这是一篇没什么用的blog,内容粘贴于百度。仅用于测试程序效果
实现定时自动访问某网址功能。
# !/usr/bin/env python
# -*- coding:utf-8 -*-
import requests
from lxml import etree
import time
def auto_click(url,num=1):
while num:
req_headers={
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.108 Safari/537.36'
}
# 获取最后一页的链接
resp=requests.get(url,headers=req_headers)
if resp.status_code==requests.codes.ok:
html=etree.HTML(resp.text)
last_page_link=html.xpath('//div[@class="pagelist"]/a[last()]/@href')[0]
# 获取最后一页的页码
# /topleeyap/article/list/4
last_page_num=int(last_page_link[-1])
# 构建所有页面的链接
base_page_link='http://blog.csdn.net/topleeyap/article/list/'
for i in range(1,last_page_num+1):
real_page_link=base_page_link+str(i)
# 提取本页所有文章链接
resp=requests.get(real_page_link,headers=req_headers)
if resp.status_code == requests.codes.ok:
html = etree.HTML(resp.text)
article_links=html.xpath('//span[@class="link_title"]/a/@href')
# 访问每一篇文章,模拟点击
for article_link in article_links:
real_article_link='http://blog.csdn.net'+article_link
requests.get(real_article_link,headers=req_headers)
print('正在第 [-{0}] 次点击 {1}'.format(num,real_article_link))
num -= 1
time.sleep(2)
if __name__ == '__main__':
num=50 # 运行次数,酌情修改
url='http://blog.csdn.net/topleeyap'
auto_click(url,num)