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 download: Ignore Spanish edition entries when searching for a book on amazon.com

Browse Source
This commit is contained in:
Kovid Goyal 2013-04-09 17:07:24 +05:30
parent 9fb122cd4b
commit 949b3c04f9
1 changed files with 60 additions and 58 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
src/calibre/ebooks/metadata/sources/amazon.py
View File

@ -276,7 +276,6 @@ class Worker(Thread): # Get details {{{
self.log.exception('Error parsing authors for url: %r'%self.url)
authors = []
if not title or not authors or not asin:
self.log.error('Could not find title/authors/asin for %r'%self.url)
self.log.error('ASIN: %r Title: %r Authors: %r'%(asin, title,
@ -431,7 +430,6 @@ class Worker(Thread): # Get details {{{
desc = re.sub(r'(?s)<!--.*?-->', '', desc)
return sanitize_comments_html(desc)
def parse_comments(self, root):
ans = ''
desc = root.xpath('//div[@id="ps-content"]/div[@class="content"]')
@ -637,7 +635,6 @@ class Amazon(Source):
mi.tags = list(map(fixcase, mi.tags))
mi.isbn = check_isbn(mi.isbn)
def create_query(self, log, title=None, authors=None, identifiers={}, # {{{
domain=None):
if domain is None:
@ -724,7 +721,10 @@ class Amazon(Source):
def title_ok(title):
title = title.lower()
for x in ('bulk pack', '[audiobook]', '[audio cd]'):
bad = ['bulk pack', '[audiobook]', '[audio cd]']
if self.domain == 'com':
bad.append('(spanish edition)')
for x in bad:
if x in title:
return False
return True
@ -751,7 +751,6 @@ class Amazon(Source):
matches.append(a.get('href'))
break
# Keep only the top 5 matches as the matches are sorted by relevance by
# Amazon so lower matches are not likely to be very relevant
return matches[:5]
@ -795,7 +794,6 @@ class Amazon(Source):
log.exception(msg)
return as_unicode(msg)
raw = clean_ascii_chars(xml_to_unicode(raw,
strip_encoding_pats=True, resolve_entities=True)[0])
@ -825,7 +823,6 @@ class Amazon(Source):
# The error is almost always a not found error
found = False
if found:
matches = self.parse_results_page(root)
@ -907,6 +904,11 @@ if __name__ == '__main__': # tests {{{
isbn_test, title_test, authors_test, comments_test, series_test)
com_tests = [ # {{{
( # Has a spanish edition
{'title':'11/22/63'},
[title_test('11/22/63: A Novel', exact=True), authors_test(['Stephen King']),]
),
( # + in title and uses id="main-image" for cover
{'title':'C++ Concurrency in Action'},
[title_test('C++ Concurrency in Action: Practical Multithreading',
@ -917,8 +919,8 @@ if __name__ == '__main__': # tests {{{
( # Series
{'identifiers':{'amazon':'0756407117'}},
[title_test(
"Throne of the Crescent Moon"
, exact=True), series_test('Crescent Moon Kingdoms', 1),
"Throne of the Crescent Moon",
exact=True), series_test('Crescent Moon Kingdoms', 1),
comments_test('Makhslood'),
]
),
@ -926,8 +928,8 @@ if __name__ == '__main__': # tests {{{
( # Different comments markup, using Book Description section
{'identifiers':{'amazon':'0982514506'}},
[title_test(
"Griffin's Destiny: Book Three: The Griffin's Daughter Trilogy"
, exact=True),
"Griffin's Destiny: Book Three: The Griffin's Daughter Trilogy",
exact=True),
comments_test('Jelena'), comments_test('Leslie'),
]
),