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

Google images metadata download plugin: Fix for change in website causing no covers to be downloaded

Browse Source 
Fixes #1698314 [Google Images plugin can't find any images](https://bugs.launchpad.net/calibre/+bug/1698314)
This commit is contained in:
Kovid Goyal 2017-06-16 14:04:37 +05:30
parent bc6656c801
commit f5446f68a7
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 3 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
src/calibre/ebooks/metadata/sources/google_images.py
View File

@ -9,10 +9,9 @@ __docformat__ = 'restructuredtext en'
from collections import OrderedDict from collections import OrderedDict
from calibre import random_user_agent
from calibre.ebooks.metadata.sources.base import Source, Option from calibre.ebooks.metadata.sources.base import Source, Option
USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64; rv:45.0) Gecko/20100101 Firefox/45.0'
class GoogleImages(Source): class GoogleImages(Source):
@ -51,7 +50,7 @@ class GoogleImages(Source):
@property @property
def user_agent(self): def user_agent(self):
return USER_AGENT return random_user_agent(allow_ie=False)
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
@ -75,7 +74,7 @@ class GoogleImages(Source):
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)
for div in root.xpath('//div[@class="rg_meta"]'): for div in root.xpath('//div[@class="rg_meta notranslate"]'):
try: try:
data = json.loads(div.text) data = json.loads(div.text)
except Exception: except Exception: