上传文件至 /

数据处理与标注.py

@@ -0,0 +1,25 @@
+import json
+
+# 1. 读取原始数据
+with open("movies.json", "r", encoding="utf-8") as f:
+    movies = json.load(f)
+
+# 2. 过滤掉quote为空的条目
+filtered_data = [
+    {
+        "id": movie["rank"],
+        "title": movie["title"],
+        "quote": movie["quote"]
+    }
+    for movie in movies
+    if movie["quote"].strip() != ""
+]
+
+print(f"过滤前：{len(movies)} 条")
+print(f"过滤后：{len(filtered_data)} 条")
+
+# 3. 保存为Label Studio可导入的格式
+with open("filtered_quotes.json", "w", encoding="utf-8") as f:
+    json.dump(filtered_data, f, ensure_ascii=False, indent=4)
+
+print("✅ 已生成 filtered_quotes.json，可直接导入Label Studio")

数据采集.py

@@ -0,0 +1,65 @@
+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/135.0.0.0 Safari/537.36",
+    "Referer": "https://movie.douban.com/top250"
+}
+
+movies_data = []
+
+# 豆瓣Top250前50条，需要爬2页（start=0和start=25）
+for start in range(0, 50, 25):
+    url = f"https://movie.douban.com/top250?start={start}"
+    print(f"正在爬取第 {start//25 + 1} 页...")
+    
+    # 发送请求
+    response = requests.get(url, headers=headers)
+    response.raise_for_status()  # 请求失败自动报错
+    soup = BeautifulSoup(response.text, "html.parser")
+    
+    # 提取所有电影条目
+    movie_items = soup.find_all("div", class_="item")
+    
+    for idx, item in enumerate(movie_items):
+        rank = start + idx + 1
+        
+        # 1. 电影名称
+        title_tag = item.find("span", class_="title")
+        title = title_tag.text.strip() if title_tag else ""
+        
+        # 2. 主演信息
+        actors = ""
+        bd_div = item.find("div", class_="bd")
+        if bd_div:
+            p_tag = bd_div.find("p")
+            if p_tag:
+                info_text = p_tag.text.strip()
+                if "主演:" in info_text:
+                    actors_part = info_text.split("主演:")[-1].strip()
+                    actors = actors_part.split("\n")[0].strip()
+        
+        # 3. 短评（适配当前页面的inq标签）
+        quote_tag = item.find("span", class_="inq")
+        quote = quote_tag.text.strip() if quote_tag else ""
+        
+        # 构造数据
+        movie_info = {
+            "rank": rank,
+            "title": title,
+            "actors": actors,
+            "quote": quote
+        }
+        movies_data.append(movie_info)
+        print(f"已获取：{rank}. {title} | 短评：{quote if quote else '无'}")
+    
+    # 每页爬完暂停2秒，避免请求过快被封
+    time.sleep(2)
+
+# 保存到movies.json
+with open("movies.json", "w", encoding="utf-8") as f:
+    json.dump(movies_data, f, ensure_ascii=False, indent=4)
+
+print("\n✅ 爬取完成！数据已保存到 movies.json")