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