py

pac2.py

@@ -0,0 +1,32 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Fri Jun 11 16:55:39 2021
+
+@author: 86158
+"""
+
+
+import requests
+from lxml import etree
+
+with open('advertise.txt', 'w', encoding='utf-8') as f:
+    for i in range(3):
+        url = 'https://www.job001.cn/jobs?pageNo=1'+str(i)
+        headers = {
+            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.111 Safari/537.36"
+        }
+        r=requests.get(url=url,headers=headers)
+        r.encoding = 'utf-8'
+        html=r.text
+        doc = etree.HTML(html)
+        content1=doc.xpath('//div[@class="mouseListenTop clearfix"]/a/text()')
+        content2=doc.xpath('//div[@class="jobRight"]/dl/dt/a/text()')
+        content3=doc.xpath('//div[@class="mouseListenTop clearfix"]/span/text()')
+        content4=doc.xpath('//span[@class="salaryList"]/text()')
+        content5=doc.xpath('//span[@class="cityConJobsWork"]/text()')
+        
+        for i in range(0,len(content1)):
+            f.write(content1[i]+'|'+content2[i]+'|'+content4[i]+'|'+content5[i]+'|'+content3[i]+'\n')
+            print(content1[i]+'|'+content2[i]+'|'+content4[i]+'|'+content5[i]+'|'+content3[i]+'\n')
+
+