Backup_Repos/calibre
1
0
Fork 0
mirror of git://github.com/kovidgoyal/calibre.git synced 2025-12-28 15:45:51 +01:00
Code Issues Projects Releases Wiki Activity

Amazon metadata download: Ignore ' and " in titles when matching results

Browse source
This commit is contained in:
Kovid Goyal 2021-01-01 19:38:42 +05:30
parent 501e7b8973
commit c4c1c5f841
No known key found for this signature in database
GPG key ID: 06BC317B515ACE7C
1 changed files with 7 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
src/calibre/ebooks/metadata/sources/amazon.py
View file

@ -908,7 +908,7 @@ def parse_language(self, pd):
class Amazon(Source):
name = 'Amazon.com'
version = (1, 2, 14)
version = (1, 2, 15)
minimum_calibre_version = (2, 82, 0)
description = _('Downloads metadata and covers from Amazon')
@ -1478,9 +1478,13 @@ def filter_result(self, title, authors, identifiers, mi, log): # {{{
if not self.use_search_engine:
return True
if title is not None:
tokens = {icu_lower(x).rstrip(':') for x in title.split() if len(x) > 3}
def tokenize_title(x):
return icu_lower(x).replace("'", '').replace('"', '').rstrip(':')
tokens = {tokenize_title(x) for x in title.split() if len(x) > 3}
if tokens:
result_tokens = {icu_lower(x).rstrip(':') for x in mi.title.split()}
result_tokens = {tokenize_title(x) for x in mi.title.split()}
if not tokens.intersection(result_tokens):
log('Ignoring result:', mi.title, 'as its title does not match')
return False