python获取免费代理

import requests
from bs4 import BeautifulSoup
requests.packages.urllib3.disable_warnings()
from pytesseract import image_to_string
from string import ascii_lowercase
from random import choice

url = 'https://proxy.mimvp.com/free.php?proxy=in_socks'
headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36'
}
content = requests.get(url,headers=headers,verify=False).text
soup = BeautifulSoup(content,'lxml')
ips = soup.select('.tbl-proxy-ip')
proxyType = soup.select('.tbl-proxy-type')
ports = soup.select('.tbl-proxy-port')

def getIP():
    ipAll = []
    for ipHtml in ips[1:]:
        ip = ipHtml.contents
        ipAll.append(ip[0])
    return ipAll

def getPort():
    portAll = []
    hostUrl = 'https://proxy.mimvp.com/'
    for portHtml in ports:
        try:
            port = portHtml.img['src']
            completUrl = hostUrl+port
            imgBin = requests.get(completUrl).content
            imgFile = ''.join(choice(ascii_lowercase) for _ in range(5))+'.jpg'
            imgFileHandler = open(imgFile,'wb')
            imgFileHandler.write(imgBin)
            imgFileHandler.close()

            testdata_dir_config = '--tessdata-dir "C:\\Program Files (x86)\\Tesseract-OCR\\tessdata"'
            verifyCode = image_to_string(imgFile,lang='eng',config=testdata_dir_config)
            portAll.append(verifyCode)
        except:
            pass
    return portAll

def getProxyType():
    proxyTypes = []
    for typeHtml in proxyType:
        types = typeHtml.contents
        proxyTypes.append(types)
    return proxyTypes

allPort = getPort()
allIp = getIP()
types = getProxyType()
for i in range(len(allIp)):
    print allIp[i]+':'+allPort[i]+','+types[i]

  (1)需要安装:Tesseract-OCR;

  (2)为Tesseract-OCR设置环境变量

识别的时候有20%的可能将port识别为字母,也就是20%的出错率,因为代码中的代理网站的端口是图片形式提供,OCR识别会有一定出错。

posted @ 2018-07-25 11:17 webappsec93 阅读(...) 评论(...) 编辑 收藏