更新 260326 2509165026.py

260326 2509165026.py

@@ -1,26 +1,42 @@
 import requests
 from bs4 import BeautifulSoup
+import json
+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"
+}
 
+movies = []
+for page in range(2):
+    url = f"https://movie.douban.com/top250?start={page*25}"
+    response = requests.get(url, headers=headers)
+    soup = BeautifulSoup(response.text, "html.parser")
     
-url = f'https://picsum.photos/'
+    items = soup.find_all("div", class_="item")
+    for idx, item in enumerate(items):
     
-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'}
+        rank = page * 25 + idx + 1
         
-response = requests.get(url, headers=headers,timeout=10)
-response.encoding = 'utf-8'
-soup = BeautifulSoup(response.text, 'html.parser')
+        title = item.find("span", class_="title").text.strip()
         
-img_tags = soup.select('img.resize')
-for i, img_tag in enumerate(img_tags[:5]):
-    img_src = img_tag.get('src')
-    print(f"正在下载第 {i+1} 张图片：{img_src}")
-    img_respnse = requests.get(img_src,headers=headers, timeout=10)
+        info_text = item.find("div", class_="bd").p.text.strip()
+        actors_line = info_text.split("\n")[0] if "\n" in info_text else info_text
+        actors = actors_line.split("主演: ")[-1].strip() if "主演: " in actors_line else "未知主演"
         
+        short_comment_tag = item.find("span", class_="inq")
+        short_comment = short_comment_tag.text.strip() if short_comment_tag else "暂无短评"
         
-    img_response = requests.get(img_src, timeout=10)
+        movies.append({
+            "rank": rank,
+            "title": title,
+            "actors": actors,
+            "short_comment": short_comment
+        })
     
-    with open('image.jpg', 'wb') as f:
-        f.write(img_response.content)
-        print("下载完成")
+    time.sleep(1)
 
+with open("movies.json", "w", encoding="utf-8") as f:
+    json.dump(movies, f, ensure_ascii=False, indent=4)
+
+print("✅ 数据采集完成，已保存到 movies.json")