python-ox/ox/web/google.py

38 lines
1.1 KiB
Python

# -*- coding: utf-8 -*-
# vi:si:et:sw=4:sts=4:ts=4
import re
import urllib
import ox
from ox import stripTags
DEFAULT_MAX_RESULTS = 10
DEFAULT_TIMEOUT = 24*60*60
def readUrlUnicode(url, data=None, headers=ox.net.DEFAULT_HEADERS, timeout=DEFAULT_TIMEOUT):
return ox.cache.readUrlUnicode(url, data, headers, timeout)
def quote_plus(s):
if not isinstance(s, str):
s = s.encode('utf-8')
return urllib.quote_plus(s)
def find(query, max_results=DEFAULT_MAX_RESULTS, timeout=DEFAULT_TIMEOUT):
"""
Return max_results tuples with title, url, description
>>> find("The Matrix site:imdb.com", 1)[0][0]
u'The Matrix (1999) - IMDb'
>>> find("The Matrix site:imdb.com", 1)[0][1]
u'http://www.imdb.com/title/tt0133093/'
"""
url = 'http://google.com/search?q=%s' % quote_plus(query)
data = readUrlUnicode(url, timeout=timeout)
results = []
for a in re.compile('<a href="(\S+?)" class=l .*?>(.*?)</a>').findall(data):
results.append((stripTags(a[1]), a[0], ''))
if len(results) >= max_results:
break
return results