summaryrefslogtreecommitdiffstats
path: root/yt_dlp/extractor/eroprofile.py
blob: 2067217e7c95516ee16d4280512feb9eaf9ba62c (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
import re
import urllib.parse

from .common import InfoExtractor
from ..utils import (
    ExtractorError,
    merge_dicts,
)


class EroProfileIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?eroprofile\.com/m/videos/view/(?P<id>[^/]+)'
    _LOGIN_URL = 'http://www.eroprofile.com/auth/auth.php?'
    _NETRC_MACHINE = 'eroprofile'
    _TESTS = [{
        'url': 'http://www.eroprofile.com/m/videos/view/sexy-babe-softcore',
        'md5': 'c26f351332edf23e1ea28ce9ec9de32f',
        'info_dict': {
            'id': '3733775',
            'display_id': 'sexy-babe-softcore',
            'ext': 'm4v',
            'title': 'sexy babe softcore',
            'thumbnail': r're:https?://.*\.jpg',
            'age_limit': 18,
        },
        'skip': 'Video not found',
    }, {
        'url': 'http://www.eroprofile.com/m/videos/view/Try-It-On-Pee_cut_2-wmv-4shared-com-file-sharing-download-movie-file',
        'md5': '1baa9602ede46ce904c431f5418d8916',
        'info_dict': {
            'id': '1133519',
            'ext': 'm4v',
            'title': 'Try It On Pee_cut_2.wmv - 4shared.com - file sharing - download movie file',
            'thumbnail': r're:https?://.*\.jpg',
            'age_limit': 18,
        },
        'skip': 'Requires login',
    }]

    def _perform_login(self, username, password):
        query = urllib.parse.urlencode({
            'username': username,
            'password': password,
            'url': 'http://www.eroprofile.com/',
        })
        login_url = self._LOGIN_URL + query
        login_page = self._download_webpage(login_url, None, False)

        m = re.search(r'Your username or password was incorrect\.', login_page)
        if m:
            raise ExtractorError(
                'Wrong username and/or password.', expected=True)

        self.report_login()
        redirect_url = self._search_regex(
            r'<script[^>]+?src="([^"]+)"', login_page, 'login redirect url')
        self._download_webpage(redirect_url, None, False)

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

        webpage = self._download_webpage(url, display_id)

        m = re.search(r'You must be logged in to view this video\.', webpage)
        if m:
            self.raise_login_required('This video requires login')

        video_id = self._search_regex(
            [r"glbUpdViews\s*\('\d*','(\d+)'", r'p/report/video/(\d+)'],
            webpage, 'video id', default=None)

        title = self._html_search_regex(
            (r'Title:</th><td>([^<]+)</td>', r'<h1[^>]*>(.+?)</h1>'),
            webpage, 'title')

        info = self._parse_html5_media_entries(url, webpage, video_id)[0]

        return merge_dicts(info, {
            'id': video_id,
            'display_id': display_id,
            'title': title,
            'age_limit': 18,
        })


class EroProfileAlbumIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?eroprofile\.com/m/videos/album/(?P<id>[^/]+)'
    IE_NAME = 'EroProfile:album'

    _TESTS = [{
        'url': 'https://www.eroprofile.com/m/videos/album/BBW-2-893',
        'info_dict': {
            'id': 'BBW-2-893',
            'title': 'BBW 2',
        },
        'playlist_mincount': 486,
    },
    ]

    def _extract_from_page(self, page):
        for url in re.findall(r'href=".*?(/m/videos/view/[^"]+)"', page):
            yield self.url_result(f'https://www.eroprofile.com{url}', EroProfileIE.ie_key())

    def _entries(self, playlist_id, first_page):
        yield from self._extract_from_page(first_page)

        page_urls = re.findall(rf'href=".*?(/m/videos/album/{playlist_id}\?pnum=(\d+))"', first_page)
        max_page = max(int(n) for _, n in page_urls)

        for n in range(2, max_page + 1):
            url = f'https://www.eroprofile.com/m/videos/album/{playlist_id}?pnum={n}'
            yield from self._extract_from_page(
                self._download_webpage(url, playlist_id,
                                       note=f'Downloading playlist page {int(n) - 1}'))

    def _real_extract(self, url):
        playlist_id = self._match_id(url)
        first_page = self._download_webpage(url, playlist_id, note='Downloading playlist')
        playlist_title = self._search_regex(
            r'<title>Album: (.*) - EroProfile</title>', first_page, 'playlist_title')

        return self.playlist_result(self._entries(playlist_id, first_page), playlist_id, playlist_title)