pachongwanchen

1243/爬虫.py.txt

@@ -0,0 +1,30 @@
+import requests
+from bs4 import BeautifulSoup as bs
+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"
+}
+
+url = 'https://www.baidu.com'
+params = {'key':'value'}  
+
+try:
+    response = requests.get(url, params=params, headers=headers, timeout=5)
+    response.raise_for_status()
+    print("״̬<D7B4><CCAC>:", response.status_code)
+    print('-'*20)
+
+    html_content = response.text
+    soup = bs(html_content, 'lxml')
+    title = soup.find('title').string
+    print("ҳ<><D2B3><EFBFBD><EFBFBD><EFBFBD><EFBFBD>:", title)
+    print('='*20)
+    links = soup.find_all('a')
+    for link in links:
+        href = link.get('href')
+        if href: 
+            print("<22><><EFBFBD><EFBFBD>:", href)
+    print('='*20)
+except requests.exceptions.RequestException as e:
+    print(f"<22><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>: {e}")
+except Exception as e:
+    print(f"<22><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>: {e}")