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

Metadata download: Update plugin to get covers from google image search to handle changes to the google website. Fixes #1254973 [Google Images metadata search yields no results](https://bugs.launchpad.net/calibre/+bug/1254973)

Browse Source
This commit is contained in:
Kovid Goyal 2013-11-26 17:02:02 +05:30
parent 6f07157a6c
commit 3bc7e7d943
1 changed files with 6 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
src/calibre/ebooks/metadata/sources/google_images.py
View File

@ -39,7 +39,7 @@ class GoogleImages(Source):
title=None, authors=None, identifiers={}, timeout=30, get_best_cover=False): title=None, authors=None, identifiers={}, timeout=30, get_best_cover=False):
if not title: if not title:
return return
timeout = max(60, timeout) # Needs at least a minute timeout = max(60, timeout) # Needs at least a minute
title = ' '.join(self.get_title_tokens(title)) title = ' '.join(self.get_title_tokens(title))
author = ' '.join(self.get_author_tokens(authors)) author = ' '.join(self.get_author_tokens(authors))
urls = self.get_image_urls(title, author, log, abort, timeout) urls = self.get_image_urls(title, author, log, abort, timeout)
@ -59,14 +59,16 @@ class GoogleImages(Source):
return [] return []
USER_AGENT = 'Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.2.13) Gecko/20101210 Firefox/3.6.13' USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64; rv:25.0) Gecko/20100101 Firefox/25.0'
def find_image_urls(br, ans): def find_image_urls(br, ans):
import urlparse import urlparse
for w in br.page.mainFrame().documentElement().findAll('.images_table a[href]'): for w in br.page.mainFrame().documentElement().findAll('div#ires a.rg_l[href]'):
try: try:
imgurl = urlparse.parse_qs(urlparse.urlparse(unicode(w.attribute('href'))).query)['imgurl'][0] imgurl = urlparse.parse_qs(urlparse.urlparse(unicode(w.attribute('href'))).query)['imgurl'][0]
except: except:
# import traceback
# traceback.print_exc()
continue continue
if imgurl not in ans: if imgurl not in ans:
ans.append(imgurl) ans.append(imgurl)
@ -98,7 +100,7 @@ def search(title, author, size, timeout, debug=False):
if debug: if debug:
br.show_browser() br.show_browser()
br.close() br.close()
del br # Needed to prevent PyQt from segfaulting del br # Needed to prevent PyQt from segfaulting
return ans return ans
def test_google(): def test_google():