aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/vidme.py
blob: eb5cde761af54d0d33b6ca99e746963afbc756de (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
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
from __future__ import unicode_literals

from .common import InfoExtractor
from ..compat import compat_HTTPError
from ..utils import (
    ExtractorError,
    int_or_none,
    float_or_none,
    parse_iso8601,
)


class VidmeIE(InfoExtractor):
    _VALID_URL = r'https?://vid\.me/(?:e/)?(?P<id>[\da-zA-Z]+)'
    _TESTS = [{
        'url': 'https://vid.me/QNB',
        'md5': 'f42d05e7149aeaec5c037b17e5d3dc82',
        'info_dict': {
            'id': 'QNB',
            'ext': 'mp4',
            'title': 'Fishing for piranha - the easy way',
            'description': 'source: https://www.facebook.com/photo.php?v=312276045600871',
            'thumbnail': 're:^https?://.*\.jpg',
            'timestamp': 1406313244,
            'upload_date': '20140725',
            'age_limit': 0,
            'duration': 119.92,
            'view_count': int,
            'like_count': int,
            'comment_count': int,
        },
    }, {
        'url': 'https://vid.me/Gc6M',
        'md5': 'f42d05e7149aeaec5c037b17e5d3dc82',
        'info_dict': {
            'id': 'Gc6M',
            'ext': 'mp4',
            'title': 'O Mere Dil ke chain - Arnav and Khushi VM',
            'thumbnail': 're:^https?://.*\.jpg',
            'timestamp': 1441211642,
            'upload_date': '20150902',
            'uploader': 'SunshineM',
            'uploader_id': '3552827',
            'age_limit': 0,
            'duration': 223.72,
            'view_count': int,
            'like_count': int,
            'comment_count': int,
        },
        'params': {
            'skip_download': True,
        },
    }, {
        # tests uploader field
        'url': 'https://vid.me/4Iib',
        'info_dict': {
            'id': '4Iib',
            'ext': 'mp4',
            'title': 'The Carver',
            'description': 'md5:e9c24870018ae8113be936645b93ba3c',
            'thumbnail': 're:^https?://.*\.jpg',
            'timestamp': 1433203629,
            'upload_date': '20150602',
            'uploader': 'Thomas',
            'uploader_id': '109747',
            'age_limit': 0,
            'duration': 97.859999999999999,
            'view_count': int,
            'like_count': int,
            'comment_count': int,
        },
        'params': {
            'skip_download': True,
        },
    }, {
        # nsfw test from http://naked-yogi.tumblr.com/post/118312946248/naked-smoking-stretching
        'url': 'https://vid.me/e/Wmur',
        'info_dict': {
            'id': 'Wmur',
            'ext': 'mp4',
            'title': 'naked smoking & stretching',
            'thumbnail': 're:^https?://.*\.jpg',
            'timestamp': 1430931613,
            'upload_date': '20150506',
            'uploader': 'naked-yogi',
            'uploader_id': '1638622',
            'age_limit': 18,
            'duration': 653.26999999999998,
            'view_count': int,
            'like_count': int,
            'comment_count': int,
        },
        'params': {
            'skip_download': True,
        },
    }, {
        # nsfw, user-disabled
        'url': 'https://vid.me/dzGJ',
        'only_matching': True,
    }, {
        # suspended
        'url': 'https://vid.me/Ox3G',
        'only_matching': True,
    }, {
        # no formats in the API response
        'url': 'https://vid.me/e5g',
        'info_dict': {
            'id': 'e5g',
            'ext': 'mp4',
            'title': 'Video upload (e5g)',
            'thumbnail': 're:^https?://.*\.jpg',
            'timestamp': 1401480195,
            'upload_date': '20140530',
            'uploader': None,
            'uploader_id': None,
            'age_limit': 0,
            'duration': 483,
            'view_count': int,
            'like_count': int,
            'comment_count': int,
        },
        'params': {
            'skip_download': True,
        },
    }]

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

        try:
            response = self._download_json(
                'https://api.vid.me/videoByUrl/%s' % video_id, video_id)
        except ExtractorError as e:
            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400:
                response = self._parse_json(e.cause.read(), video_id)
            else:
                raise

        error = response.get('error')
        if error:
            raise ExtractorError(
                '%s returned error: %s' % (self.IE_NAME, error), expected=True)

        video = response['video']

        if video.get('state') in ('user-disabled', 'suspended'):
            raise ExtractorError(
                'Vidme said: This video has been suspended either due to a copyright claim, '
                'or for violating the terms of use.',
                expected=True)

        formats = [{
            'format_id': f.get('type'),
            'url': f['uri'],
            'width': int_or_none(f.get('width')),
            'height': int_or_none(f.get('height')),
            'preference': 0 if f.get('type', '').endswith('clip') else 1,
        } for f in video.get('formats', []) if f.get('uri')]

        if not formats and video.get('complete_url'):
            formats.append({
                'url': video.get('complete_url'),
                'width': int_or_none(video.get('width')),
                'height': int_or_none(video.get('height')),
            })

        self._sort_formats(formats)

        title = video['title']
        description = video.get('description')
        thumbnail = video.get('thumbnail_url')
        timestamp = parse_iso8601(video.get('date_created'), ' ')
        uploader = video.get('user', {}).get('username')
        uploader_id = video.get('user', {}).get('user_id')
        age_limit = 18 if video.get('nsfw') is True else 0
        duration = float_or_none(video.get('duration'))
        view_count = int_or_none(video.get('view_count'))
        like_count = int_or_none(video.get('likes_count'))
        comment_count = int_or_none(video.get('comment_count'))

        return {
            'id': video_id,
            'title': title or 'Video upload (%s)' % video_id,
            'description': description,
            'thumbnail': thumbnail,
            'uploader': uploader,
            'uploader_id': uploader_id,
            'age_limit': age_limit,
            'timestamp': timestamp,
            'duration': duration,
            'view_count': view_count,
            'like_count': like_count,
            'comment_count': comment_count,
            'formats': formats,
        }