mirrors/searxng
1
0
Fork 0
mirror of https://github.com/searxng/searxng.git synced 2024-06-18 05:00:35 +00:00
Code Issues Projects Releases Wiki Activity

[fix] skip non-complete google news results

Browse source
This commit is contained in:
Adam Tauber 2017-01-10 11:03:05 +01:00
parent 94327d67fc
commit 108392f8da
1 changed files with 8 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

13
searx/engines/google_news.py
View file

@ -66,11 +66,14 @@ def response(resp):
# parse results
for result in dom.xpath('//div[@class="g"]|//div[@class="g _cy"]'):
r = {
'url': result.xpath('.//div[@class="_cnc"]//a/@href')[0],
'title': ''.join(result.xpath('.//div[@class="_cnc"]//h3//text()')),
'content': ''.join(result.xpath('.//div[@class="st"]//text()')),
}
try:
r = {
'url': result.xpath('.//div[@class="_cnc"]//a/@href')[0],
'title': ''.join(result.xpath('.//div[@class="_cnc"]//h3//text()')),
'content': ''.join(result.xpath('.//div[@class="st"]//text()')),
}
except:
continue
imgs = result.xpath('.//img/@src')
if len(imgs) and not imgs[0].startswith('data'):