Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 18:24:30 -04:00
Code Issues Packages Projects Releases Wiki Activity

Google Images metadata download plugin: Fix error when searching for books with non-English characters in the title or author names. Fixes #1577036 ["KeyError" during search cover in the "Google Images Covers"](https://bugs.launchpad.net/calibre/+bug/1577036)

Browse Source
This commit is contained in:
Kovid Goyal 2016-05-01 07:24:41 +05:30
parent 822c7a449c
commit dc622318ab
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
src/calibre/ebooks/metadata/sources/google_images.py
View File

@ -53,13 +53,13 @@ class GoogleImages(Source):
def get_image_urls(self, title, author, log, abort, timeout): def get_image_urls(self, title, author, log, abort, timeout):
from calibre.utils.cleantext import clean_ascii_chars from calibre.utils.cleantext import clean_ascii_chars
from urllib import quote_plus from urllib import urlencode
import html5lib import html5lib
import json import json
from collections import OrderedDict from collections import OrderedDict
ans = OrderedDict() ans = OrderedDict()
br = self.browser br = self.browser
q = quote_plus('%s %s'%(title, author)) q = urlencode({'as_q': ('%s %s'%(title, author)).encode('utf-8')}).decode('utf-8')
sz = self.prefs['size'] sz = self.prefs['size']
if sz == 'any': if sz == 'any':
sz = '' sz = ''
@ -69,7 +69,7 @@ class GoogleImages(Source):
sz = 'isz:lt,islt:%s,' % sz sz = 'isz:lt,islt:%s,' % sz
# See https://www.google.com/advanced_image_search to understand this # See https://www.google.com/advanced_image_search to understand this
# URL scheme # URL scheme
url = 'https://www.google.com/search?as_st=y&tbm=isch&as_q={}&as_epq=&as_oq=&as_eq=&cr=&as_sitesearch=&safe=images&tbs={}iar:t,ift:jpg'.format(q, sz) url = 'https://www.google.com/search?as_st=y&tbm=isch&{}&as_epq=&as_oq=&as_eq=&cr=&as_sitesearch=&safe=images&tbs={}iar:t,ift:jpg'.format(q, sz)
log('Search URL: ' + url) log('Search URL: ' + url)
raw = br.open(url).read().decode('utf-8') raw = br.open(url).read().decode('utf-8')
root = html5lib.parse(clean_ascii_chars(raw), treebuilder='lxml', namespaceHTMLElements=False) root = html5lib.parse(clean_ascii_chars(raw), treebuilder='lxml', namespaceHTMLElements=False)