1.网站js文件获取

++++++++++++++++++++++

pls,input your domain like: http://111.com

 

#coding:utf8
#encoding=utf8
import requests
import sys
import re
reload(sys)
sys.setdefaultencoding( "utf-8" )
def getjs2(html):
    reg=r'src="(.*?)"'
    listre=re.compile(reg)
    mylist=re.findall(listre,html.strip())
    return mylist
def getdomain(url):
    reg=r'://(.*?)/'
    listre=re.compile(reg)
    mylist=re.findall(listre,url)
    #print mylist[0]
    return mylist

headers={
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64; rv:56.0) Gecko/20100101 Firefox/56.0',
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
    'Accept-Language': 'zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3',
    'Content-Type': 'application/x-www-form-urlencoded',
    #'Referer': 'http://xlab.tencent.com/special/spectre/spectre_check.html',
    'Upgrade-Insecure-Requests': '1',
    'Cookie': 'pgv_pvid=4723488520'
}
if len(sys.argv)>1:
    url=sys.argv[1]
    str1=url.split('/')[-1:][0]
    url=url.replace(str1,'')
    try:
        #print str1
        url2=sys.argv[1]    
        html=requests.get(url2,headers=headers,timeout=5)
        #print 'target\'s stratus:'+str(html.status_code)
        html=html.text.replace("'",'"')
        #print html.encode("utf-8",'ignore')
        for i in getjs2(html):
            #print i
            if i.find(".js")>0:
                if i.find("http://")>=0 or i.find("https://")>=0 or i.find("//")>=0 :
                    murl=i
                    print murl
                elif i.find("/")==0:
                    murl=url.split('/')[0]+'//'+getdomain(url)[0]+i
                    print murl
                else:
                    i=i.split(".js")[0]
                    murl=url+'/'+i+'.js'
                    murl=murl.replace('//','/')
                    print murl
    except Exception as e:
        print e

else:
    print 'pls,input your domain like: http://111.com'

 

转载于:https://www.cnblogs.com/crac/p/8215466.html