爬取乌云上所有人民币和乌云符号的漏洞（python脚本）

 import httplib
 from HTMLParser import HTMLParser
 import urlparse
 import urllib
 from bs4 import BeautifulSoup
 import re
 from time import sleep
 '''
 usage: 

 input your wooyun cookies,then just go crawl!!

 author: Elliott

 '''

 domain = 'wooyun.org'
 cookies = ''  # !!!!here   input your wooyun cookies
 user_agent = 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:29.0) Gecko/20100101 Firefox/29.0'

 def countnumber():  # the function to get page num
     global domain
     global cookies
     global user_agent
     conn = httplib.HTTPConnection(domain)
     conn.request('GET','/user.php?action=openbugs','',{'Cookie':cookies,'User-Agent':user_agent,'Referer':'http://wooyun.org/index.php','Host':'wooyun.org'})
     content = conn.getresponse()
     content = content.read()
     soup = BeautifulSoup(content)
     tag = soup.find_all('p',attrs={'class':'page'})
     if len(tag) == 0:
         tag = 'None'
     else:
         tag = str(tag[0])
     pattern = re.compile('>.*<a class=\"current\">')
     result = pattern.findall(tag)
     if len(result) == 0:
         result = 'None'
     else:
         result = str(result[0])
     number = filter(str.isdigit, result)
     num = number[5:]  #get then total page number
     return int(num)

 def dealthepage(content):
     global domain
     global cookies
     global user_agent
     conn = httplib.HTTPConnection(domain)
     soup = BeautifulSoup(content)
     k = soup.find_all('a')
     item = k[27:47]
     pattern = re.compile('href=\"(.+?)\"')
     hreaf = []
     for i in range(len(item)):
     ss = pattern.findall(str(item[i]))
         if len(ss) == 0:
             break
     hreaf.append(str(ss[0]))
     for i in hreaf:
         #sleep(0.5)
     conn.request('GET',i,'',{'Cookie':cookies,'User-Agent':user_agent,'Referer':'http://wooyun.org/index.php','Host':'wooyun.org'})
     content2 = conn.getresponse()
     content2 = content2.read()
     soup2 = BeautifulSoup(content2)
     imgtag = soup2.find_all(class_='credit')
     '''may be $ or cloud'''
     if len(imgtag) != 0:
         findcloud = re.compile('src=\"\/images\/credit\.png\"')
         findmoney = re.compile('src=\"\/images\/m(.?)\.png\"')
         cloudnum = findcloud.findall(content2)
         moneylevel = findmoney.findall(content2)
         cloud = 0
         money = 0
         if len(cloudnum) != 0:
             if len(cloudnum) == 1:
                 cloud = 1
             if len(cloudnum) == 2:
                 cloud = 2
             if len(cloudnum) == 3:
                 cloud = 3
         if len(moneylevel) != 0:
             if len(moneylevel) == 1:
                 money = 1
             if len(moneylevel) == 2:
                 money = 2
             if len(moneylevel) == 3:
                 money = 3
         title = soup2.findAll(attrs={"class":"wybug_title"})
         if len(title) == 0:
             title = 'No Title'
         else:
             title = str(title[0])
         deltag = re.compile('r<[^>]+>')
         title = deltag.sub('',title)
         author = soup2.findAll(attrs={"class":"wybug_author"})
         if len(author) == 0:
             author = 'No name'
         else:
             author = str(author[0])
         author = deltag.sub('',author)
         date = soup2.findAll(attrs={"class":"wybug_date"})
         if len(date) == 0:
             date = 'No time'
         else:
             date = str(date[0])
         date = deltag.sub('',date)
         link = "http://www.wooyun.org"+i
         link = str(link)
         f = open("test.html","a+")
         s = "<tr><td>level:cloud="+str(cloud)+"money="+str(money)+"</td><th>"+date+"</th><td><a href='"+link+"'>"+title+"</a></td><th>"+author+"</th></tr><br>"
         f.write(s)
         f.close

 if __name__ == '__main__':
     num = countnumber()  #get page num
     for i in range(num):
         conn = httplib.HTTPConnection(domain)
         conn.request('GET','/user.php?action=openbugs&pNO='+str(i+1),'',{'Cookie':cookies,'User-Agent':user_agent,'Referer':'http://wooyun.org/index.php','Host':'wooyun.org'})
         content = conn.getresponse()
         content = content.read()
         dealthepage(content)

附章效果图：