上传文件至 /

1.py

@@ -0,0 +1,65 @@
+import warnings
+warnings.filterwarnings("ignore", category=DeprecationWarning)
+warnings.filterwarnings("ignore", category=UserWarning)
+
+import pandas as pd
+import numpy as np
+from sklearn.model_selection import train_test_split
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.svm import LinearSVC
+from sklearn.metrics import accuracy_score, classification_report
+
+genre_dict = {
+    0: "剧情",
+    1: "喜剧",
+    2: "科幻",
+    3: "悬疑",
+    4: "动作",
+    5: "爱情",
+    6: "动画",
+    7: "犯罪",
+    8: "奇幻",
+    9: "纪录"
+}
+num_classes = len(genre_dict)
+
+def load_data(file_path="movie_data.csv"):
+    df = pd.read_csv(file_path)
+    texts = df["text"].astype(str).tolist()
+    labels = df["label"].astype(int).tolist()
+    return texts, labels
+
+def text_feature_extraction(texts):
+    vectorizer = TfidfVectorizer(
+        max_features=10000,
+        stop_words="english",
+        ngram_range=(1, 2)
+    )
+    features = vectorizer.fit_transform(texts)
+    return features, vectorizer
+
+def train_and_evaluate(features, labels):
+    X_train, X_test, y_train, y_test = train_test_split(
+        features, labels, test_size=0.2, random_state=42, stratify=labels
+    )
+    model = LinearSVC(random_state=42, max_iter=10000)
+    model.fit(X_train, y_train)
+    y_pred = model.predict(X_test)
+    acc = accuracy_score(y_test, y_pred)
+    print(f"测试集准确率: {acc:.4f}")
+    print("\n分类报告:")
+    print(classification_report(y_test, y_pred, target_names=genre_dict.values()))
+    return model
+
+def predict_genre(model, vectorizer, new_text):
+    new_feature = vectorizer.transform([new_text])
+    pred_label = model.predict(new_feature)[0]
+    return genre_dict[pred_label]
+
+if __name__ == "__main__":
+    texts, labels = load_data()
+    features, vectorizer = text_feature_extraction(texts)
+    model = train_and_evaluate(features, labels)
+    sample_text = "一个孤独的科学家发明了时间机器，却在穿梭时空的过程中陷入了悖论..."
+    print(f"\n示例文本: {sample_text}")
+    print(f"预测类型: {predict_genre(model, vectorizer, sample_text)}")

2.py

@@ -0,0 +1,43 @@
+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 = []
+# 豆瓣Top250每页25条，前50条需要爬取2页（start=0和start=25）
+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")
+    
+    items = soup.find_all("div", class_="item")
+    for idx, item in enumerate(items):
+        rank = page * 25 + idx + 1
+        # 电影名称
+        title = item.find("span", class_="title").text.strip()
+        # 主演信息
+        info = item.find("div", class_="bd").find("p", class_="").text.strip()
+        actors = info.split("\n")[0].split("主演:")[-1].strip() if "主演:" in info else "未知"
+        # 短评
+        quote_tag = item.find("span", class_="inq")
+        quote = quote_tag.text.strip() if quote_tag else "无短评"
+        
+        movies.append({
+            "rank": rank,
+            "title": title,
+            "actors": actors,
+            "quote": quote
+        })
+    
+    # 礼貌间隔，避免被反爬
+    time.sleep(1)
+
+# 保存为movies.json
+with open("movies.json", "w", encoding="utf-8") as f:
+    json.dump(movies, f, ensure_ascii=False, indent=2)
+
+print("爬取完成，数据已保存到 movies.json")

3.py

@@ -0,0 +1,32 @@
+import requests
+from bs4 import BeautifulSoup
+import csv
+import time
+
+# 1. 发送请求
+url = 'https://movie.douban.com/top250'
+headers = {'User-Agent': 'Mozilla/5.0...'}
+response = requests.get(url, headers=headers)
+
+# 2. 解析数据
+soup = BeautifulSoup(response.text, 'lxml')
+movies = []
+
+for item in soup.select('.item'):
+    title = item.select_one('.title').get_text()
+    rating = item.select_one('.rating_num').get_text()
+    quote = item.select_one('.inq').get_text() if item.select_one('.inq') else ''
+    
+    movies.append({
+        'title': title.strip(),
+        'rating': rating,
+        'quote': quote
+    })
+
+# 3. 保存为CSV
+with open('movies.csv', 'w', newline='', encoding='utf-8') as f:
+    writer = csv.DictWriter(f, fieldnames=['title', 'rating', 'quote'])
+    writer.writeheader()
+    writer.writerows(movies)
+
+print(f'已保存 {len(movies)} 部电影到 movies.csv')

movies.csv

@@ -0,0 +1,26 @@
+title,rating,quote
+肖申克的救赎,9.7,
+霸王别姬,9.6,
+泰坦尼克号,9.5,
+阿甘正传,9.5,
+千与千寻,9.4,
+美丽人生,9.5,
+星际穿越,9.4,
+这个杀手不太冷,9.4,
+盗梦空间,9.4,
+楚门的世界,9.4,
+辛德勒的名单,9.5,
+忠犬八公的故事,9.4,
+海上钢琴师,9.3,
+疯狂动物城,9.3,
+三傻大闹宝莱坞,9.2,
+机器人总动员,9.3,
+放牛班的春天,9.3,
+无间道,9.3,
+控方证人,9.6,
+寻梦环游记,9.1,
+大话西游之大圣娶亲,9.2,
+熔炉,9.3,
+触不可及,9.3,
+教父,9.3,
+末代皇帝,9.3,