From 73d5077cf2594d23ebff641d72c430d643727a53 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E4=B8=81=E6=81=A9=E7=90=AA?=
 <2509165047@student.example.com>
Date: Thu, 26 Mar 2026 15:49:07 +0800
Subject: [PATCH] =?UTF-8?q?=E6=8F=90=E4=BA=A4=E7=88=AC=E8=99=AB=E4=BB=A3?=
 =?UTF-8?q?=E7=A0=81=20test.py?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 test.py | 31 +++++++++++++++++++++++++++++++
 1 file changed, 31 insertions(+)
 create mode 100644 test.py

diff --git a/test.py b/test.py
new file mode 100644
index 0000000..a5699a1
--- /dev/null
+++ b/test.py
@@ -0,0 +1,31 @@
+import requests
+from bs4 import BeautifulSoup
+
+a = 0
+url = f'https://www.douban.com/doulist/3936288/?start={a}&sort=time&playable=0&sub_type='
+
+headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.110 Safari/537.36'}
+
+# print(soup)
+# print('---------------------------I)
+# print('---------------------------')
+# print('')
+
+for page in range(10):
+    a = page*25
+    url = f'https://www.douban.com/doulist/3936288/?start={a}&sort=time&playable=0&sub_type='
+    print("爬取第{c}页内容".format(c=page+1))
+    response = requests.get(url, headers=headers, timeout=10)
+    response.encoding = 'utf-8'
+    soup = BeautifulSoup(response.text, 'html.parser')
+    print(soup)
+# for b in soup.find_all('a'):
+#   print(a)
+#   href = b.get('href','')
+#   if '/subject/' in href:
+#         title = b.get_text(strip=True)
+#         print(title)
+# //*[@id="17023343"]/div/div[2]/div[4]/a
+
+c = soup.select('p')
+print(c)