代码

code

@@ -0,0 +1,22 @@
+import requests
+from lxml import etree
+f=open('advertise.txt','w',encoding='utf-8')
+def run(url):
+    headers={'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.212 Safari/537.36 Edg/90.0.818.62'}
+    r=requests.get(url,headers=headers)
+    r.encoding='utf-8'
+    html=r.text
+    doc=etree.HTML(html) 
+    divs=doc.xpath('/html/body/div[15]/div[1]/div[1]/div[@class="jobsList"]')   
+    for div in divs:
+        zhiwei = div.xpath('.//div[@class="mouseListenTop clearfix"]//a/text()')[0].strip()
+        gongsi = div.xpath('.//div[@class="jobRight"]//a/text()')[0].strip()  
+        yuexin = div.xpath('.//span[@class="salaryList"]/text()')[0].strip()
+        diqu = div.xpath('.//span[@class="cityConJobsWork"]/text()')[0].strip()
+        riqi = div.xpath('.//span[@class="time"]/text()')[0].strip()
+        f.write(zhiwei+'|'+gongsi+'|'+yuexin+'|'+diqu+'|'+riqi+'\n')     
+for i in range(1,3):
+    url='https://www.job001.cn/jobs?pageNo='+str(i)
+    run(url)
+f.close()
+!cat advertise.txt