Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Amazon metadata: When filtering search engine results by title ignore words of the title that are purely punctuation

Browse Source
This commit is contained in:
Kovid Goyal 2024-06-17 10:10:55 +05:30
parent 43121af37d
commit 44bceacf03
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 9 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
src/calibre/ebooks/metadata/sources/amazon.py
View File

@ -1082,7 +1082,7 @@ class Worker(Thread): # Get details {{{
class Amazon(Source):
name = 'Amazon.com'
version = (1, 3, 7)
version = (1, 3, 8)
minimum_calibre_version = (2, 82, 0)
description = _('Downloads metadata and covers from Amazon')
@ -1684,13 +1684,20 @@ class Amazon(Source):
if not self.use_search_engine:
return True
if title is not None:
import regex
only_punctuation_pat = regex.compile(r'^\p{P}+$')
def tokenize_title(x):
return icu_lower(x).replace("'", '').replace('"', '').rstrip(':')
ans = icu_lower(x).replace("'", '').replace('"', '').rstrip(':')
if only_punctuation_pat.match(ans) is not None:
ans = ''
return ans
tokens = {tokenize_title(x) for x in title.split() if len(x) > 3}
tokens.discard('')
if tokens:
result_tokens = {tokenize_title(x) for x in mi.title.split()}
result_tokens.discard('')
if not tokens.intersection(result_tokens):
log('Ignoring result:', mi.title, 'as its title does not match')
return False