yt_dlp/extractor/monstercat.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     clean_html,
   6     extract_attributes,
   7     get_element_by_class,
   8     get_element_html_by_class,
   9     get_element_text_and_html_by_tag,
  10     int_or_none,
  11     strip_or_none,
  12     traverse_obj,
  13     try_call,
  14     unified_strdate,
  15 )
  16
  17
  18 class MonstercatIE(InfoExtractor):
  19     _VALID_URL = r'https?://www\.monstercat\.com/release/(?P<id>\d+)'
  20     _TESTS = [{
  21         'url': 'https://www.monstercat.com/release/742779548009',
  22         'playlist_count': 20,
  23         'info_dict': {
  24             'title': 'The Secret Language of Trees',
  25             'id': '742779548009',
  26             'thumbnail': 'https://www.monstercat.com/release/742779548009/cover',
  27             'release_date': '20230711',
  28             'album': 'The Secret Language of Trees',
  29             'album_artist': 'BT',
  30         },
  31     }]
  32
  33     def _extract_tracks(self, table, album_meta):
  34         for td in re.findall(r'<tr[^<]*>((?:(?!</tr>)[\w\W])+)', table):  # regex by chatgpt due to lack of get_elements_by_tag
  35             title = clean_html(try_call(
  36                 lambda: get_element_by_class('d-inline-flex flex-column', td).partition(' <span')[0]))
  37             ids = extract_attributes(try_call(lambda: get_element_html_by_class('btn-play cursor-pointer mr-small', td)) or '')
  38             track_id = ids.get('data-track-id')
  39             release_id = ids.get('data-release-id')
  40
  41             track_number = int_or_none(try_call(lambda: get_element_by_class('py-xsmall', td)))
  42             if not track_id or not release_id:
  43                 self.report_warning(f'Skipping track {track_number}, ID(s) not found')
  44                 self.write_debug(f'release_id={release_id!r} track_id={track_id!r}')
  45                 continue
  46             yield {
  47                 **album_meta,
  48                 'title': title,
  49                 'track': title,
  50                 'track_number': track_number,
  51                 'artist': clean_html(try_call(lambda: get_element_by_class('d-block fs-xxsmall', td))),
  52                 'url': f'https://www.monstercat.com/api/release/{release_id}/track-stream/{track_id}',
  53                 'id': track_id,
  54                 'ext': 'mp3',
  55             }
  56
  57     def _real_extract(self, url):
  58         url_id = self._match_id(url)
  59         html = self._download_webpage(url, url_id)
  60         # wrap all `get_elements` in `try_call`, HTMLParser has problems with site's html
  61         tracklist_table = try_call(lambda: get_element_by_class('table table-small', html)) or ''
  62
  63         title = try_call(lambda: get_element_text_and_html_by_tag('h1', html)[0])
  64         date = traverse_obj(html, ({lambda html: get_element_by_class('font-italic mb-medium d-tablet-none d-phone-block',
  65                             html).partition('Released ')}, 2, {strip_or_none}, {unified_strdate}))
  66
  67         album_meta = {
  68             'title': title,
  69             'album': title,
  70             'thumbnail': f'https://www.monstercat.com/release/{url_id}/cover',
  71             'album_artist': try_call(
  72                 lambda: get_element_by_class('h-normal text-uppercase mb-desktop-medium mb-smallish', html)),
  73             'release_date': date,
  74         }
  75
  76         return self.playlist_result(
  77             self._extract_tracks(tracklist_table, album_meta), playlist_id=url_id, **album_meta)