yt_dlp/extractor/storyfire.py

   1 import functools
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     OnDemandPagedList,
   6     format_field,
   7     int_or_none,
   8     smuggle_url,
   9 )
  10
  11
  12 class StoryFireBaseIE(InfoExtractor):
  13     _VALID_URL_BASE = r'https?://(?:www\.)?storyfire\.com/'
  14
  15     def _call_api(self, path, video_id, resource, query=None):
  16         return self._download_json(
  17             f'https://storyfire.com/app/{path}/{video_id}', video_id,
  18             f'Downloading {resource} JSON metadata', query=query)
  19
  20     def _parse_video(self, video):
  21         title = video['title']
  22         vimeo_id = self._search_regex(
  23             r'https?://player\.vimeo\.com/external/(\d+)',
  24             video['vimeoVideoURL'], 'vimeo id')
  25
  26         uploader_id = video.get('hostID')
  27
  28         return {
  29             '_type': 'url_transparent',
  30             'id': vimeo_id,
  31             'title': title,
  32             'description': video.get('description'),
  33             'url': smuggle_url(
  34                 'https://player.vimeo.com/video/' + vimeo_id, {
  35                     'referer': 'https://storyfire.com/',
  36                 }),
  37             'thumbnail': video.get('storyImage'),
  38             'view_count': int_or_none(video.get('views')),
  39             'like_count': int_or_none(video.get('likesCount')),
  40             'comment_count': int_or_none(video.get('commentsCount')),
  41             'duration': int_or_none(video.get('videoDuration')),
  42             'timestamp': int_or_none(video.get('publishDate')),
  43             'uploader': video.get('username'),
  44             'uploader_id': uploader_id,
  45             'uploader_url': format_field(uploader_id, None, 'https://storyfire.com/user/%s/video'),
  46             'episode_number': int_or_none(video.get('episodeNumber') or video.get('episode_number')),
  47         }
  48
  49
  50 class StoryFireIE(StoryFireBaseIE):
  51     _VALID_URL = StoryFireBaseIE._VALID_URL_BASE + r'video-details/(?P<id>[0-9a-f]{24})'
  52     _TEST = {
  53         'url': 'https://storyfire.com/video-details/5df1d132b6378700117f9181',
  54         'md5': 'caec54b9e4621186d6079c7ec100c1eb',
  55         'info_dict': {
  56             'id': '378954662',
  57             'ext': 'mp4',
  58             'title': 'Buzzfeed Teaches You About Memes',
  59             'uploader_id': 'ntZAJFECERSgqHSxzonV5K2E89s1',
  60             'timestamp': 1576129028,
  61             'description': 'md5:0b4e28021548e144bed69bb7539e62ea',
  62             'uploader': 'whang!',
  63             'upload_date': '20191212',
  64             'duration': 418,
  65             'view_count': int,
  66             'like_count': int,
  67             'comment_count': int,
  68         },
  69         'params': {
  70             'skip_download': True,
  71         },
  72         'expected_warnings': ['Unable to download JSON metadata'],
  73     }
  74
  75     def _real_extract(self, url):
  76         video_id = self._match_id(url)
  77         video = self._call_api(
  78             'generic/video-detail', video_id, 'video')['video']
  79         return self._parse_video(video)
  80
  81
  82 class StoryFireUserIE(StoryFireBaseIE):
  83     _VALID_URL = StoryFireBaseIE._VALID_URL_BASE + r'user/(?P<id>[^/]+)/video'
  84     _TEST = {
  85         'url': 'https://storyfire.com/user/UQ986nFxmAWIgnkZQ0ftVhq4nOk2/video',
  86         'info_dict': {
  87             'id': 'UQ986nFxmAWIgnkZQ0ftVhq4nOk2',
  88         },
  89         'playlist_mincount': 151,
  90     }
  91     _PAGE_SIZE = 20
  92
  93     def _fetch_page(self, user_id, page):
  94         videos = self._call_api(
  95             'publicVideos', user_id, f'page {page + 1}', {
  96                 'skip': page * self._PAGE_SIZE,
  97             })['videos']
  98         for video in videos:
  99             yield self._parse_video(video)
 100
 101     def _real_extract(self, url):
 102         user_id = self._match_id(url)
 103         entries = OnDemandPagedList(functools.partial(
 104             self._fetch_page, user_id), self._PAGE_SIZE)
 105         return self.playlist_result(entries, user_id)
 106
 107
 108 class StoryFireSeriesIE(StoryFireBaseIE):
 109     _VALID_URL = StoryFireBaseIE._VALID_URL_BASE + r'write/series/stories/(?P<id>[^/?&#]+)'
 110     _TESTS = [{
 111         'url': 'https://storyfire.com/write/series/stories/-Lq6MsuIHLODO6d2dDkr/',
 112         'info_dict': {
 113             'id': '-Lq6MsuIHLODO6d2dDkr',
 114         },
 115         'playlist_mincount': 13,
 116     }, {
 117         'url': 'https://storyfire.com/write/series/stories/the_mortal_one/',
 118         'info_dict': {
 119             'id': 'the_mortal_one',
 120         },
 121         'playlist_count': 0,
 122     }]
 123
 124     def _extract_videos(self, stories):
 125         for story in stories.values():
 126             if story.get('hasVideo'):
 127                 yield self._parse_video(story)
 128
 129     def _real_extract(self, url):
 130         series_id = self._match_id(url)
 131         stories = self._call_api(
 132             'seriesStories', series_id, 'series stories')
 133         return self.playlist_result(self._extract_videos(stories), series_id)