summaryrefslogtreecommitdiffstats
path: root/yt_dlp/extractor/storyfire.py
blob: 566f777827341a08feaf39106d53f9688d50982e (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
import functools

from .common import InfoExtractor
from ..utils import (
    format_field,
    int_or_none,
    OnDemandPagedList,
    smuggle_url,
)


class StoryFireBaseIE(InfoExtractor):
    _VALID_URL_BASE = r'https?://(?:www\.)?storyfire\.com/'

    def _call_api(self, path, video_id, resource, query=None):
        return self._download_json(
            'https://storyfire.com/app/%s/%s' % (path, video_id), video_id,
            'Downloading %s JSON metadata' % resource, query=query)

    def _parse_video(self, video):
        title = video['title']
        vimeo_id = self._search_regex(
            r'https?://player\.vimeo\.com/external/(\d+)',
            video['vimeoVideoURL'], 'vimeo id')

        uploader_id = video.get('hostID')

        return {
            '_type': 'url_transparent',
            'id': vimeo_id,
            'title': title,
            'description': video.get('description'),
            'url': smuggle_url(
                'https://player.vimeo.com/video/' + vimeo_id, {
                    'referer': 'https://storyfire.com/',
                }),
            'thumbnail': video.get('storyImage'),
            'view_count': int_or_none(video.get('views')),
            'like_count': int_or_none(video.get('likesCount')),
            'comment_count': int_or_none(video.get('commentsCount')),
            'duration': int_or_none(video.get('videoDuration')),
            'timestamp': int_or_none(video.get('publishDate')),
            'uploader': video.get('username'),
            'uploader_id': uploader_id,
            'uploader_url': format_field(uploader_id, None, 'https://storyfire.com/user/%s/video'),
            'episode_number': int_or_none(video.get('episodeNumber') or video.get('episode_number')),
        }


class StoryFireIE(StoryFireBaseIE):
    _VALID_URL = StoryFireBaseIE._VALID_URL_BASE + r'video-details/(?P<id>[0-9a-f]{24})'
    _TEST = {
        'url': 'https://storyfire.com/video-details/5df1d132b6378700117f9181',
        'md5': 'caec54b9e4621186d6079c7ec100c1eb',
        'info_dict': {
            'id': '378954662',
            'ext': 'mp4',
            'title': 'Buzzfeed Teaches You About Memes',
            'uploader_id': 'ntZAJFECERSgqHSxzonV5K2E89s1',
            'timestamp': 1576129028,
            'description': 'md5:0b4e28021548e144bed69bb7539e62ea',
            'uploader': 'whang!',
            'upload_date': '20191212',
            'duration': 418,
            'view_count': int,
            'like_count': int,
            'comment_count': int,
        },
        'params': {
            'skip_download': True,
        },
        'expected_warnings': ['Unable to download JSON metadata']
    }

    def _real_extract(self, url):
        video_id = self._match_id(url)
        video = self._call_api(
            'generic/video-detail', video_id, 'video')['video']
        return self._parse_video(video)


class StoryFireUserIE(StoryFireBaseIE):
    _VALID_URL = StoryFireBaseIE._VALID_URL_BASE + r'user/(?P<id>[^/]+)/video'
    _TEST = {
        'url': 'https://storyfire.com/user/UQ986nFxmAWIgnkZQ0ftVhq4nOk2/video',
        'info_dict': {
            'id': 'UQ986nFxmAWIgnkZQ0ftVhq4nOk2',
        },
        'playlist_mincount': 151,
    }
    _PAGE_SIZE = 20

    def _fetch_page(self, user_id, page):
        videos = self._call_api(
            'publicVideos', user_id, 'page %d' % (page + 1), {
                'skip': page * self._PAGE_SIZE,
            })['videos']
        for video in videos:
            yield self._parse_video(video)

    def _real_extract(self, url):
        user_id = self._match_id(url)
        entries = OnDemandPagedList(functools.partial(
            self._fetch_page, user_id), self._PAGE_SIZE)
        return self.playlist_result(entries, user_id)


class StoryFireSeriesIE(StoryFireBaseIE):
    _VALID_URL = StoryFireBaseIE._VALID_URL_BASE + r'write/series/stories/(?P<id>[^/?&#]+)'
    _TESTS = [{
        'url': 'https://storyfire.com/write/series/stories/-Lq6MsuIHLODO6d2dDkr/',
        'info_dict': {
            'id': '-Lq6MsuIHLODO6d2dDkr',
        },
        'playlist_mincount': 13,
    }, {
        'url': 'https://storyfire.com/write/series/stories/the_mortal_one/',
        'info_dict': {
            'id': 'the_mortal_one',
        },
        'playlist_count': 0,
    }]

    def _extract_videos(self, stories):
        for story in stories.values():
            if story.get('hasVideo'):
                yield self._parse_video(story)

    def _real_extract(self, url):
        series_id = self._match_id(url)
        stories = self._call_api(
            'seriesStories', series_id, 'series stories')
        return self.playlist_result(self._extract_videos(stories), series_id)