完成作业四：网络数据采集（爬虫基础)

26.03.24_27.py

@@ -0,0 +1,20 @@
+import requests
+from bs4 import BeautifulSoup
+header={'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36'}
+url = 'https://www.douban.com/doulist/3936288/'
+response = requests.get(url, headers=header, timeout=10)
+response.encoding = 'utf-8'
+print(response.status_code)
+soup = BeautifulSoup(response.text,'html.parser')
+movies=[]
+for a in soup.find_all('a'):
+    #print(a)
+    href = a.get('href','')
+    if '/subject' in href:
+        title = a.get_text(strip=True)
+        print(title)
+        movies.append(title)
+print('----------')
+print(movies)
+
+