From a6b143a6d35ebab3f89112b39bc27109283b2d76 Mon Sep 17 00:00:00 2001
From: po9eakyfz <3055861661@qq.com>
Date: Mon, 6 May 2024 14:34:51 +0800
Subject: [PATCH] ADD file via upload

---
 5.py | 49 +++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 49 insertions(+)
 create mode 100644 5.py

diff --git a/5.py b/5.py
new file mode 100644
index 0000000..3c3d388
--- /dev/null
+++ b/5.py
@@ -0,0 +1,49 @@
+import re
+import requests
+
+url_first = 'https://www.jxxdxy.edu.cn/news-list-xiaoyuanyaowen'
+url_last = '.html'
+urls = []
+urls.append(url_first + url_last)
+for i in range(2, 21):
+    urls.append(url_first + '-'+str(i) + url_last)
+
+# for url in urls:
+#     print(url)
+a = {
+    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML,like Gecko) Chrom/124.0.0.0 Safari/537.36 Edg/124.0.0.0'
+
+}
+# res = requests.get(urls[0], headers=a)
+# res.encoding = 'utf-8'
+
+# print(res.text)
+
+# for url in urls:
+#     response = requests.get(url, headers=a)
+#     print(response.status_code)
+#     print(response.encoding)
+lists = []
+for url in urls:
+    response = requests.get(url, headers=a)
+    lists.append(response.text)
+bd_re = '<li><a href="(.*?)" title="(.*?)".*?fr timee">(.*?)</span>'
+
+abc = []
+for text in lists:
+    result = re.findall(bd_re, text, re.S)
+    abc.append(result)
+    print(result)
+    print(len(result))
+
+# str = '产教融合'
+# for text in abc:
+#     for i in text:
+#         if str in i[1]:
+#             print(i)
+
+# time = '2024-03'
+# for text in abc:
+#     for i in text:
+#         if time in i[2]:
+#             print(i)
\ No newline at end of file