diff options
Diffstat (limited to 'yt_dlp/extractor/monstercat.py')
| -rw-r--r-- | yt_dlp/extractor/monstercat.py | 37 |
1 files changed, 17 insertions, 20 deletions
diff --git a/yt_dlp/extractor/monstercat.py b/yt_dlp/extractor/monstercat.py index 930c13e27..f17b91f5a 100644 --- a/yt_dlp/extractor/monstercat.py +++ b/yt_dlp/extractor/monstercat.py @@ -4,15 +4,11 @@ from .common import InfoExtractor from ..utils import ( clean_html, extract_attributes, - get_element_by_class, - get_element_html_by_class, - get_element_text_and_html_by_tag, int_or_none, strip_or_none, - traverse_obj, - try_call, unified_strdate, ) +from ..utils.traversal import find_element, traverse_obj class MonstercatIE(InfoExtractor): @@ -26,19 +22,21 @@ class MonstercatIE(InfoExtractor): 'thumbnail': 'https://www.monstercat.com/release/742779548009/cover', 'release_date': '20230711', 'album': 'The Secret Language of Trees', - 'album_artist': 'BT', + 'album_artists': ['BT'], }, }] def _extract_tracks(self, table, album_meta): for td in re.findall(r'<tr[^<]*>((?:(?!</tr>)[\w\W])+)', table): # regex by chatgpt due to lack of get_elements_by_tag - title = clean_html(try_call( - lambda: get_element_by_class('d-inline-flex flex-column', td).partition(' <span')[0])) - ids = extract_attributes(try_call(lambda: get_element_html_by_class('btn-play cursor-pointer mr-small', td)) or '') + title = traverse_obj(td, ( + {find_element(cls='d-inline-flex flex-column')}, + {lambda x: x.partition(' <span')}, 0, {clean_html})) + ids = traverse_obj(td, ( + {find_element(cls='btn-play cursor-pointer mr-small', html=True)}, {extract_attributes})) or {} track_id = ids.get('data-track-id') release_id = ids.get('data-release-id') - track_number = int_or_none(try_call(lambda: get_element_by_class('py-xsmall', td))) + track_number = traverse_obj(td, ({find_element(cls='py-xsmall')}, {int_or_none})) if not track_id or not release_id: self.report_warning(f'Skipping track {track_number}, ID(s) not found') self.write_debug(f'release_id={release_id!r} track_id={track_id!r}') @@ -48,7 +46,7 @@ class MonstercatIE(InfoExtractor): 'title': title, 'track': title, 'track_number': track_number, - 'artist': clean_html(try_call(lambda: get_element_by_class('d-block fs-xxsmall', td))), + 'artists': traverse_obj(td, ({find_element(cls='d-block fs-xxsmall')}, {clean_html}, all)), 'url': f'https://www.monstercat.com/api/release/{release_id}/track-stream/{track_id}', 'id': track_id, 'ext': 'mp3', @@ -57,20 +55,19 @@ class MonstercatIE(InfoExtractor): def _real_extract(self, url): url_id = self._match_id(url) html = self._download_webpage(url, url_id) - # wrap all `get_elements` in `try_call`, HTMLParser has problems with site's html - tracklist_table = try_call(lambda: get_element_by_class('table table-small', html)) or '' - - title = try_call(lambda: get_element_text_and_html_by_tag('h1', html)[0]) - date = traverse_obj(html, ({lambda html: get_element_by_class('font-italic mb-medium d-tablet-none d-phone-block', - html).partition('Released ')}, 2, {strip_or_none}, {unified_strdate})) + # NB: HTMLParser may choke on this html; use {find_element} or try_call(lambda: get_element...) + tracklist_table = traverse_obj(html, {find_element(cls='table table-small')}) or '' + title = traverse_obj(html, ({find_element(tag='h1')}, {clean_html})) album_meta = { 'title': title, 'album': title, 'thumbnail': f'https://www.monstercat.com/release/{url_id}/cover', - 'album_artist': try_call( - lambda: get_element_by_class('h-normal text-uppercase mb-desktop-medium mb-smallish', html)), - 'release_date': date, + 'album_artists': traverse_obj(html, ( + {find_element(cls='h-normal text-uppercase mb-desktop-medium mb-smallish')}, {clean_html}, all)), + 'release_date': traverse_obj(html, ( + {find_element(cls='font-italic mb-medium d-tablet-none d-phone-block')}, + {lambda x: x.partition('Released ')}, 2, {strip_or_none}, {unified_strdate})), } return self.playlist_result( |