Amazon metadata download: Recognize common patterns of embedding the series name after the title and remove it automatically

This commit is contained in:
Kovid Goyal 2016-06-06 18:19:04 +05:30
parent f915daed36
commit 150d6762f7

View File

@ -881,6 +881,10 @@ class Amazon(Source):
mi.isbn = check_isbn(mi.isbn) mi.isbn = check_isbn(mi.isbn)
if mi.series and docase: if mi.series and docase:
mi.series = fixcase(mi.series) mi.series = fixcase(mi.series)
if mi.title and mi.series:
for pat in (r':\s*Book\s+\d+\s+of\s+%s$', r'\(%s\)$'):
pat = pat % re.escape(mi.series)
mi.title = re.sub(pat, '', mi.title, flags=re.I)
def get_website_domain(self, domain): def get_website_domain(self, domain):
udomain = domain udomain = domain