Shulou(Shulou.com)06/03 Report--

Python uses Baidu to do url collection

pip install tableprint

paramiko==2.0.8

Syntax: python url_collection.py -h Output help information

python url_collection.py Information to collect-p Number of pages-t Number of processes-o File name and format saved

New file touch url_collection.py

Write the formal part of the code

#coding: utf-8

import requests

from bs4 import BeautifulSoup as bs

import re

from Queue import Queue

import threading

from argparse import ArgumentParser

logo="""

u u l | ccccc ooooo l l eeeeee cccccc ttttttt

u u r rr l | c o o l l e c t

u u r r r l | c o o l l eeeeee c t

u u r l | c o o l l e c t

u u u r l | c o o l l e c t

uuuuuuuu u r lllll | ccccc ooooo llllll lllll eeeeee cccccc t

By : Snow wolf

"""

print(logo)

arg = ArgumentParser(description='baidu_url_collect py-script by snowwolf')

arg.add_argument('keyword',help='keyword like inurl:.? id= for searching sqli site')

arg.add_argument('-p','--page', help='page count', dest='pagecount', type=int)

arg.add_argument('-t','--thread', help='the thread_count', dest='thread_count', type=int, default=10)

arg.add_argument('-o','--outfile', help='the file save result', dest='outfile', default='result.txt')

result = arg.parse_args()

headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64; rv:50.0) Gecko/20100101 Firefox/50.0'}

class Bd_url(threading.Thread):

def init(self, que):

threading.Thread.init(self)

self._ que = que

def run(self): while not self._ que.empty(): URL = self._ que.get() try: self.bd_url_collect(URL) except Exception,e: print e passdef bd_url_collect(self, url): r = requests.get(url, headers=headers, timeout=3) soup = bs(r.content, 'lxml', from_encoding='utf-8') bqs = soup.find_all(name='a', attrs={'data-click':re.compile(r'. '), 'class':None}) for bq in bqs: r = requests.get(bq['href'], headers=headers, timeout=3) if r.status_code == 200: print r.url with open(result.outfile, 'a') as f: f.write(r.url + '\n')

def main():

thread = []

thread_count = result.thread_count

que = Queue()

for i in range(0,(result.pagecount-1)*10,10):

que.put('https://www.baidu.com/s? wd=' + result.keyword + '&pn=' + str(i))

for i in range(thread_count): thread.append(Bd_url(que))for i in thread: i.start()for i in thread: i.join()

if name == 'main':

main()

code end on

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.