完成作业X

2509165012罗欣怡.py

@@ -0,0 +1,28 @@
+import requests
+from bs4 import BeautifulSoup
+
+url = "https://www.douban.com/doulist/3936288/?start={}&sort=time&playable=&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'
+}
+
+response = requests.get(url, headers=headers, timeout=10)
+response.encoding = 'utf-8'
+soup = BeautifulSoup(response.text, 'html.parser')
+
+# print(soup)
+print("--------------------------")
+print("--------------------------")
+print("--------------------------")
+
+for page in range(10):
+    a = page*25
+    url = f"https://www.douban.com/doulist/3936288/?start={a}&sort=time&playable=&sub_type="
+    
+    print(f"爬取第{page}页内容")
+    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)