diff options
| author | jhwgh1968 <jhwgh1968@protonmail.com> | 2021-08-15 06:02:11 +0000 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2021-08-15 11:32:11 +0530 |
| commit | d967c68e4ce83d48f50d97710123bb4ed8f95d1b (patch) | |
| tree | 9734e3ee2d11a316a87605d44497e85572de2420 | |
| parent | 3dd39c5f9a55b8169cf35bc2b33a08842b3c40fe (diff) | |
| download | hypervideo-pre-d967c68e4ce83d48f50d97710123bb4ed8f95d1b.tar.lz hypervideo-pre-d967c68e4ce83d48f50d97710123bb4ed8f95d1b.tar.xz hypervideo-pre-d967c68e4ce83d48f50d97710123bb4ed8f95d1b.zip | |
[eroprofile] Fix page skipping in albums (#701)
Bug from #658
Authored by: jhwgh1968
| -rw-r--r-- | yt_dlp/extractor/eroprofile.py | 10 |
1 files changed, 6 insertions, 4 deletions
diff --git a/yt_dlp/extractor/eroprofile.py b/yt_dlp/extractor/eroprofile.py index 54ed9a49e..a8396f1d3 100644 --- a/yt_dlp/extractor/eroprofile.py +++ b/yt_dlp/extractor/eroprofile.py @@ -114,11 +114,13 @@ class EroProfileAlbumIE(InfoExtractor): yield from self._extract_from_page(first_page) page_urls = re.findall(rf'href=".*?(/m/videos/album/{playlist_id}\?pnum=(\d+))"', first_page) + max_page = max(int(n) for _, n in page_urls) - for url, n in page_urls[1:]: - yield from self._extract_from_page(self._download_webpage( - f'https://www.eroprofile.com{url}', - playlist_id, note=f'Downloading playlist page {int(n) - 1}')) + for n in range(2, max_page + 1): + url = f'https://www.eroprofile.com/m/videos/album/{playlist_id}?pnum={n}' + yield from self._extract_from_page( + self._download_webpage(url, playlist_id, + note=f'Downloading playlist page {int(n) - 1}')) def _real_extract(self, url): playlist_id = self._match_id(url) |