完成作业爬虫三种形式

wenben.txt

@@ -0,0 +1,44 @@
+import requests
+import re
+import time
+
+headers = {
+    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36'
+}
+
+all_chinese_titles = []
+
+# ѭ<><D1AD><EFBFBD><EFBFBD>ȡ10ҳ<30><D2B3>ÿҳ25<32><35><EFBFBD><EFBFBD><EFBFBD><EFBFBD>250<35><30><EFBFBD><EFBFBD>
+for page in range(10):
+    start = page * 25
+    url = f'https://movie.douban.com/top250?start={start}&filter='
+    print(f'<27><><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ȡ<EFBFBD><C8A1> {page+1} ҳ...')
+    
+    try:
+        response = requests.get(url, headers=headers)
+        response.raise_for_status()  # <20><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>Ƿ<EFBFBD><C7B7>ɹ<EFBFBD>
+        html = response.text
+        
+        # <20><><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ȡ<EFBFBD><C8A1><EFBFBD>е<EFBFBD>Ӱ<EFBFBD><D3B0><EFBFBD><EFBFBD>
+        pattern = r'<span class="title">([^<&]+)</span>'
+        titles = re.findall(pattern, html)
+        
+        # <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('/')]
+        all_chinese_titles.extend(chinese_titles)
+        
+        time.sleep(1)  # <20>ӳ<EFBFBD>1<EFBFBD>룬<EFBFBD><EBA3AC><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>챻<EFBFBD><ECB1BB>
+    except Exception as e:
+        print(f'<27><> {page+1} ҳ<><D2B3>ȡʧ<C8A1><CAA7>: {e}')
+        break
+
+# <20><><EFBFBD>浽<EFBFBD>ı<EFBFBD><C4B1>ļ<EFBFBD>
+with open('douban_top250.txt', 'w', encoding='utf-8') as f:
+    for i, title in enumerate(all_chinese_titles, 1):
+        f.write(f'{i}. {title}\n')
+
+print(f'<27>ѳɹ<D1B3><C9B9><EFBFBD><EFBFBD><EFBFBD>ȫ<EFBFBD><C8AB> {len(all_chinese_titles)} <20><><EFBFBD><EFBFBD>Ӱ<EFBFBD><D3B0> douban_top250.txt')
+
+# <20><>֤<EFBFBD><D6A4><EFBFBD><EFBFBD>
+with open('douban_top250.txt', 'r', encoding='utf-8') as f:
+    print(f.read())