python扒取西刺代理ip并使用ip访问网址

最新推荐文章于 2020-01-12 19:10:17 发布

浮华流年

最新推荐文章于 2020-01-12 19:10:17 发布

阅读量695

点赞数

文章标签： python 代理ip

本文链接：https://blog.csdn.net/m0_37971044/article/details/80496517

版权

from bs4 import BeautifulSoup
from urllib import request
import requests
import pymysql
import urllib

config = {
    'host':'127.0.0.1',
    'port':3306,
    'user':'root',
    'password':'root',
    'db':'test',
}
conn = pymysql.connect(**config)
cursor = conn.cursor()
header = {
'User-Agent':"Mozilla/5.0 (Windows NT 6.1; WOW64; rv:52.0) Gecko/20100101 Firefox/52.0"
}
url = 'http://www.xicidaili.com/'
data = requests.get(url,headers=header)
infos = data.content.decode('utf-8')
soup = BeautifulSoup(infos,'html.parser')
#print(soup)
ddd = soup.findAll('tr','odd')
#print(ddd)
n = 0
for dd in ddd:
    dlist = dd.findAll('td')
    ip = dlist[1].string
    port = dlist[2].string
    address = dlist[3].string
    type = dlist[5].string
    #print(ip)
    #print(port)
    #print(address)
    #print(type)
    if type == 'HTTP' or type=='HTTPS':
        n = n+1
        type = type.lower()
        urls = {
            type:ip+':'+port
        }
        data = requests.get(url,proxies=urls)
        if data:
            print(data.content.decode('utf-8'))
print(n)