python的spider如何让鼠标不_python wooyun爬虫&&模拟鼠标等

，今天我们就来谈谈python在爬虫及实际应用方面的小技巧

一、python爬取wooyun镜像站文章

代码放出来吧，两个程序，一个抓来图片放在本地，一个抓来页面源码：

wooyun_spider:

[Python] 纯文本查看 复制代码#coding: utf-8

import requests

from bs4 import BeautifulSoup

import re

import os

def dopost(url):

r = requests.get(url, timeout=6)

if r.status_code == 200:

return r.content

def bsparser(content):

soup = BeautifulSoup(content, 'html.parser', from_encoding='utf-8')

bqs = soup.find_all('a', href=re.compile(r'/wooyun\-\d+\-\d+\.html'))

return bqs

dic = {}

if __name__ == '__main__':

if os.path.exists(r'd:\wooyun'):

print 'd://wooyun dir exists...spider begin'

else:

os.mkdir(r'd:\wooyun')

print 'mkdir d://wooyun...spider begin'

for i in range(1,5):

ii = '%d' % i

url = 'http://wy.hxsec.com/search?keywords=&&content_search_by=by_bugs&&search_by_html=False&&page=' + ii

content = dopost(url)

bqs = bsparser(content)

for bq in bqs:

dic[bq.get_text()] = bq['href']

#for k in dic.keys ;for v in dic.values ;

for (k, v) in dic.items():

#print k, v

try:

con = dopost(v)

file_str = 'd://wooyun/