yt_dlp/extractor/storyfire.py

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