0x2620/python-ox
2
1
Fork 0
Code Issues Pull requests Releases Wiki Activity

search cleanup

Browse source
This commit is contained in:
j 2010-12-31 12:53:24 +05:30
commit 9fc6425a9e
2 changed files with 5 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

7
ox/web/duckduckgo.py
View file

@ -5,14 +5,15 @@ import urllib
import ox
from ox import stripTags, decodeHtml
from ox.utils import json
from ox.cache import readUrl
from ox.cache import readUrlUnicode
def find(query, timeout=ox.cache.cache_timeout):
params = urllib.urlencode({'q': query})
if isinstance(query, unicode):
query = query.encode('utf-8')
url = 'http://duckduckgo.com/html/?' + params
print url
data = readUrl(url, timeout=timeout)
data = readUrlUnicode(url, timeout=timeout)
results = []
regex = '<a .*?class="l le" href="(.+?)">(.*?)</a>.*?<div class="cra">(.*?)</div>'
for r in re.compile(regex, re.DOTALL).findall(data):