并发爬取直聘网招聘信息

#并发爬取直聘网找招聘信息

import re
import json
import urllib
import urllib.parse  
from urllib.request import urlopen
from multiprocessing import Pool


def get_content(target_url):#获取页面信息
    headers = {'User-Agent': ' Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.67 Safari/537.36'}
    req = urllib.request.Request(url=target_url, headers=headers)
    content = urllib.request.urlopen(req).read().decode("utf-8")
    return content #把返回值给回调函数get_msg

def get_msg(content):
    obj = re.compile(r'ka="search_list_.*?<div class="job-title">(?P<job>.*?)</div>'
                     r'.*?<span class="red">(?P<salary>.*?)</span>'
                     r'.*?<p>(?P<adress>.*?)<em class="vline"></em>(?P<jingyan>.*?)<em class="vline"></em>(?P<xueli>.*?)</p>'
                     r'.*?target="_blank">(?P<company>.*?)</a></h3>', re.S)
    f=open("java.txt","a",encoding="utf-8")
    g = obj.finditer(content)
    for el in g:
        dic = {'job': el.group("job"), "salary": el.group("salary"), 'company': el.group("company")}
        # dic = {'job': el.group("job"), "salary": el.group("salary"), 'company': el.group("company"),
        #        "经验": el.group("jingyan"), "地址": el.group("adress"), "学历": el.group("xueli")}
        # dic = {'job': el.group("job"), "salary": el.group("salary"), 'company': el.group("company"),
        #        "经验": el.group("jingyan"), "地址": el.group("adress"), "学历": el.group("xueli")}
        print(dic)
        s = json.dumps(dic, ensure_ascii=False)
        f.write(s + "
")
    f.close()

if __name__ == '__main__':

    word = "开发"  #目标地址中的中文
    word = urllib.parse.quote(word)  #通过urllib.parse.quote(word）使得目标网址中的中文可以访问，进行爬取
    url_lst = []  # 装目标网址
    for i in range(1, 11):#循环得到10个目标网页
        url = "https://www.zhipin.com/c101280600/?query=Java%s&page=%s&ka=page-%s" % (word, i, i)
        url_lst.append(url)
    p=Pool(4)  #创建进程池，可以同时进行4个任务

    #目标任务有10个页面
    for url in url_lst:

       p.apply_async(get_content,args=(url,),callback=get_msg)

    p.close() #不在向进程池中添加任务
    p.join()  #主进程等到子进程的结束