网络数据采集（爬虫基础）

0326+2509165015.py

@@ -0,0 +1,30 @@
+import requests
+from bs4 import BeautifulSoup
+import os
+if not os.path.exists('images'):
+    os.makedirs('images')
+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://picsum.photos/'
+try:
+    response = requests.get(url, headers=headers, timeout=10)
+    response.raise_for_status() 
+    soup = BeautifulSoup(response.text, 'html.parser')
+    img_tags = soup.find_all('img', class_='resize')
+    for index, img in enumerate(img_tags[:5]):
+        img_url = img.get('src')
+        if img_url:
+            if not img_url.startswith('http'):
+                img_url = f'https://picsum.photos{img_url}'
+            print(f"正在下载第 {index+1} 张图片: {img_url}")
+            img_response = requests.get(img_url, headers=headers, timeout=10)
+            img_response.raise_for_status()
+            img_name = f'images/image_{index+1}.jpg'
+            with open(img_name, 'wb') as f:
+                f.write(img_response.content)
+            print(f"✅ 保存成功: {img_name}")
+except requests.exceptions.RequestException as e:
+    print(f"网络请求出错: {e}")
+except Exception as e:
+    print(f"发生未知错误: {e}")