Cool_Tools/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-20 13:57:25 +01:00
Code Issues Packages Projects Releases Wiki Activity

[PromoDJ] Some refactoring

Browse Source
This commit is contained in:
DmitryScaletta 2024-02-14 14:00:03 +03:00
parent 13f116fce6
commit a634e7c5d1
No known key found for this signature in database
GPG Key ID: 167A65222EDD4C2A
1 changed files with 16 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
yt_dlp/extractor/promodj.py
View File

@ -74,8 +74,7 @@ def _set_url_page(self, url, page):
def _fetch_page(self, url, allowed_media_cats, playlist_id, page): def _fetch_page(self, url, allowed_media_cats, playlist_id, page):
page_url = self._set_url_page(url, page + 1) page_url = self._set_url_page(url, page + 1)
html = self._download_webpage(page_url, f'{playlist_id}-page-{page + 1}') html = self._download_webpage(page_url, f'{playlist_id}-page-{page + 1}')
current_page = int(clean_html(get_element_by_class('NavigatorCurrentPage', html)) or '1') if self._get_current_page(html) != page + 1:
if current_page != page + 1:
return return
for a in get_elements_html_by_class('player_standard_tool__play', html): for a in get_elements_html_by_class('player_standard_tool__play', html):
@ -115,6 +114,9 @@ def _get_playlist_page_size(self, url):
is_default_playlist = '/groups/' not in url is_default_playlist = '/groups/' not in url
return 30 if is_default_playlist else 20 return 30 if is_default_playlist else 20
def _get_current_page(self, html):
return int(clean_html(get_element_by_class('NavigatorCurrentPage', html)) or '1')
def _fetch_media_data(self, ids, video_id): def _fetch_media_data(self, ids, video_id):
data = {} data = {}
for i, id in enumerate(ids): for i, id in enumerate(ids):
@ -232,11 +234,10 @@ def _parse_pages(self, url, playlist_id):
for page_url, page_title in re.findall(r'<a href=\"([^\"]+)\">([^<]+)</a>', content_html): for page_url, page_title in re.findall(r'<a href=\"([^\"]+)\">([^<]+)</a>', content_html):
yield self.url_result(page_url, PromoDJUserPageIE, video_title=page_title) yield self.url_result(page_url, PromoDJUserPageIE, video_title=page_title)
def _fetch_blog_page(self, url, playlist_id, page): def _fetch_blogs_page(self, url, playlist_id, page):
page_url = self._set_url_page(url, page + 1) page_url = self._set_url_page(url, page + 1)
html = self._download_webpage(page_url, f'{playlist_id}-page-{page + 1}') html = self._download_webpage(page_url, f'{playlist_id}-page-{page + 1}')
current_page = int(clean_html(get_element_by_class('NavigatorCurrentPage', html)) or '1') if self._get_current_page(html) != page + 1:
if current_page != page + 1:
return return
for a in get_elements_html_by_class('post_title_moderated', html): for a in get_elements_html_by_class('post_title_moderated', html):
@ -250,7 +251,7 @@ def _real_extract(self, url):
entries = self._parse_pages(url, playlist_id) entries = self._parse_pages(url, playlist_id)
elif type == 'blog': elif type == 'blog':
entries = OnDemandPagedList( entries = OnDemandPagedList(
functools.partial(self._fetch_blog_page, url, playlist_id), functools.partial(self._fetch_blogs_page, url, playlist_id),
self._PAGE_SIZE) self._PAGE_SIZE)
return self.playlist_result(entries, playlist_id) return self.playlist_result(entries, playlist_id)
@ -472,14 +473,7 @@ def _parse_media(self, html, id, type):
has_formats = len(formats_from_html) != 0 has_formats = len(formats_from_html) != 0
is_paid = re.search(self._IS_PAID_RE, meta_html) is_paid = re.search(self._IS_PAID_RE, meta_html)
if not has_formats and is_paid: if not has_formats and type == 'videos':
media_data_raw = self._search_regex(self._MUSIC_DATA_REGEX, html, 'media data')
media_data = self._parse_json(media_data_raw, id)
formats = [{
'url': source.get('URL'),
'size': int_or_none(source.get('size')),
} for source in traverse_obj(media_data, ('sources')) if url_or_none(source.get('URL'))]
elif not has_formats and type == 'videos':
media_data_raw = self._search_regex(self._VIDEO_DATA_REGEX, html, 'media data') media_data_raw = self._search_regex(self._VIDEO_DATA_REGEX, html, 'media data')
media_data = self._parse_json(media_data_raw, id) media_data = self._parse_json(media_data_raw, id)
video_config = self._parse_json(media_data['config'], id) video_config = self._parse_json(media_data['config'], id)
@ -487,6 +481,13 @@ def _parse_media(self, html, id, type):
formats = [{ formats = [{
'url': traverse_obj(video, ('play', '@url', {url_or_none})), 'url': traverse_obj(video, ('play', '@url', {url_or_none})),
}] }]
elif not has_formats or is_paid:
media_data_raw = self._search_regex(self._MUSIC_DATA_REGEX, html, 'media data')
media_data = self._parse_json(media_data_raw, id)
formats = [{
'url': source.get('URL'),
'size': int_or_none(source.get('size')),
} for source in traverse_obj(media_data, ('sources')) if url_or_none(source.get('URL'))]
else: else:
formats = [{ formats = [{
'url': url, 'url': url,
@ -558,13 +559,10 @@ class PromoDJShortIE(PromoDJBaseIE):
'only_matching': True, 'only_matching': True,
}] }]
_PAGE_URL_REGEX = r'<meta property="og:url"\s*content="(?P<url>[^"]+)"'
def _real_extract(self, url): def _real_extract(self, url):
id = self._match_id(url) id = self._match_id(url)
html = self._download_webpage(url, id) html = self._download_webpage(url, id)
url = re.findall(self._PAGE_URL_REGEX, html)[0] return self.url_result(self._og_search_url(html), PromoDJIE, id)
return self.url_result(url, PromoDJIE, id)
class PromoDJRadioIE(PromoDJBaseIE): class PromoDJRadioIE(PromoDJBaseIE):