Cool_Tools/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-20 05:47:24 +01:00
Code Issues Packages Projects Releases Wiki Activity

Refactored code to avoid potentials bugs

Browse Source 
Made the following changes:
1. added static page limit to avoid potential infinite loop scenario
2. added comments to explain more about the artist page results
3. updated artist page _call_api params to match browser request
4. refactored code to remove extra first page api call for playlist name
This commit is contained in:
subrat-lima 2024-08-27 10:49:08 +05:30
parent ccbbd37dca
commit bfcb22aca1
1 changed files with 17 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
yt_dlp/extractor/jiosaavn.py
View File

@ -224,7 +224,8 @@ class JioSaavnArtistIE(JioSaavnBaseIE):
def _fetch_page(self, token, page): def _fetch_page(self, token, page):
return self._call_api('artist', token, f'artist page {page}', { return self._call_api('artist', token, f'artist page {page}', {
'p': page, 'n': self._PAGE_SIZE, 'api_version': '4', 'category': 'alphabetical', 'sort_order': 'asc'}) 'p': page, 'n_song': self._PAGE_SIZE, 'n_album': self._PAGE_SIZE, 'sub_type': '',
'includeMetaTags': '', 'api_version': '4', 'category': 'alphabetical', 'sort_order': 'asc'})
def _extract_song(self, song_data, url=None): def _extract_song(self, song_data, url=None):
info = traverse_obj(song_data, { info = traverse_obj(song_data, {
@ -253,23 +254,29 @@ def _yield_songs(self, playlist_data):
yield self.url_result(url, JioSaavnSongIE, url_transparent=True, **song_info) yield self.url_result(url, JioSaavnSongIE, url_transparent=True, **song_info)
def _entries(self, token, page): def _entries(self, token, page):
page_data = self._fetch_page(token, page) page_data = self._first_page if page == 0 else self._fetch_page(token, page)
yield from self._yield_songs(page_data) yield from self._yield_songs(page_data)
def _generate_result(self, token): def _generate_result(self, token):
pagenum = 0 # note:
# 1. the total number of songs in a page result is not constant
# 2. end of list is identified by 'topSongs' array being empty
page = 0
result = [] result = []
while True:
entries = list(self._entries(token, pagenum)) # added static page count limit to avoid potential infinite loop
while page < 20000:
entries = list(self._entries(token, page))
if len(entries) == 0: if len(entries) == 0:
break break
result.extend(entries) result.extend(entries)
pagenum += 1 page += 1
return result return result
def _real_extract(self, url): def _real_extract(self, url):
artist_token_id = self._match_id(url) display_id = self._match_id(url)
artist_playlist_entries = self._generate_result(artist_token_id) self._first_page = self._fetch_page(display_id, 0)
name = self._fetch_page(artist_token_id, 0).get('name') entries = self._generate_result(display_id)
name = self._first_page.get('name')
return self.playlist_result(artist_playlist_entries, artist_token_id, name) return self.playlist_result(entries, display_id, name)