youtube_dlc/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     # HEADRequest,
   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         # video_url = self._request_webpage(
  30         #    HEADRequest(video['vimeoVideoURL']), video_id).geturl()
  31         # formats = []
  32         # for v_url, suffix in [(video_url, '_sep'), (video_url.replace('/sep/video/', '/video/'), '')]:
  33         #    formats.extend(self._extract_m3u8_formats(
  34         #        v_url, video_id, 'mp4', 'm3u8_native',
  35         #        m3u8_id='hls' + suffix, fatal=False))
  36         #    formats.extend(self._extract_mpd_formats(
  37         #        v_url.replace('.m3u8', '.mpd'), video_id,
  38         #        mpd_id='dash' + suffix, fatal=False))
  39         # self._sort_formats(formats)
  40
  41         uploader_id = video.get('hostID')
  42
  43         return {
  44             '_type': 'url_transparent',
  45             'id': vimeo_id,
  46             'title': title,
  47             'description': video.get('description'),
  48             'url': smuggle_url(
  49                 'https://player.vimeo.com/video/' + vimeo_id, {
  50                     'http_headers': {
  51                         'Referer': 'https://storyfire.com/',
  52                     }
  53                 }),
  54             # 'formats': formats,
  55             'thumbnail': video.get('storyImage'),
  56             'view_count': int_or_none(video.get('views')),
  57             'like_count': int_or_none(video.get('likesCount')),
  58             'comment_count': int_or_none(video.get('commentsCount')),
  59             'duration': int_or_none(video.get('videoDuration')),
  60             'timestamp': int_or_none(video.get('publishDate')),
  61             'uploader': video.get('username'),
  62             'uploader_id': uploader_id,
  63             'uploader_url': 'https://storyfire.com/user/%s/video' % uploader_id if uploader_id else None,
  64             'episode_number': int_or_none(video.get('episodeNumber') or video.get('episode_number')),
  65         }
  66
  67
  68 class StoryFireIE(StoryFireBaseIE):
  69     _VALID_URL = StoryFireBaseIE._VALID_URL_BASE + r'video-details/(?P<id>[0-9a-f]{24})'
  70     _TEST = {
  71         'url': 'https://storyfire.com/video-details/5df1d132b6378700117f9181',
  72         'md5': 'caec54b9e4621186d6079c7ec100c1eb',
  73         'info_dict': {
  74             'id': '378954662',
  75             'ext': 'mp4',
  76             'title': 'Buzzfeed Teaches You About Memes',
  77             'uploader_id': 'ntZAJFECERSgqHSxzonV5K2E89s1',
  78             'timestamp': 1576129028,
  79             'description': 'md5:0b4e28021548e144bed69bb7539e62ea',
  80             'uploader': 'whang!',
  81             'upload_date': '20191212',
  82             'duration': 418,
  83             'view_count': int,
  84             'like_count': int,
  85             'comment_count': int,
  86         },
  87         'params': {
  88             'skip_download': True,
  89         },
  90         'expected_warnings': ['Unable to download JSON metadata']
  91     }
  92
  93     def _real_extract(self, url):
  94         video_id = self._match_id(url)
  95         video = self._call_api(
  96             'generic/video-detail', video_id, 'video')['video']
  97         return self._parse_video(video)
  98
  99
 100 class StoryFireUserIE(StoryFireBaseIE):
 101     _VALID_URL = StoryFireBaseIE._VALID_URL_BASE + r'user/(?P<id>[^/]+)/video'
 102     _TEST = {
 103         'url': 'https://storyfire.com/user/UQ986nFxmAWIgnkZQ0ftVhq4nOk2/video',
 104         'info_dict': {
 105             'id': 'UQ986nFxmAWIgnkZQ0ftVhq4nOk2',
 106         },
 107         'playlist_mincount': 151,
 108     }
 109     _PAGE_SIZE = 20
 110
 111     def _fetch_page(self, user_id, page):
 112         videos = self._call_api(
 113             'publicVideos', user_id, 'page %d' % (page + 1), {
 114                 'skip': page * self._PAGE_SIZE,
 115             })['videos']
 116         for video in videos:
 117             yield self._parse_video(video)
 118
 119     def _real_extract(self, url):
 120         user_id = self._match_id(url)
 121         entries = OnDemandPagedList(functools.partial(
 122             self._fetch_page, user_id), self._PAGE_SIZE)
 123         return self.playlist_result(entries, user_id)
 124
 125
 126 class StoryFireSeriesIE(StoryFireBaseIE):
 127     _VALID_URL = StoryFireBaseIE._VALID_URL_BASE + r'write/series/stories/(?P<id>[^/?&#]+)'
 128     _TESTS = [{
 129         'url': 'https://storyfire.com/write/series/stories/-Lq6MsuIHLODO6d2dDkr/',
 130         'info_dict': {
 131             'id': '-Lq6MsuIHLODO6d2dDkr',
 132         },
 133         'playlist_mincount': 13,
 134     }, {
 135         'url': 'https://storyfire.com/write/series/stories/the_mortal_one/',
 136         'info_dict': {
 137             'id': 'the_mortal_one',
 138         },
 139         'playlist_count': 0,
 140     }]
 141
 142     def _extract_videos(self, stories):
 143         for story in stories.values():
 144             if story.get('hasVideo'):
 145                 yield self._parse_video(story)
 146
 147     def _real_extract(self, url):
 148         series_id = self._match_id(url)
 149         stories = self._call_api(
 150             'seriesStories', series_id, 'series stories')
 151         return self.playlist_result(self._extract_videos(stories), series_id)