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

Handle yet another amazon website change

Browse Source
This commit is contained in:
Kovid Goyal 2013-09-21 08:15:07 +05:30
parent 3d3cb1fdb9
commit ae1d2874d8
1 changed files with 21 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

33
src/calibre/ebooks/metadata/sources/amazon.py
View File

@ -748,6 +748,16 @@ class Amazon(Source):
mi.tags = list(map(fixcase, mi.tags)) mi.tags = list(map(fixcase, mi.tags))
mi.isbn = check_isbn(mi.isbn) mi.isbn = check_isbn(mi.isbn)
def get_website_domain(self, domain):
udomain = domain
if domain == 'uk':
udomain = 'co.uk'
elif domain == 'jp':
udomain = 'co.jp'
elif domain == 'br':
udomain = 'com.br'
return udomain
def create_query(self, log, title=None, authors=None, identifiers={}, # {{{ def create_query(self, log, title=None, authors=None, identifiers={}, # {{{
domain=None): domain=None):
from urllib import urlencode from urllib import urlencode
@ -803,14 +813,7 @@ class Amazon(Source):
encoded_q = dict([(x.encode(encode_to, 'ignore'), y.encode(encode_to, encoded_q = dict([(x.encode(encode_to, 'ignore'), y.encode(encode_to,
'ignore')) for x, y in 'ignore')) for x, y in
q.iteritems()]) q.iteritems()])
udomain = domain url = 'http://www.amazon.%s/s/?'%self.get_website_domain(domain) + urlencode(encoded_q)
if domain == 'uk':
udomain = 'co.uk'
elif domain == 'jp':
udomain = 'co.jp'
elif domain == 'br':
udomain = 'com.br'
url = 'http://www.amazon.%s/s/?'%udomain + urlencode(encoded_q)
return url, domain return url, domain
# }}} # }}}
@ -828,7 +831,7 @@ class Amazon(Source):
return url return url
# }}} # }}}
def parse_results_page(self, root): # {{{ def parse_results_page(self, root, domain): # {{{
from lxml.html import tostring from lxml.html import tostring
matches = [] matches = []
@ -851,7 +854,10 @@ class Amazon(Source):
for a in links: for a in links:
title = tostring(a, method='text', encoding=unicode) title = tostring(a, method='text', encoding=unicode)
if title_ok(title): if title_ok(title):
matches.append(a.get('href')) url = a.get('href')
if url.startswith('/'):
url = 'http://www.amazon.%s%s' % (self.get_website_domain(domain), url)
matches.append(url)
break break
if not matches: if not matches:
@ -862,7 +868,10 @@ class Amazon(Source):
for a in td.xpath(r'descendant::td[@class="dataColumn"]/descendant::a[@href]/span[@class="srTitle"]/..'): for a in td.xpath(r'descendant::td[@class="dataColumn"]/descendant::a[@href]/span[@class="srTitle"]/..'):
title = tostring(a, method='text', encoding=unicode) title = tostring(a, method='text', encoding=unicode)
if title_ok(title): if title_ok(title):
matches.append(a.get('href')) url = a.get('href')
if url.startswith('/'):
url = 'http://www.amazon.%s%s' % (self.get_website_domain(domain), url)
matches.append(url)
break break
# Keep only the top 5 matches as the matches are sorted by relevance by # Keep only the top 5 matches as the matches are sorted by relevance by
@ -938,7 +947,7 @@ class Amazon(Source):
found = False found = False
if found: if found:
matches = self.parse_results_page(root) matches = self.parse_results_page(root, domain)
if abort.is_set(): if abort.is_set():
return return