Created
October 14, 2010 17:12
-
-
Save bbelchak/626584 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from urllib2 import * | |
from HTMLParser import HTMLParser | |
class Googleit(HTMLParser): | |
""" | |
Simple Python API to google. Returns a single numbered result from a search string. | |
Usage: | |
result = Googleit(term, number) | |
""" | |
def __init__(self, search, resnum): | |
HTMLParser.__init__(self) | |
self.search = search.replace('','+') # Thanks s3r1al :) | |
self.resnum = resnum | |
self.links = [] | |
req = Request('http://www.google.co.uk/search?q=' + self.search) | |
req.add_header('User-Agent', 'Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10.5; en-US; rv:1.9.0.1) Gecko/2008070206 Firefox/3.0.1') | |
r = urlopen(req) | |
html = r.read() | |
self.feed(html) | |
self.result = self.links[18:][self.resnum-1] | |
def handle_starttag(self, tag, attrs): | |
if tag == 'a' and attrs: | |
if attrs[0][0] == 'href': | |
if attrs[0][1][:4] == 'http': | |
self.links.append(attrs[0][1]) | |
if __name__ == "__main__": | |
search_term = "let me google that for you" | |
resnum = 3 | |
result = Googleit(search_term, resnum) | |
print result.result |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment