python-ox/ox/web/duckduckgo.py

23 lines
739 B
Python
Raw Normal View History

2010-12-29 12:06:14 +00:00
# -*- coding: utf-8 -*-
# vi:si:et:sw=4:sts=4:ts=4
import re
import urllib
import ox
from ox import strip_tags, decode_html
2010-12-29 12:06:14 +00:00
from ox.utils import json
from ox.cache import read_url
2010-12-29 12:06:14 +00:00
def find(query, timeout=ox.cache.cache_timeout):
2010-12-31 07:23:24 +00:00
if isinstance(query, unicode):
query = query.encode('utf-8')
2010-12-31 07:32:22 +00:00
params = urllib.urlencode({'q': query})
2010-12-29 12:06:14 +00:00
url = 'http://duckduckgo.com/html/?' + params
2013-06-01 11:21:13 +00:00
data = read_url(url, timeout=timeout).decode('utf-8')
2010-12-29 12:06:14 +00:00
results = []
2013-06-01 10:25:20 +00:00
regex = '<a .*?class="large" href="(.+?)">(.*?)</a>.*?<div class="snippet">(.*?)</div>'
2010-12-29 12:06:14 +00:00
for r in re.compile(regex, re.DOTALL).findall(data):
results.append((strip_tags(decode_html(r[1])), r[0], strip_tags(decode_html(r[2]))))
2010-12-29 12:06:14 +00:00
return results