yt_dlp/extractor/picarto.py

   1 import urllib.parse
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     ExtractorError,
   6     str_or_none,
   7     traverse_obj,
   8 )
   9
  10
  11 class PicartoIE(InfoExtractor):
  12     _VALID_URL = r'https?://(?:www.)?picarto\.tv/(?P<id>[a-zA-Z0-9]+)'
  13     _TEST = {
  14         'url': 'https://picarto.tv/Setz',
  15         'info_dict': {
  16             'id': 'Setz',
  17             'ext': 'mp4',
  18             'title': 're:^Setz [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
  19             'timestamp': int,
  20             'is_live': True,
  21         },
  22         'skip': 'Stream is offline',
  23     }
  24
  25     @classmethod
  26     def suitable(cls, url):
  27         return False if PicartoVodIE.suitable(url) else super().suitable(url)
  28
  29     def _real_extract(self, url):
  30         channel_id = self._match_id(url)
  31
  32         data = self._download_json(
  33             'https://ptvintern.picarto.tv/ptvapi', channel_id, query={
  34                 'query': '''{
  35   channel(name: "%s") {
  36     adult
  37     id
  38     online
  39     stream_name
  40     title
  41   }
  42   getLoadBalancerUrl(channel_name: "%s") {
  43     url
  44   }
  45 }''' % (channel_id, channel_id),  # noqa: UP031
  46             })['data']
  47         metadata = data['channel']
  48
  49         if metadata.get('online') == 0:
  50             raise ExtractorError('Stream is offline', expected=True)
  51         title = metadata['title']
  52
  53         cdn_data = self._download_json(
  54             data['getLoadBalancerUrl']['url'] + '/stream/json_' + metadata['stream_name'] + '.js',
  55             channel_id, 'Downloading load balancing info')
  56
  57         formats = []
  58         for source in (cdn_data.get('source') or []):
  59             source_url = source.get('url')
  60             if not source_url:
  61                 continue
  62             source_type = source.get('type')
  63             if source_type == 'html5/application/vnd.apple.mpegurl':
  64                 formats.extend(self._extract_m3u8_formats(
  65                     source_url, channel_id, 'mp4', m3u8_id='hls', fatal=False))
  66             elif source_type == 'html5/video/mp4':
  67                 formats.append({
  68                     'url': source_url,
  69                 })
  70
  71         mature = metadata.get('adult')
  72         if mature is None:
  73             age_limit = None
  74         else:
  75             age_limit = 18 if mature is True else 0
  76
  77         return {
  78             'id': channel_id,
  79             'title': title.strip(),
  80             'is_live': True,
  81             'channel': channel_id,
  82             'channel_id': metadata.get('id'),
  83             'channel_url': f'https://picarto.tv/{channel_id}',
  84             'age_limit': age_limit,
  85             'formats': formats,
  86         }
  87
  88
  89 class PicartoVodIE(InfoExtractor):
  90     _VALID_URL = r'https?://(?:www\.)?picarto\.tv/(?:videopopout|\w+/videos)/(?P<id>[^/?#&]+)'
  91     _TESTS = [{
  92         'url': 'https://picarto.tv/videopopout/ArtofZod_2017.12.12.00.13.23.flv',
  93         'md5': '3ab45ba4352c52ee841a28fb73f2d9ca',
  94         'info_dict': {
  95             'id': 'ArtofZod_2017.12.12.00.13.23.flv',
  96             'ext': 'mp4',
  97             'title': 'ArtofZod_2017.12.12.00.13.23.flv',
  98             'thumbnail': r're:^https?://.*\.jpg',
  99         },
 100         'skip': 'The VOD does not exist',
 101     }, {
 102         'url': 'https://picarto.tv/ArtofZod/videos/772650',
 103         'md5': '00067a0889f1f6869cc512e3e79c521b',
 104         'info_dict': {
 105             'id': '772650',
 106             'ext': 'mp4',
 107             'title': 'Art of Zod - Drawing and Painting',
 108             'thumbnail': r're:^https?://.*\.jpg',
 109             'channel': 'ArtofZod',
 110             'age_limit': 18,
 111         },
 112     }, {
 113         'url': 'https://picarto.tv/videopopout/Plague',
 114         'only_matching': True,
 115     }]
 116
 117     def _real_extract(self, url):
 118         video_id = self._match_id(url)
 119
 120         data = self._download_json(
 121             'https://ptvintern.picarto.tv/ptvapi', video_id, query={
 122                 'query': f'''{{
 123   video(id: "{video_id}") {{
 124     id
 125     title
 126     adult
 127     file_name
 128     video_recording_image_url
 129     channel {{
 130       name
 131     }}
 132   }}
 133 }}''',
 134             })['data']['video']
 135
 136         file_name = data['file_name']
 137         netloc = urllib.parse.urlparse(data['video_recording_image_url']).netloc
 138
 139         formats = self._extract_m3u8_formats(
 140             f'https://{netloc}/stream/hls/{file_name}/index.m3u8', video_id, 'mp4', m3u8_id='hls')
 141
 142         return {
 143             'id': video_id,
 144             **traverse_obj(data, {
 145                 'id': ('id', {str_or_none}),
 146                 'title': ('title', {str}),
 147                 'thumbnail': 'video_recording_image_url',
 148                 'channel': ('channel', 'name', {str}),
 149                 'age_limit': ('adult', {lambda x: 18 if x else 0}),
 150             }),
 151             'formats': formats,
 152         }