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)}")

260324+2509165020.py/260324+2509165020.txt

@@ -1,29 +0,0 @@
-import requests
-from bs4 import BeautifulSoup
-import time
-BASE_URL = "https://www.douban.com/doulist/3936288/" 
-START_PAGE = 1                          
-END_PAGE = 100                          
-HEADERS = {
-    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"
-}
-
-def crawl_page(page):
-    url = f"{BASE_URL}{page}"
-    try:
-        resp = requests.get(url, headers=HEADERS, timeout=10)
-        resp.raise_for_status()
-        soup = BeautifulSoup(resp.text, "html.parser")
-        items = soup.find_all("div", class_="item")
-        for item in items:
-            title = item.find("h3").get_text(strip=True)
-            print(title) 
-        print(f"<22><> {page} ҳ<><D2B3>ȡ<EFBFBD><C8A1><EFBFBD><EFBFBD>")
-
-    except Exception as e:
-        print(f"<22><> {page} ҳ<><D2B3><EFBFBD><EFBFBD><EFBFBD><EFBFBD>{e}")
-
-if __name__ == "__main__":
-    for page in range(START_PAGE, END_PAGE + 1):
-        crawl_page(page)
-        time.sleep(1)