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

[hentai2read] ensure consistent extraction results

Browse Source
This commit is contained in:
Mike Fährmann
2017-12-03 02:34:35 +01:00
parent a1980b16f3
commit 6b8e3003df
1 changed files with 5 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
gallery_dl/extractor/hentai2read.py
View File

@@ -38,16 +38,11 @@ class Hentai2readMangaExtractor(MangaExtractor):
mtype, pos = text.extract( mtype, pos = text.extract(
page, '<small class="text-danger">[', ']</small>', pos) page, '<small class="text-danger">[', ']</small>', pos)
manga_id = util.safe_int(text.extract(page, 'data-mid="', '"', pos)[0]) manga_id = util.safe_int(text.extract(page, 'data-mid="', '"', pos)[0])
page, pos = text.extract(
page, '<ul class="nav-chapters remove-margin-b">', '</ul>\n</div>')
pos = 0 for url, chapter_id, chapter in re.findall(
while True: r'<li>\s+<a href="([^"]+)"'
url, pos = text.extract(page, '<li>\n<a href="', '"', pos) r'[^>]+data-cid="([^"]+)">'
if not url: r'\s+([^<]+)<', page):
return results
chapter_id, pos = text.extract(page, 'data-cid="', '"', pos)
chapter, pos = text.extract(page, '\n', '<', pos)
chapter, _, title = text.unescape(chapter).strip().partition(" - ") chapter, _, title = text.unescape(chapter).strip().partition(" - ")
results.append((url, { results.append((url, {
"manga_id": manga_id, "manga": manga, "type": mtype, "manga_id": manga_id, "manga": manga, "type": mtype,
@@ -55,6 +50,7 @@ class Hentai2readMangaExtractor(MangaExtractor):
"chapter": util.safe_int(chapter), "chapter": util.safe_int(chapter),
"title": title, "lang": "en", "language": "English", "title": title, "lang": "en", "language": "English",
})) }))
return results
class Hentai2readChapterExtractor(hentaicdn.HentaicdnChapterExtractor): class Hentai2readChapterExtractor(hentaicdn.HentaicdnChapterExtractor):