网络数据采集（爬虫基础）

260324+2509165020.py.py

@@ -0,0 +1,35 @@
+import requests
+from bs4 import BeautifulSoup
+
+
+base_url = "https://www.douban.com/doulist/3936287/?start={}&sort=time&playable=0&sub_type="
+
+headers = {
+    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.110 Safari/537.36',
+    'Referer': 'https://www.douban.com/' }
+
+for page in range(10):
+    
+    start = page * 25
+    url = base_url.format(start)
+    
+    try:
+        
+        response = requests.get(url, headers=headers, timeout=10)
+        response.encoding = 'utf-8'
+        
+        
+        soup = BeautifulSoup(response.text, 'html.parser')
+     
+        items = soup.find_all('div', class_='doulist-item')
+        
+        print(f"===== 第 {page+1} 页 =====")
+        for item in items:
+            
+            title_tag = item.find('div', class_='title')
+            if title_tag and title_tag.a:
+                movie_title = title_tag.a.get_text(strip=True)
+                print(movie_title)
+                
+    except Exception as e:
+        print(f"第 {page+1} 页请求失败：{str(e)}")

260326+2509165020.py.py

@@ -0,0 +1,26 @@
+import requests
+from bs4 import BeautifulSoup
+headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.110 Safari/537.36'}
+
+for i in range(5):
+    try:
+        url = 'https://picsum.photos/'
+        response = requests.get(url, headers=headers, timeout=10)
+        response.encoding = 'utf-8'
+        soup = BeautifulSoup(response.text, 'html.parser')
+        img_tag = soup.select_one('img.resize')
+
+        if img_tag:
+            img_src = img_tag.get('src')
+            print(f"第 {i+1} 张图片链接: {img_src}")
+            img_response = requests.get(img_src, timeout=10)
+
+            with open(f'image_{i+1}.jpg', 'wb') as f:
+                f.write(img_response.content)
+
+        print(f"✅ 第 {i+1} 张下载完成！\n")
+
+    except Exception as e:
+        print(f"❌ 第 {i+1} 张下载失败: {e}\n")
+
+print("🎉 5 张图片全部下载完毕！")

爬虫2/爬虫课堂作业3.19.py.txt

@@ -0,0 +1,19 @@
+import requests
+from bs4 import BeautifulSoup
+url = 'https://movie.douban.com/top250'
+params = {'start': '0', 'filter': ''}  
+response = requests.get(url, params=params)
+if response.status_code == 200:
+    html_content = response.text
+    print("请求成功，获取到 HTML 内容")
+else:
+    print(f"请求失败，状态码: {response.status_code}")
+soup = BeautifulSoup(html_content, 'lxml')
+title = soup.find('title').string
+print("页面标题:", title)
+links = soup.find_all('a')
+for link in links:
+    print("链接地址:", link.get('href'))
+div_elements = soup.select('div.item')
+for div in div_elements:
+    print("电影条目内容:", div.text)