aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/vine.py
blob: be72f3147d5be525c25fe53063df43b337510ae4 (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
# coding: utf-8
from __future__ import unicode_literals

import re
import itertools

from .common import InfoExtractor
from ..utils import (
    int_or_none,
    unified_strdate,
)


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 Dorsey',
            'upload_date': '20130519',
            'uploader': 'Jack Dorsey',
            'uploader_id': '76',
            'like_count': int,
            'comment_count': int,
            'repost_count': int,
        },
    }, {
        'url': 'https://vine.co/v/MYxVapFvz2z',
        'md5': '7b9a7cbc76734424ff942eb52c8f1065',
        'info_dict': {
            'id': 'MYxVapFvz2z',
            'ext': 'mp4',
            'title': 'Fuck Da Police #Mikebrown #justice #ferguson #prayforferguson #protesting #NMOS14',
            'alt_title': 'Vine by Mars Ruiz',
            'upload_date': '20140815',
            'uploader': 'Mars Ruiz',
            'uploader_id': '1102363502380728320',
            'like_count': int,
            'comment_count': int,
            'repost_count': int,
        },
    }, {
        'url': 'https://vine.co/v/bxVjBbZlPUH',
        'md5': 'ea27decea3fa670625aac92771a96b73',
        'info_dict': {
            'id': 'bxVjBbZlPUH',
            'ext': 'mp4',
            'title': '#mw3 #ac130 #killcam #angelofdeath',
            'alt_title': 'Vine by Z3k3',
            'upload_date': '20130430',
            'uploader': 'Z3k3',
            'uploader_id': '936470460173008896',
            'like_count': int,
            'comment_count': int,
            'repost_count': int,
        },
    }, {
        'url': 'https://vine.co/oembed/MYxVapFvz2z.json',
        'only_matching': True,
    }, {
        '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',
            'upload_date': '20150705',
            'uploader': 'Pimry_zaa',
            'uploader_id': '1135760698325307392',
            'like_count': int,
            'comment_count': int,
            'repost_count': int,
        },
        'params': {
            'skip_download': True,
        },
    }]

    def _real_extract(self, url):
        video_id = self._match_id(url)
        webpage = self._download_webpage('https://vine.co/v/' + video_id, video_id)

        data = self._parse_json(
            self._html_search_regex(
                r'window\.POST_DATA = { %s: ({.+?}) };\s*</script>' % video_id,
                webpage, 'vine data'),
            video_id)

        formats = [{
            'format_id': '%(format)s-%(rate)s' % f,
            'vcodec': f.get('format'),
            'quality': f.get('rate'),
            'url': f['videoUrl'],
        } for f in data['videoUrls'] if f.get('videoUrl')]

        self._sort_formats(formats)

        username = data.get('username')

        return {
            'id': video_id,
            'title': data.get('description') or self._og_search_title(webpage),
            'alt_title': 'Vine by %s' % username if username else self._og_search_description(webpage, default=None),
            'thumbnail': data.get('thumbnailUrl'),
            'upload_date': unified_strdate(data.get('created')),
            'uploader': username,
            'uploader_id': data.get('userIdStr'),
            'like_count': int_or_none(data.get('likes', {}).get('count')),
            'comment_count': int_or_none(data.get('comments', {}).get('count')),
            'repost_count': int_or_none(data.get('reposts', {}).get('count')),
            '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)