github/gallery-dl
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[hentaihere] ensure consistent extraction results

Browse Source 
sometimes there is a random space before the next <a>
This commit is contained in:
Mike Fährmann
2018-02-05 15:26:25 +01:00
parent 377b78b3c9
commit 7b5ba69951
1 changed files with 4 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
gallery_dl/extractor/hentaihere.py
View File

@@ -40,10 +40,11 @@ class HentaihereMangaExtractor(MangaExtractor):
page, '<span class="mngType text-danger">[', ']</span>', pos) page, '<span class="mngType text-danger">[', ']</span>', pos)
while True: while True:
url, pos = text.extract( marker, pos = text.extract(
page, '<li class="sub-chp clearfix">\n<a href="', '"', pos) page, '<li class="sub-chp clearfix">', '', pos)
if not url: if marker is None:
return results return results
url, pos = text.extract(page, '<a href="', '"', pos)
chapter, pos = text.extract(page, 'title="Tagged: -">\n', '<', pos) chapter, pos = text.extract(page, 'title="Tagged: -">\n', '<', pos)
chapter_id, pos = text.extract(page, '/C', '"', pos) chapter_id, pos = text.extract(page, '/C', '"', pos)
chapter, _, title = text.unescape(chapter).strip().partition(" - ") chapter, _, title = text.unescape(chapter).strip().partition(" - ")