python解析代理

来源：互联网发布：pdf转换word软件编辑：程序博客网时间：2024/06/14 04:25

import requestsfrom bs4 import BeautifulSoupproxy_list = []headers = {    'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36',    'Cookie':'_free_proxy_session=BAh7B0kiD3Nlc3Npb25faWQGOgZFVEkiJTY2OTIwMmE3ODU2NDViYTFlZDRiNTJhOWQwOTBmMTRhBjsAVEkiEF9jc3JmX3Rva2VuBjsARkkiMU5nZGN5S3ZheEpmV1owcFkvblZFWjVHdTdWZ0NHdXZac1Z1Skh2S3pxc2s9BjsARg%3D%3D--304ab96df8cd6042700bfcae3bb226199d246fc1; CNZZDATA1256960793=66246918-1478613112-%7C1478613112'}for i in range(1,5):    urls = 'http://www.xicidaili.com/nn/{}'.format(str(i))    content = requests.get(urls,headers = headers)    soup = BeautifulSoup(content.text,'lxml')    trs = soup.find_all('tr')    for tr in trs[1:]:        tds = tr.findAll('td')        ip = tds[1].text.strip()        port = tds[2].text.strip()        protocal = tds[5].text.strip()        if protocal == 'HTTP' or protocal == 'HTTPS':            # print('{}://{}:{}'.format(protocal,ip,port))            proxy_list.append('{}://{}:{}'.format(protocal,ip,port))for i in proxy_list:    print(i)

QQ 3351845519

0 0