python--wooyun pdf documnet download script

The following code :html

#!/usr/bin/env python
#coding:utf-8
#__author__:Bing

from bs4 import BeautifulSoup
import requests,re,random,threading,time
import pdfkit

USER_AGENTS = ["Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; AcooBrowser; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",\
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; Acoo Browser; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)",\
"Mozilla/4.0 (compatible; MSIE 7.0; AOL 9.5; AOLBuild 4337.35; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",\
"Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US)",\
"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)",\
"Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)",\
"Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)",\
"Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) AppleWebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)",\
"Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6",\
"Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/20070215 K-Ninja/2.1.1",\
"Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/20080705 Firefox/3.0 Kapiko/3.0",\
"Mozilla/5.0 (X11; Linux i686; U;) Gecko/20070322 Kazehakase/0.4.5",\
"Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.8) Gecko Fedora/1.9.0.8-1.fc10 Kazehakase/0.5.6",\
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",\
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3) AppleWebKit/535.20 (KHTML, like Gecko) Chrome/19.0.1036.7 Safari/535.20",\
"Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; fr) Presto/2.9.168 Version/11.52",\
]

def random_useragent():
    return random.choice(USER_AGENTS)

def get_wooyun(int):
    headers = { "Accept":"text/html,application/xhtml+xml,application/xml;",
                "Accept-Encoding":"gzip",
                "Accept-Language":"zh-CN,zh;q=0.8",
                "Referer":"http://www.baidu.com",
                "User-Agent":str(random_useragent())
                } 
    url = "http://www.wooyun.org/bugs/new_public/page/%d" % int
    data = requests.get(url,headers=headers)
    soup = BeautifulSoup(data.text,"html5lib")
    tags_a =soup.findAll(name="tr")
    for i in tags_a[1:]:
        name = str(i.td.a.attrs["href"]).split("/")[2]  #input database file_url
        url = str("http://www.wooyun.org"+i.td.a.attrs["href"])
        print name,url
        pdfkit.from_url(url,name+'.pdf')


start_time = time.time()
for i in range(1,2001):
    try:
        get_wooyun(i)
    except:
        print "Error Information: %s" % i


end_time = time.time() 
print end_time-start_time

Picture as below:html5

相關文章
相關標籤/搜索