3.31

爬虫3.31.py

@@ -0,0 +1,24 @@
+import requests
+from bs4 import BeautifulSoup
+
+url = "https://movie.douban.com/top250?start=0&filter="
+
+headers = {'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'}
+
+requests = requests.get(url, headers=headers,timeout =10)
+requests.encoding = 'utf-8'
+
+html = requests.text
+
+pattern = r'<span>{{= sub_title}}</span>'
+titles = re.findall(pattern, html)
+
+chinese_titles = [t for t in titles if not t.startswith('/')]
+
+top10 = chinese_titles[:10]
+
+with open('movies.txt', 'w', encoding='utf-8') as f:
+    for i, title in enumerate(top10, 1):
+        f.write(f'{i}. {title}\n')
+
+print('已保存前10部电影到 movies.txt')