Python-多线程爬虫实战，以csdn为例

代理限制问题，需要自己搭建代理池，否则效果不明显。

#!/usr/bin/env python

# -*- encoding: utf-8 -*-

'''
@Author  :   {Jack Zhao}

@Time    :   2019/9/3 17:46

@Contact :   {zc_dlmu@163.com}

@Desc    :  
'''

# !/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:
            # 构建所有页面的链接
            base_page_link='http://blog.csdn.net/weixin_40539952/article/list/'
            for i in range(2):
                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('//div[@class="article-list"]//h4/a/@href')

                    # 访问每一篇文章，模拟点击
                    for article_link in article_links:
                        real_article_link= 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=500   
    url='http://blog.csdn.net/weixin_40539952'
    auto_click(url,num)

多线程版本很简单，如下

#!/usr/bin/env python 
# -*- encoding: utf-8 -*-

'''
@Author  :   {Jack Zhao}
@Time    :   2020/05/08 17:46
@Contact :   {zc_dlmu@163.com}
@Desc    :   增加多线程功能
'''

# !/usr/bin/env python

# -*- coding:utf-8 -*-

import requests
import time
from lxml import etree
from threading import Thread


def auto_click(url="http://blog.csdn.net/weixin_40539952",num=500):
    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:
            # 构建所有页面的链接
            base_page_link='http://blog.csdn.net/weixin_40539952/article/list/'
            for i in range(4):
                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('//div[@class="article-list"]//h4/a/@href')
 
                    # 访问每一篇文章，模拟点击
                    for article_link in article_links:
                        real_article_link= article_link
                        print('正在第 [-{0}] 次点击 {1}'.format(num,real_article_link))
                        try:
                            requests.get(real_article_link,headers=req_headers)
                            print('OK!')
                        except:
                            print("wrong!")
        num -= 1
        time.sleep(2)

		
	
if __name__=='__main__':
	t_list = []
	for i in range(4):
		t = Thread(target = auto_click)
		t_list.append(t)
		t.start() #启动进程
		
	for t in t_list:
		t.join() #回收进程