简易爬虫爬取51job招聘信息

简易爬虫爬取51job招聘信息

目标:
——>入门级别

import re
questclass Grab(object):# 定义类属性num = 0def __init__(self):# 请求的网址self.url = ",000000,0000,00,9,99,python,2,1.html?"# 请求头self.headers = {"Host": "search.51job","User-Agent":"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 Safari/537.36"}def openurl(self):# 创建请求对象fin_url = quest.Request(url=self.url,headers=self.headers)# 请求网址read_data = quest.urlopen(fin_url)# 读取内容data = ad().decode("gbk")# 正则匹配字符,取出存放信息的链接mes_list = re.findall(r"jobs.51job.+.html", data)# 遍历存放链接的列表for i in mes_list:self.deal(i)def deal(self,url):# 请求取出的网址files = quest.urlopen(url)# 读取网站data = ad()# 正则匹配内容find_list = re.findall(r"<p>.*</p>",data.decode("gbk"))# 打开文件写入new_file = open("zhaopin"+"/"+str(Grab.num)+".txt","w")new_file.write(str(find_list))new_file.close()Grab.num += 1
def main():# 创建对象g = Grab()g.openurl()if __name__ == "__main__":main()