Created
April 26, 2012 16:12
-
-
Save anonymous/2500652 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
import urllib2 | |
import simplejson | |
import re | |
import requests | |
from bs4 import BeautifulSoup | |
from random import choice | |
# The request also includes the userip parameter which provides the end | |
# user's IP address. Doing so will help distinguish this legitimate | |
# server-side traffic from traffic which doesn't come from an end-user. | |
id = "hotdog" # dynamic id from site | |
url = ('https://ajax.googleapis.com/ajax/services/search/web' | |
'?v=1.0&q='+ id + '&userip=USERS-IP-ADDRESS') | |
request = urllib2.Request(url, None, {'Referer': "www.google.com" }) | |
response = urllib2.urlopen(request) # opening url | |
# Process the JSON string. | |
results = simplejson.load(response) | |
results = results["responseData"] | |
results = results['cursor'] | |
results = results["moreResultsUrl"] | |
print results | |
#results = results['resultCount'] | |
#regex to add number to results | |
split = re.split("start=0", results) | |
newurl= split[0] + "start=100" +split[1] | |
print "found!!!"+ newurl | |
r = requests.get(newurl) | |
# print r.status_code | |
# print r.headers['content-type'] | |
r= r.text | |
soup = BeautifulSoup(r) | |
all=[] | |
for link in soup.find_all("a"): | |
all.append(link.get("href")) | |
for s in all: | |
if re.findall("/url?", s): | |
split1 = re.split("&", s) | |
split2 =re.split("=", split1[0]) | |
deathlinks=[] | |
sp =(split2[1]).split("//n") | |
print sp[0] | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment