aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/tiktok.py
blob: ea1beb8af7dfa2cd44057c0be88960819435095d (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
# coding: utf-8
from __future__ import unicode_literals

from .common import InfoExtractor
from ..utils import (
    compat_str,
    ExtractorError,
    float_or_none,
    int_or_none,
    str_or_none,
    try_get,
    url_or_none,
)


class TikTokBaseIE(InfoExtractor):
    def _extract_video(self, data, video_id=None):
        video = data['video']
        description = str_or_none(try_get(data, lambda x: x['desc']))
        width = int_or_none(try_get(data, lambda x: video['width']))
        height = int_or_none(try_get(data, lambda x: video['height']))

        format_urls = set()
        formats = []
        for format_id in ('download', 'play'):
            format_url = url_or_none(video.get('%sAddr' % format_id))
            if not format_url:
                continue
            if format_url in format_urls:
                continue
            format_urls.add(format_url)
            formats.append({
                'url': format_url,
                'ext': 'mp4',
                'height': height,
                'width': width,
                'http_headers': {
                    'Referer': 'https://www.tiktok.com/',
                }
            })
        self._sort_formats(formats)

        thumbnail = url_or_none(video.get('cover'))
        duration = float_or_none(video.get('duration'))

        uploader = try_get(data, lambda x: x['author']['nickname'], compat_str)
        uploader_id = try_get(data, lambda x: x['author']['id'], compat_str)

        timestamp = int_or_none(data.get('createTime'))

        def stats(key):
            return int_or_none(try_get(
                data, lambda x: x['stats']['%sCount' % key]))

        view_count = stats('play')
        like_count = stats('digg')
        comment_count = stats('comment')
        repost_count = stats('share')

        aweme_id = data.get('id') or video_id

        return {
            'id': aweme_id,
            'title': uploader or aweme_id,
            'description': description,
            'thumbnail': thumbnail,
            'duration': duration,
            'uploader': uploader,
            'uploader_id': uploader_id,
            'timestamp': timestamp,
            'view_count': view_count,
            'like_count': like_count,
            'comment_count': comment_count,
            'repost_count': repost_count,
            'formats': formats,
        }


class TikTokIE(TikTokBaseIE):
    _VALID_URL = r'https?://(?:www\.)?tiktok\.com/@[^/]+/video/(?P<id>\d+)'
    _TESTS = [{
        'url': 'https://www.tiktok.com/@zureeal/video/6606727368545406213',
        'md5': '163ceff303bb52de60e6887fe399e6cd',
        'info_dict': {
            'id': '6606727368545406213',
            'ext': 'mp4',
            'title': 'Zureeal',
            'description': '#bowsette#mario#cosplay#uk#lgbt#gaming#asian#bowsettecosplay',
            'thumbnail': r're:^https?://.*',
            'duration': 15,
            'uploader': 'Zureeal',
            'uploader_id': '188294915489964032',
            'timestamp': 1538248586,
            'upload_date': '20180929',
            'view_count': int,
            'like_count': int,
            'comment_count': int,
            'repost_count': int,
        }
    }]

    def _real_initialize(self):
        # Setup session (will set necessary cookies)
        self._request_webpage(
            'https://www.tiktok.com/', None, note='Setting up session')

    def _real_extract(self, url):
        video_id = self._match_id(url)
        webpage = self._download_webpage(url, video_id)
        data = self._parse_json(self._search_regex(
            r'<script[^>]+\bid=["\']__NEXT_DATA__[^>]+>\s*({.+?})\s*</script',
            webpage, 'data'), video_id)['props']['pageProps']['itemInfo']['itemStruct']
        return self._extract_video(data, video_id)


class TikTokUserIE(TikTokBaseIE):
    _VALID_URL = r'https://(?:www\.)?tiktok\.com/@(?P<id>[^/?#&]+)'
    _TESTS = [{
        'url': 'https://www.tiktok.com/@zureeal',
        'info_dict': {
            'id': '188294915489964032',
        },
        'playlist_mincount': 24,
    }]
    _WORKING = False

    @classmethod
    def suitable(cls, url):
        return False if TikTokIE.suitable(url) else super(TikTokUserIE, cls).suitable(url)

    def _real_extract(self, url):
        user_id = self._match_id(url)
        data = self._download_json(
            'https://m.tiktok.com/h5/share/usr/list/%s/' % user_id, user_id,
            query={'_signature': '_'})
        entries = []
        for aweme in data['aweme_list']:
            try:
                entry = self._extract_video(aweme)
            except ExtractorError:
                continue
            entry['extractor_key'] = TikTokIE.ie_key()
            entries.append(entry)
        return self.playlist_result(entries, user_id)