上传文件至 /

44.txt

@@ -0,0 +1,33 @@
+import requests
+import re
+
+# 1. <20><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ȡҳ<C8A1><D2B3>
+headers = {
+    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'
+}
+url = 'https://movie.douban.com/top250'
+
+response = requests.get(url, headers=headers)
+html = response.text
+
+# 2. <20><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʽ<EFBFBD><CABD>ȡ<EFBFBD><C8A1>Ӱ<EFBFBD><D3B0><EFBFBD><EFBFBD>
+# <20><>Ӱ<EFBFBD><D3B0><EFBFBD><EFBFBD><EFBFBD><EFBFBD> <span class="title"> <20><>
+pattern = r'<span class="title">([^<&]+)</span>'
+titles = re.findall(pattern, html)
+
+# 3. <20><><EFBFBD>˵<EFBFBD>Ӣ<EFBFBD><D3A2><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ֻ<EFBFBD><D6BB><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>
+chinese_titles = [t for t in titles if not t.startswith('/')]
+
+# ȡǰ10<31><30>
+top10 = chinese_titles[:10]
+
+# 4. <20><><EFBFBD>浽<EFBFBD>ı<EFBFBD><C4B1>ļ<EFBFBD>
+with open('movies.txt', 'w', encoding='utf-8') as f:
+    for i, title in enumerate(top10, 1):
+        f.write(f'{i}. {title}\n')
+
+print('<27>ѱ<EFBFBD><D1B1><EFBFBD>ǰ10<31><30><EFBFBD><EFBFBD>Ӱ<EFBFBD><D3B0> movies.txt')
+
+# <20><>ʾ<EFBFBD><CABE><EFBFBD><EFBFBD><EFBFBD><EFBFBD>֤
+with open('movies.txt', 'r', encoding='utf-8') as f:
+    print(f.read())