[mangahere] fix metadata extraction
This commit is contained in:
@@ -92,9 +92,8 @@ class MangahereChapterExtractor(AsynchronousExtractor):
|
|||||||
"""Collect metadata for extractor-job"""
|
"""Collect metadata for extractor-job"""
|
||||||
manga, pos = text.extract(page, '<title>', '</title>')
|
manga, pos = text.extract(page, '<title>', '</title>')
|
||||||
chid , pos = text.extract(page, '.net/store/manga/', '/', pos)
|
chid , pos = text.extract(page, '.net/store/manga/', '/', pos)
|
||||||
_ , pos = text.extract(page, '<select class="wid60"', '', pos)
|
pages, pos = text.extract(page, ' class="wid60"', '</select>', pos)
|
||||||
_ , pos = text.extract(page, '</select>', '', pos)
|
count = re.findall(r">(\d+)<", pages)[-1]
|
||||||
count, pos = text.extract(page, '>', '<', pos-30)
|
|
||||||
manga = re.match((r"(.+) \d+(\.\d+)? - Read .+ Chapter "
|
manga = re.match((r"(.+) \d+(\.\d+)? - Read .+ Chapter "
|
||||||
r"\d+(\.\d+)? Online"), manga).group(1)
|
r"\d+(\.\d+)? Online"), manga).group(1)
|
||||||
return {
|
return {
|
||||||
|
|||||||
@@ -73,8 +73,8 @@ skip = [
|
|||||||
"exhentai", "kissmanga", "mangafox", "dynastyscans", "nijie",
|
"exhentai", "kissmanga", "mangafox", "dynastyscans", "nijie",
|
||||||
"archivedmoe", "archiveofsins", "thebarchive",
|
"archivedmoe", "archiveofsins", "thebarchive",
|
||||||
# temporary issues
|
# temporary issues
|
||||||
"imgtrex",
|
"nyafuu",
|
||||||
"loveisover", # certificate verify failed
|
"mangazuki",
|
||||||
]
|
]
|
||||||
# enable selective testing for direct calls
|
# enable selective testing for direct calls
|
||||||
if __name__ == '__main__' and len(sys.argv) > 1:
|
if __name__ == '__main__' and len(sys.argv) > 1:
|
||||||
|
|||||||
Reference in New Issue
Block a user