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     update_url,
   9 )
  10
  11
  12 class PicartoIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:www.)?picarto\.tv/(?P<id>[a-zA-Z0-9]+)'
  14     _TEST = {
  15         'url': 'https://picarto.tv/Setz',
  16         'info_dict': {
  17             'id': 'Setz',
  18             'ext': 'mp4',
  19             'title': 're:^Setz [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
  20             'timestamp': int,
  21             'is_live': True,
  22         },
  23         'skip': 'Stream is offline',
  24     }
  25
  26     @classmethod
  27     def suitable(cls, url):
  28         return False if PicartoVodIE.suitable(url) else super().suitable(url)
  29
  30     def _real_extract(self, url):
  31         channel_id = self._match_id(url)
  32
  33         data = self._download_json(
  34             'https://ptvintern.picarto.tv/ptvapi', channel_id, query={
  35                 'query': '''{
  36   channel(name: "%s") {
  37     adult
  38     id
  39     online
  40     stream_name
  41     title
  42   }
  43   getLoadBalancerUrl(channel_name: "%s") {
  44     url
  45   }
  46 }''' % (channel_id, channel_id),  # noqa: UP031
  47             }, headers={'Accept': '*/*', 'Content-Type': 'application/json'})['data']
  48         metadata = data['channel']
  49
  50         if metadata.get('online') == 0:
  51             raise ExtractorError('Stream is offline', expected=True)
  52         title = metadata['title']
  53
  54         cdn_data = self._download_json(''.join((
  55             update_url(data['getLoadBalancerUrl']['url'], scheme='https'),
  56             '/stream/json_', metadata['stream_name'], '.js')),
  57             channel_id, 'Downloading load balancing info')
  58
  59         formats = []
  60         for source in (cdn_data.get('source') or []):
  61             source_url = source.get('url')
  62             if not source_url:
  63                 continue
  64             source_type = source.get('type')
  65             if source_type == 'html5/application/vnd.apple.mpegurl':
  66                 formats.extend(self._extract_m3u8_formats(
  67                     source_url, channel_id, 'mp4', m3u8_id='hls', fatal=False))
  68             elif source_type == 'html5/video/mp4':
  69                 formats.append({
  70                     'url': source_url,
  71                 })
  72
  73         mature = metadata.get('adult')
  74         if mature is None:
  75             age_limit = None
  76         else:
  77             age_limit = 18 if mature is True else 0
  78
  79         return {
  80             'id': channel_id,
  81             'title': title.strip(),
  82             'is_live': True,
  83             'channel': channel_id,
  84             'channel_id': metadata.get('id'),
  85             'channel_url': f'https://picarto.tv/{channel_id}',
  86             'age_limit': age_limit,
  87             'formats': formats,
  88         }
  89
  90
  91 class PicartoVodIE(InfoExtractor):
  92     _VALID_URL = r'https?://(?:www\.)?picarto\.tv/(?:videopopout|\w+/videos)/(?P<id>[^/?#&]+)'
  93     _TESTS = [{
  94         'url': 'https://picarto.tv/videopopout/ArtofZod_2017.12.12.00.13.23.flv',
  95         'md5': '3ab45ba4352c52ee841a28fb73f2d9ca',
  96         'info_dict': {
  97             'id': 'ArtofZod_2017.12.12.00.13.23.flv',
  98             'ext': 'mp4',
  99             'title': 'ArtofZod_2017.12.12.00.13.23.flv',
 100             'thumbnail': r're:^https?://.*\.jpg',
 101         },
 102         'skip': 'The VOD does not exist',
 103     }, {
 104         'url': 'https://picarto.tv/ArtofZod/videos/771008',
 105         'md5': 'abef5322f2700d967720c4c6754b2a34',
 106         'info_dict': {
 107             'id': '771008',
 108             'ext': 'mp4',
 109             'title': 'Art of Zod - Drawing and Painting',
 110             'thumbnail': r're:^https?://.*\.jpg',
 111             'channel': 'ArtofZod',
 112             'age_limit': 18,
 113         },
 114     }, {
 115         'url': 'https://picarto.tv/videopopout/Plague',
 116         'only_matching': True,
 117     }]
 118
 119     def _real_extract(self, url):
 120         video_id = self._match_id(url)
 121
 122         data = self._download_json(
 123             'https://ptvintern.picarto.tv/ptvapi', video_id, query={
 124                 'query': f'''{{
 125   video(id: "{video_id}") {{
 126     id
 127     title
 128     adult
 129     file_name
 130     video_recording_image_url
 131     channel {{
 132       name
 133     }}
 134   }}
 135 }}''',
 136             }, headers={'Accept': '*/*', 'Content-Type': 'application/json'})['data']['video']
 137
 138         file_name = data['file_name']
 139         netloc = urllib.parse.urlparse(data['video_recording_image_url']).netloc
 140
 141         formats = self._extract_m3u8_formats(
 142             f'https://{netloc}/stream/hls/{file_name}/index.m3u8', video_id, 'mp4', m3u8_id='hls')
 143
 144         return {
 145             'id': video_id,
 146             **traverse_obj(data, {
 147                 'id': ('id', {str_or_none}),
 148                 'title': ('title', {str}),
 149                 'thumbnail': 'video_recording_image_url',
 150                 'channel': ('channel', 'name', {str}),
 151                 'age_limit': ('adult', {lambda x: 18 if x else 0}),
 152             }),
 153             'formats': formats,
 154         }