渗透测试——批量SRC节奏曲之无辜关键词url

左手的ㄟ右手 2021-07-26 01:36 213阅读 0赞

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzMzNjA4MDAw_size_16_color_FFFFFF_t_70]

--------------------

QQ 1274510382  
Wechat JNZ\_aming  
商业联盟 QQ群538250800  
技术搞事 QQ群599020441  
解决方案 QQ群152889761  
加入我们 QQ群649347320  
共享学习 QQ群674240731  
纪年科技aming  
网络安全 ,深度学习,嵌入式,机器强化,生物智能,生命科学。

叮叮叮：产品已上线 —>关注 官方-微信公众号——济南纪年信息科技有限公司  
民生项目：商城加盟/娱乐交友/创业商圈/外包兼职开发-项目发布/  
安全项目：态势感知防御系统/内网巡查系统  
云服项目：动态扩容云主机/域名/弹性存储-数据库-云盘/API-AIeverthing  
产品咨询/服务售后（同）

## 纸上得来终觉浅,绝知此事要躬行 ！！！   寻找志同道合伙伴创业中。。。抱团滴滴aming联系方式！! ##

--------------------

#### \#本文为广告系统自动投放广告 ####

#### \# 如有侵权 删改 请速速联系我们 ####

--------------------

import requests,time
    from lxml import etree
    import sys
    
    
    # 得到 HTML GET
    def Redirect(url):
        try :
            res = requests.get(url,timeout=10)
            url = res.url
        except Exception as e:
            print('出问题啦 ！！！！ ',e)
            time.sleep(1)
        return url
    
    
    def baidu_search(wd,pn_max,sav_file_name):
        url = 'http://www.baidu.com/s'
        return_set = set()
    
        for page in range(pn_max):
            pn = page * 10
            querystring = { 'wd': wd, 'pn': pn}
            headers = { 
                'pragma': 'no-cache',
                'accept-encoding': 'gzip,deflate,br',
                'accept-language': 'zh-CN,zh;q=0.8',
                'upgrade-insecure-requests': '1',
                'user-agent': "Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:62.0) Gecko/20100101 Firefox/62.0",
                'accept': "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
                'cache-control': "no-cache",
                'connection': "keep-alive",
            }
    
            # 构造请求
            try:
                response = requests.request('GET', url, headers=headers, params=querystring)
                print('构造百度url', response.url)
                selector = etree.HTML(response.text, parser=etree.HTMLParser(encoding='utf-8'))
            except Exception as e:
                print('页面加载失败', e)
                continue
    
            with open(sav_file_name, 'a+') as f:
                for i in range(1, 10):
                    try:
                        context = selector.xpath('//*[@id="' + str(pn + i) + '"]/h3/a[1]/@href')
                        print(len(context), context[0])
                        i = Redirect(context[0])
                        print('引擎爬虫 索引 内容 =' + context[0])
                        print(' 结果URL =' + i)
                        print("------------------------------------------------------------------------------")
                        f.write(i)
                        f.write('\n')
                        break
                        return_set.add(i)
                        f.write('\n')
                    except Exception as e:
                        print(i, return_set)
                        print('3', e)
    
        return return_set
    
    
    def deleone(oneurl):
    
        print("排除了"+ str(len(oneurl))+"个网址")
    
    
    
        urls = []
    
        with open(sys.path[0] + '/url.txt', 'r',encoding='utf-8') as f:
            for i in f:
                my_data = f.readline().strip()
                urls.append(my_data)
    
        for one in  oneurl:
            for url in urls:
                if one in url:
                    xxx  = urls.index(url)
                    urls.pop(xxx)
    
                else:
                    pass
        print("筛选完成【】：" + str(urls))
    
        open('url.txt','w')
        for i in urls:
            with  open('url.txt','a+') as  f:
                f.write(str(i)+'\n')
    
    
    
        return urls
    
    
    
    
    
    
    
    
    
    
    
    
    if __name__ == '__main__':
        wd = 'inurl:php?id='
        # 关键词
    
        pn = 100
        # 多少页
    
        save_file_name = 'url.txt'
    
        # 保存文件名
    
        return_set = baidu_search(wd, pn, save_file_name)
    
        oneurl = ["baidu.com", "sogou.com", "soso.com", "sina.com", "163.com", "bing.com", "letv.com", "weibo.com",
                  "sohu.com", "taobao.com", "paipai.com", "qq.com", "ifeng.com", "cntv.com", "icbc.com", "baike.com",
                  "douban.com",
                  "youtube.com", "ku6.com", "pptv.com", "56.com", "pps.tv", "docin.com", ]
        deleone(oneurl)

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzMzNjA4MDAw_size_16_color_FFFFFF_t_70]: /images/20210725/c5c150a468524afea5a53c73ca137d81.png