#coding=utf-8
import random
import re
import time
import requests
from bs4 import BeautifulSoup
class ProxyHandler(object):
def __init__(self):
self.user_agent_list = [
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1",
"Mozilla/5.0 (X11; CrOS i686 2268.111.0) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6",
"Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6",
"Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1"
]
# 获取代理地址的网址
self.proxy_get_url = ‘http://www.xicidaili.com‘
# 目标地址
self.visit_url = ‘https://blog.csdn.net/t1623183652/article/details/73292150‘
# 获取能用的代理集合
self.proxy_list = []
# 请求超时时间为100s
self.timeout = 100
def get_proxy_list(self):
‘‘‘
解析得到需要的代理列表数据
:return:
‘‘‘
# 从self.user_agent_list中随机取出一个字符串
UA = random.choice(self.user_agent_list)
print(‘随机产生的UA是====%s‘ % UA)
headers = {
‘User-Agent‘: UA
}
response = requests.get(url=self.proxy_get_url, headers=headers, timeout=self.timeout)
html = response.text
# 获取<td></td>里面的所有内容
list = re.findall(r‘<td>(.*?)</td>‘, html)
for index in range(int(len(list) / 6)):
http = list[index * 6 + 3]
ip = list[index * 6]
port = list[index * 6 + 1]
# 过滤掉一些socket连接
if re.search(r‘(HTTP|HTTPS)‘, http) is None:
continue
proxy = ‘%s://%s:%s‘ % (http.lower(), ip, port)
self.proxy_list.append(proxy)
return (self.proxy_list) #80个代理ip
#获取文章的阅读量
def readnum(self,url,header,proxy_ip):
for i in range(5):
time.sleep(60) #时间过小不能实现准确的刷阅读量（10）
try:
req = requests.get(url,headers =header,proxies=proxy_ip)
soup = BeautifulSoup(req.text,‘lxml‘)
view = soup.select(‘#mainBox > main > div.blog-content-box > div.article-info-box > div > div > span‘)[0].getText()
print("第%d次:阅读量%s" %(i+1,view))
except requests.exceptions.ConnectionError:
print ("ConnectionError")
if __name__ == ‘__main__‘:
proxy_handler = ProxyHandler()
proxy_list=proxy_handler.get_proxy_list()
print (proxy_list)
proxy_ip={
‘http‘:random.choice(proxy_list).split(r"//")[1]
}
url =(‘https://blog.csdn.net/relocy/article/details/51533302‘) header = {‘User-Agent‘:‘Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36‘} proxy_handler.readnum(url,header,proxy_ip)--------------------- 作者：青霄 来源：CSDN 原文：https://blog.csdn.net/leiwuhen92/article/details/80370449 版权声明：本文为博主原创文章，转载请附上博文链接！