aboutsummaryrefslogtreecommitdiffstats
path: root/youtube_dl/extractor/vine.py
blob: 4957a07f7bde0797f1f8b6f4c4ef9297f8e915e3 (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
# coding: utf-8
from __future__ import unicode_literals

import re
import itertools

from .common import InfoExtractor
from ..utils import (
    determine_ext,
    int_or_none,
    unified_timestamp,
)


class VineIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?vine\.co/(?:v|oembed)/(?P<id>\w+)'
    _TESTS = [{
        'url': 'https://vine.co/v/b9KOOWX7HUx',
        'md5': '2f36fed6235b16da96ce9b4dc890940d',
        'info_dict': {
            'id': 'b9KOOWX7HUx',
            'ext': 'mp4',
            'title': 'Chicken.',
            'alt_title': 'Vine by Jack',
            'timestamp': 1368997951,
            'upload_date': '20130519',
            'uploader': 'Jack',
            'uploader_id': '76',
            'view_count': int,
            'like_count': int,
            'comment_count': int,
            'repost_count': int,
        },
    }, {
        'url': 'https://vine.co/v/e192BnZnZ9V',
        'info_dict': {
            'id': 'e192BnZnZ9V',
            'ext': 'mp4',
            'title': 'ยิ้ม~ เขิน~ อาย~ น่าร้ากอ้ะ >//< @n_whitewo @orlameena #lovesicktheseries  #lovesickseason2',
            'alt_title': 'Vine by Pimry_zaa',
            'timestamp': 1436057405,
            'upload_date': '20150705',
            'uploader': 'Pimry_zaa',
            'uploader_id': '1135760698325307392',
            'view_count': int,
            'like_count': int,
            'comment_count': int,
            'repost_count': int,
        },
        'params': {
            'skip_download': True,
        },
    }, {
        'url': 'https://vine.co/v/MYxVapFvz2z',
        'only_matching': True,
    }, {
        'url': 'https://vine.co/v/bxVjBbZlPUH',
        'only_matching': True,
    }, {
        'url': 'https://vine.co/oembed/MYxVapFvz2z.json',
        'only_matching': True,
    }]

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

        data = self._download_json(
            'https://archive.vine.co/posts/%s.json' % video_id, video_id)

        def video_url(kind):
            for url_suffix in ('Url', 'URL'):
                format_url = data.get('video%s%s' % (kind, url_suffix))
                if format_url:
                    return format_url

        formats = []
        for quality, format_id in enumerate(('low', '', 'dash')):
            format_url = video_url(format_id.capitalize())
            if not format_url:
                continue
            # DASH link returns plain mp4
            if format_id == 'dash' and determine_ext(format_url) == 'mpd':
                formats.extend(self._extract_mpd_formats(
                    format_url, video_id, mpd_id='dash', fatal=False))
            else:
                formats.append({
                    'url': format_url,
                    'format_id': format_id or 'standard',
                    'quality': quality,
                })
        self._sort_formats(formats)

        username = data.get('username')

        return {
            'id': video_id,
            'title': data.get('description'),
            'alt_title': 'Vine by %s' % username if username else None,
            'thumbnail': data.get('thumbnailUrl'),
            'timestamp': unified_timestamp(data.get('created')),
            'uploader': username,
            'uploader_id': data.get('userIdStr'),
            'view_count': int_or_none(data.get('loops')),
            'like_count': int_or_none(data.get('likes')),
            'comment_count': int_or_none(data.get('comments')),
            'repost_count': int_or_none(data.get('reposts')),
            'formats': formats,
        }


class VineUserIE(InfoExtractor):
    IE_NAME = 'vine:user'
    _VALID_URL = r'(?:https?://)?vine\.co/(?P<u>u/)?(?P<user>[^/]+)/?(\?.*)?$'
    _VINE_BASE_URL = 'https://vine.co/'
    _TESTS = [
        {
            'url': 'https://vine.co/Visa',
            'info_dict': {
                'id': 'Visa',
            },
            'playlist_mincount': 46,
        },
        {
            'url': 'https://vine.co/u/941705360593584128',
            'only_matching': True,
        },
    ]

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        user = mobj.group('user')
        u = mobj.group('u')

        profile_url = '%sapi/users/profiles/%s%s' % (
            self._VINE_BASE_URL, 'vanity/' if not u else '', user)
        profile_data = self._download_json(
            profile_url, user, note='Downloading user profile data')

        user_id = profile_data['data']['userId']
        timeline_data = []
        for pagenum in itertools.count(1):
            timeline_url = '%sapi/timelines/users/%s?page=%s&size=100' % (
                self._VINE_BASE_URL, user_id, pagenum)
            timeline_page = self._download_json(
                timeline_url, user, note='Downloading page %d' % pagenum)
            timeline_data.extend(timeline_page['data']['records'])
            if timeline_page['data']['nextPage'] is None:
                break

        entries = [
            self.url_result(e['permalinkUrl'], 'Vine') for e in timeline_data]
        return self.playlist_result(entries, user)