Fri May 19 09:17:00 UTC 2023 inscode

main.py

@@ -7,20 +7,22 @@ from lxml import etree
 import requests
 from bs4 import BeautifulSoup
 
-url = 'http://yz.yuzhuprice.com:8003/findPriceByName.jspx?page.curPage=1&priceName=%E7%BA%A2%E6%9C%A8%E7%B1%BB'
 headers = {
     'User-Agent': "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.129 Safari/537.36",
 }
-response = requests.get(url,headers=headers,timeout=10)
+for x in range(1,3):
+    url = 'http://yz.yuzhuprice.com:8003/findPriceByName.jspx?page.curPage={}&priceName=%E7%BA%A2%E6%9C%A8%E7%B1%BB'.format(x)
 
-# soup = BeautifulSoup(response.content, 'html.parser')
+    response = requests.get(url,headers=headers,timeout=10)
 
-# for link in soup.find_all('a'):
-#     print(link.get('href'))
-html = response.text
-parse = etree.HTML(html) 
-all_tr = parse.xpath('//*[@id="173200"]')
-for tr in all_tr:
+    # soup = BeautifulSoup(response.content, 'html.parser')
+
+    # for link in soup.find_all('a'):
+    #     print(link.get('href'))
+    html = response.text
+    parse = etree.HTML(html) 
+    all_tr = parse.xpath('//*[@id="173200"]')
+    for tr in all_tr:
         tr = {
             'name': ''.join(tr.xpath('./td[1]/text()')).strip(),
             'price': ''.join(tr.xpath('./td[2]/text()')).strip(),
@@ -28,4 +30,6 @@ for tr in all_tr:
             'supermaket': ''.join(tr.xpath('./td[4]/text()')).strip(),
             'time': ''.join(tr.xpath('./td[5]/text()')).strip()
         }
+        print(tr)
+