,
            })
        self._sort_formats(formats)

        return {
            'id': video_id,
            'uploader': video_uploader,
            'title': video_title,
            'thumbnail': thumbnail,
            'view_count': view_count,
            'like_count': like_count,
            'dislike_count': dislike_count,
            'comment_count': comment_count,
            'formats': formats,
            'age_limit': 18,
        }


class PornHubPlaylistIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?pornhub\.com/playlist/(?P<id>\d+)'
    _TESTS = [{
        'url': 'http://www.pornhub.com/playlist/6201671',
        'info_dict': {
            'id': '6201671',
            'title': 'P0p4',
        },
        'playlist_mincount': 35,
    }]

    def _real_extract(self, url):
        playlist_id = self._match_id(url)

        webpage = self._download_webpage(url, playlist_id)

        entries = [
            self.url_result('http://www.pornhub.com/%s' % video_url, 'PornHub')
            for video_url in set(re.findall('href="/?(view_video\.php\?viewkey=\d+[^"]*)"', webpage))
        ]

        playlist = self._parse_json(
            self._search_regex(
                r'playlistObject\s*=\s*({.+?});', webpage, 'playlist'),
            playlist_id)

        return self.playlist_result(
            entries, playlist_id, playlist.get('title'), playlist.get('description'))