mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-30 12:01:28 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: do not use classmethod; fix title in the base extractor

Browse source
This commit is contained in:
grqx_wsl 2024-11-06 00:10:40 +13:00
parent c58ee488a9
commit bd857a06a0
1 changed files with 55 additions and 25 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

80
yt_dlp/extractor/boomplay.py
View file

@ -69,32 +69,30 @@ def _get_element_by_class_and_tag(cls, class_, tag, html):
def _urljoin(cls, path): def _urljoin(cls, path):
return url_or_none(urljoin(base=cls._BASE, path=path)) return url_or_none(urljoin(base=cls._BASE, path=path))
@classmethod def _get_playurl(self, item_id, item_type):
def _get_playurl(cls, item_id, item_type): resp = self._download_json(
resp = cls._download_json(
'https://www.boomplay.com/getResourceAddr', item_id, 'https://www.boomplay.com/getResourceAddr', item_id,
note='Downloading play URL', errnote='Failed to download play URL', note='Downloading play URL', errnote='Failed to download play URL',
data=urlencode_postdata({ data=urlencode_postdata({
'param': base64.b64encode(aes_cbc_encrypt_bytes(json.dumps({ 'param': base64.b64encode(aes_cbc_encrypt_bytes(json.dumps({
'itemID': item_id, 'itemID': item_id,
'itemType': item_type, 'itemType': item_type,
}).encode(), cls._KEY, cls._IV)).decode(), }).encode(), self._KEY, self._IV)).decode(),
}), headers={ }), headers={
'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8', 'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
}) })
if not (source := resp.get('source')) and (code := resp.get('code')): if not (source := resp.get('source')) and (code := resp.get('code')):
if 'unavailable in your country' in (desc := resp.get('desc')) or '': if 'unavailable in your country' in (desc := resp.get('desc')) or '':
# since NG must have failed ... # since NG must have failed ...
cls.raise_geo_restricted(countries=['GH', 'KE', 'TZ', 'CM', 'CI']) self.raise_geo_restricted(countries=['GH', 'KE', 'TZ', 'CM', 'CI'])
else: else:
raise ExtractorError(desc or f'Failed to get play url, code: {code}') raise ExtractorError(desc or f'Failed to get play url, code: {code}')
return unpad_pkcs7(aes_cbc_decrypt_bytes( return unpad_pkcs7(aes_cbc_decrypt_bytes(
base64.b64decode(source), base64.b64decode(source),
cls._KEY, cls._IV)).decode() self._KEY, self._IV)).decode()
@classmethod def _extract_formats(self, item_id, item_type='MUSIC', **kwargs):
def _extract_formats(cls, item_id, item_type='MUSIC', **kwargs): if url := url_or_none(self._get_playurl(item_id, item_type)):
if url := url_or_none(cls._get_playurl(item_id, item_type)):
return [{ return [{
'format_id': '0', 'format_id': '0',
'url': url, 'url': url,
@ -106,30 +104,29 @@ def _extract_formats(cls, item_id, item_type='MUSIC', **kwargs):
**kwargs, **kwargs,
}] }]
else: else:
cls.raise_no_formats('No formats found') self.raise_no_formats('No formats found')
@classmethod def _extract_page_metadata(self, webpage, item_id):
def _extract_page_metadata(cls, webpage, item_id): metadata_div = self._get_element_by_class_and_tag('summary', 'div', webpage) or ''
metadata_div = cls._get_element_by_class_and_tag('summary', 'div', webpage) or ''
metadata_entries = re.findall(r'(?si)<strong>(?P<entry>.*?)</strong>', metadata_div) or [] metadata_entries = re.findall(r'(?si)<strong>(?P<entry>.*?)</strong>', metadata_div) or []
description = re.sub( description = re.sub(
r'(?i)Listen and download music for free on Boomplay!', '', r'(?i)Listen and download music for free on Boomplay!', '',
clean_html(cls._get_element_by_class_and_tag( clean_html(self._get_element_by_class_and_tag(
'description_content', 'span', webpage)) or '') or None 'description_content', 'span', webpage)) or '') or None
details_section = cls._get_element_by_class_and_tag('songDetailInfo', 'section', webpage) or '' details_section = self._get_element_by_class_and_tag('songDetailInfo', 'section', webpage) or ''
metadata_entries.extend(re.findall(r'(?si)<li>(?P<entry>.*?)</li>', details_section) or []) metadata_entries.extend(re.findall(r'(?si)<li>(?P<entry>.*?)</li>', details_section) or [])
page_metadata = { page_metadata = {
'id': item_id, 'id': item_id,
'title': cls._html_search_regex(r'(?i)<h1[^>]*>([^<]+)</h1>', webpage, 'title', default=None), **self._extract_title_from_webpage(webpage),
'thumbnail': cls._html_search_meta(['og:image', 'twitter:image'], 'thumbnail': self._html_search_meta(['og:image', 'twitter:image'],
webpage, 'thumbnail', default=''), webpage, 'thumbnail', default=None),
'like_count': parse_count(cls._get_element_by_class_and_tag('btn_favorite', 'button', metadata_div)), 'like_count': parse_count(self._get_element_by_class_and_tag('btn_favorite', 'button', metadata_div)),
'repost_count': parse_count(cls._get_element_by_class_and_tag('btn_share', 'button', metadata_div)), 'repost_count': parse_count(self._get_element_by_class_and_tag('btn_share', 'button', metadata_div)),
'comment_count': parse_count(cls._get_element_by_class_and_tag('btn_comment', 'button', metadata_div)), 'comment_count': parse_count(self._get_element_by_class_and_tag('btn_comment', 'button', metadata_div)),
'duration': parse_duration(cls._get_element_by_class_and_tag('btn_duration', 'button', metadata_div)), 'duration': parse_duration(self._get_element_by_class_and_tag('btn_duration', 'button', metadata_div)),
'upload_date': unified_strdate(strip_or_none( 'upload_date': unified_strdate(strip_or_none(
cls._get_element_by_class_and_tag('btn_pubDate', 'button', metadata_div))), self._get_element_by_class_and_tag('btn_pubDate', 'button', metadata_div))),
'description': description, 'description': description,
} }
for metadata_entry in metadata_entries: for metadata_entry in metadata_entries:
@ -147,6 +144,40 @@ def _extract_page_metadata(cls, webpage, item_id):
page_metadata['release_year'] = int_or_none(v) page_metadata['release_year'] = int_or_none(v)
return page_metadata return page_metadata
def _extract_title_from_webpage(self, webpage):
if h1_title := self._html_search_regex(r'(?i)<h1[^>]*>([^<]+)</h1>', webpage, 'title', default=None):
return {'title': h1_title}
else:
return self._fix_title(
self._html_search_meta(['og:title', 'twitter:title'], webpage, 'title', default=None)
or self._html_search_regex(r'(?i)<title[^>]*>([^<]+)</title>', webpage, 'title', default=None))
@staticmethod
def _fix_title(title):
"""
fix various types of titles(og:title, twitter:title, title tag in html head):
"""
if not title:
return {}
title_patterns = (
r'^(?P<title>(?P<artist>.+)) Songs MP3 Download, New Songs \& Albums \| Boomplay$', # artists
r'^(?P<artist>.+?) - (?P<title>.+) MP3\ Download \& Lyrics \| Boomplay$', # music
r'^Download (?P<artist>.+) album songs: (?P<title>.+?) \| Boomplay Music$', # album
r'^Search:(?P<title>.+) \| Boomplay Music$', # search url
r'^(?P<title>.+) \| Podcast \| Boomplay$', # podcast, episode
r'^(?P<title>.+) \| Boomplay(?: Music)?$', # video, playlist, generic playlists
)
for pattern in title_patterns:
if match := re.search(pattern, title):
return {
'title': match.group('title'),
'artists': [match.group('artist')] if 'artist' in match.groupdict() else None,
}
return {'title': title}
@classmethod @classmethod
def _extract_from_webpage(cls, url, webpage, **kwargs): def _extract_from_webpage(cls, url, webpage, **kwargs):
if kwargs: if kwargs:
@ -166,7 +197,7 @@ def _extract_embed_urls(cls, url, webpage):
<a <a
(?:\s(?:[^>"']|"[^"]*"|'[^']*')*)? (?:\s(?:[^>"']|"[^"]*"|'[^']*')*)?
(?<=\s)href\s*=\s*(?P<_q>['"]) (?<=\s)href\s*=\s*(?P<_q>['"])
(?!javascript:)(?P<href>/(?:{media_types})/\d+/?[\-\w=?&#:;@]*) (?P<href>/(?:{media_types})/\d+/?[\-\w=?&#:;@]*)
(?P=_q) (?P=_q)
(?:\s(?:[^>"']|"[^"]*"|'[^']*')*)? (?:\s(?:[^>"']|"[^"]*"|'[^']*')*)?
>''', webpage): >''', webpage):
@ -290,7 +321,6 @@ def _real_extract(self, url):
webpage = self._download_webpage(url, ep_id) webpage = self._download_webpage(url, ep_id)
return merge_dicts( return merge_dicts(
self._extract_page_metadata(webpage, ep_id), { self._extract_page_metadata(webpage, ep_id), {
'title': self._og_search_title(webpage, default='').rsplit('|', 2)[0].strip() or None,
'description': self._html_search_meta( 'description': self._html_search_meta(
['description', 'og:description', 'twitter:description'], webpage), ['description', 'og:description', 'twitter:description'], webpage),
'formats': self._extract_formats(ep_id, 'EPISODE', vcodec='none'), 'formats': self._extract_formats(ep_id, 'EPISODE', vcodec='none'),