22 lines
729 B
Python
22 lines
729 B
Python
# -*- coding: utf-8 -*-
|
|
# vi:si:et:sw=4:sts=4:ts=4
|
|
import re
|
|
import urllib
|
|
import ox
|
|
from ox import strip_tags, decodeHtml
|
|
from ox.utils import json
|
|
from ox.cache import read_url
|
|
|
|
|
|
def find(query, timeout=ox.cache.cache_timeout):
|
|
if isinstance(query, unicode):
|
|
query = query.encode('utf-8')
|
|
params = urllib.urlencode({'q': query})
|
|
url = 'http://duckduckgo.com/html/?' + params
|
|
data = read_url(url, timeout=timeout, unicode=True)
|
|
results = []
|
|
regex = '<a .*?class="l le" href="(.+?)">(.*?)</a>.*?<div class="cra">(.*?)</div>'
|
|
for r in re.compile(regex, re.DOTALL).findall(data):
|
|
results.append((strip_tags(decodeHtml(r[1])), r[0], strip_tags(decodeHtml(r[2]))))
|
|
return results
|
|
|