aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/shared.py
blob: 02295d1a4cacf570ee903c06161b072f35a6da77 (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
from __future__ import unicode_literals

from .common import InfoExtractor
from ..compat import (
    compat_b64decode,
    compat_urllib_parse_unquote_plus,
)
from ..utils import (
    determine_ext,
    ExtractorError,
    int_or_none,
    js_to_json,
    KNOWN_EXTENSIONS,
    parse_filesize,
    rot47,
    url_or_none,
    urlencode_postdata,
)


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

        webpage, urlh = self._download_webpage_handle(url, video_id)

        if self._FILE_NOT_FOUND in webpage:
            raise ExtractorError(
                'Video %s does not exist' % video_id, expected=True)

        video_url = self._extract_video_url(webpage, video_id, url)

        title = self._extract_title(webpage)
        filesize = int_or_none(self._extract_filesize(webpage))

        return {
            'id': video_id,
            'url': video_url,
            'ext': 'mp4',
            'filesize': filesize,
            'title': title,
        }

    def _extract_title(self, webpage):
        return compat_b64decode(self._html_search_meta(
            'full:title', webpage, 'title')).decode('utf-8')

    def _extract_filesize(self, webpage):
        return self._html_search_meta(
            'full:size', webpage, 'file size', fatal=False)


class SharedIE(SharedBaseIE):
    IE_DESC = 'shared.sx'
    _VALID_URL = r'https?://shared\.sx/(?P<id>[\da-z]{10})'
    _FILE_NOT_FOUND = '>File does not exist<'

    _TEST = {
        'url': 'http://shared.sx/0060718775',
        'md5': '106fefed92a8a2adb8c98e6a0652f49b',
        'info_dict': {
            'id': '0060718775',
            'ext': 'mp4',
            'title': 'Bmp4',
            'filesize': 1720110,
        },
    }

    def _extract_video_url(self, webpage, video_id, url):
        download_form = self._hidden_inputs(webpage)

        video_page = self._download_webpage(
            url, video_id, 'Downloading video page',
            data=urlencode_postdata(download_form),
            headers={
                'Content-Type': 'application/x-www-form-urlencoded',
                'Referer': url,
            })

        video_url = self._html_search_regex(
            r'data-url=(["\'])(?P<url>(?:(?!\1).)+)\1',
            video_page, 'video URL', group='url')

        return video_url


class VivoIE(SharedBaseIE):
    IE_DESC = 'vivo.sx'
    _VALID_URL = r'https?://vivo\.sx/(?P<id>[\da-z]{10})'
    _FILE_NOT_FOUND = '>The file you have requested does not exists or has been removed'

    _TEST = {
        'url': 'http://vivo.sx/d7ddda0e78',
        'md5': '15b3af41be0b4fe01f4df075c2678b2c',
        'info_dict': {
            'id': 'd7ddda0e78',
            'ext': 'mp4',
            'title': 'Chicken',
            'filesize': 515659,
        },
    }

    def _extract_title(self, webpage):
        title = self._html_search_regex(
            r'data-name\s*=\s*(["\'])(?P<title>(?:(?!\1).)+)\1', webpage,
            'title', default=None, group='title')
        if title:
            ext = determine_ext(title)
            if ext.lower() in KNOWN_EXTENSIONS:
                title = title.rpartition('.' + ext)[0]
            return title
        return self._og_search_title(webpage)

    def _extract_filesize(self, webpage):
        return parse_filesize(self._search_regex(
            r'data-type=["\']video["\'][^>]*>Watch.*?<strong>\s*\((.+?)\)',
            webpage, 'filesize', fatal=False))

    def _extract_video_url(self, webpage, video_id, url):
        def decode_url_old(encoded_url):
            return compat_b64decode(encoded_url).decode('utf-8')

        stream_url = self._search_regex(
            r'data-stream\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
            'stream url', default=None, group='url')
        if stream_url:
            stream_url = url_or_none(decode_url_old(stream_url))
        if stream_url:
            return stream_url

        def decode_url(encoded_url):
            return rot47(compat_urllib_parse_unquote_plus(encoded_url))

        return decode_url(self._parse_json(
            self._search_regex(
                r'(?s)InitializeStream\s*\(\s*({.+?})\s*\)\s*;', webpage,
                'stream'),
            video_id, transform_source=js_to_json)['source'])