拉钩网数据抓取

Posted 2022-07-08 erick-l

import json
import re
import time

import requests
import multiprocessing


class HandleLaGou():
    def __init__(self):
        # 使用session保存cookies信息
        self.lagou_session = requests.Session()
        self.header = 
            ‘User-Agent‘: ‘Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_4) AppleWebKit/537.36 (Khtml, like Gecko) Chrome/75.0.3770.142 Safari/537.36‘
        
        self.city_list = ""

    # 获取全国所有城市列表的方法
    def handle_city(self):
        city_search = re.compile(r‘zhaopin/">(.*?)</a>‘)
        city_url = ‘https://www.lagou.com/jobs/allCity.html‘
        city_result = self.handle_request(method="GET", url=city_url)
        # 使用正则表达式获取城市列表
        self.city_list = city_search.findall(city_result)
        self.lagou_session.cookies.clear()  # 清除cookies
        # print(city_result)

    def handle_city_job(self, city):
        first_request_url = "https://www.lagou.com/jobs/list_python?city=%s&cl=false&fromSearch=true&labelWords=&suginput=" % city
        first_response = self.handle_request(method="GET", url=first_request_url)
        total_page_search = re.compile(r‘class="span\stotalNum">(\d+)</span>‘)
        try:
            total_page = total_page_search.search(first_response).group(1)
        # 由于没有岗位信息造成exception
        except:
            return
        else:
            for i in range(1, int(total_page) + 1):
                data = 
                    "pn":i,
                    "kd":"python"
                
                page_url = "https://www.lagou.com/jobs/positionAjax.json?px=default&city=%s&needAddtionalResult=false"% city
                referer_url = ‘https://www.lagou.com/jobs/list_python?&px=default&city=%s‘%city
                #referer_url需要进行encode
                self.header[‘Referer‘] = referer_url.encode()
                response = self.handle_request("POST",page_url,data=data,info=city)
                lagou_data = json.loads(response)
                job_list = lagou_data[‘content‘][‘positionResult‘][‘result‘]
                for job in job_list:
                    print(job)
        print(total_page)

    def handle_request(self, method, url, data=None, info=None):
        while True:
            #加入阿布云代理
            proxyinfo = "http://%s:%s@%s:%s"%(‘‘,‘‘,‘‘,‘‘)
            proxy = 
                "http":proxyinfo,
                "https":proxyinfo
            
            try:
                if method == "GET":
                    response = self.lagou_session.get(url=url, headers=self.header,proxies=proxy,timeout=6)
                elif method =="POST":
                    response = self.lagou_session.post(url=url, headers=self.header,data=data,proxies=proxy,timeout=6)
            except:
                # 需先清除cookies信息，然后重新获取
                self.lagou_session.cookies.clear()
                first_request_url = "https://www.lagou.com/jobs/list_python?city=%s&cl=false&fromSearch=true&labelWords=&suginput=" % info
                self.handle_request(method="GET", url=first_request_url)
                time.sleep(10)
                continue
            response.encoding = ‘utf-8‘
            if ‘频繁‘ in response.text:
                print("频繁")
                #需先清除cookies信息，然后重新获取
                self.lagou_session.cookies.clear()
                first_request_url = "https://www.lagou.com/jobs/list_python?city=%s&cl=false&fromSearch=true&labelWords=&suginput=" % info
                self.handle_request(method="GET", url=first_request_url)
                time.sleep(10)
                continue
            return response.text


if __name__ == ‘__main__‘:
    lagou = HandleLaGou()
    # 所有城市方法
    lagou.handle_city()
    #引入多进程，加速抓取
    pool = multiprocessing.Pool(2)
    
    for city in lagou.city_list:
        pool.apply_async(lagou.handle_city_job,args=(city,))
        
    pool.close()
    pool.join()