1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61

from flask import Flask, request, jsonify
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
import jieba
import joblib

app = Flask ( __name__ )

# === 1. 准备数据 ===
texts = [
    # 正常内容
    "我爱学习人工智能",
    "今天真开心",
    "你好，朋友",
    "祝你生活愉快",
    "我喜欢听音乐",
    "看电影真有趣",
    "一起打游戏吧",
    "美丽的风景让人心情愉快",

    # 敏感内容
    "买枪支弹药请加我",
    "出售身份证",
    "这是黄色网站链接",
    "成人内容免费看",
    "黄色小说推荐",
    "如何制作炸弹",
    "赌博网站登录入口",
    "免费看黄片"
]

labels = [0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1]  # 0=正常，1=敏感


# === 2. 中文分词函数 ===
def chinese_tokenizer(text):
    return jieba.lcut ( text )


# === 3. 向量化 + 训练模型 ===
vectorizer = TfidfVectorizer ( tokenizer=chinese_tokenizer )
X = vectorizer.fit_transform ( texts )
model = MultinomialNB ()
model.fit ( X, labels )

# === 4. 保存模型（方便部署） ===
joblib.dump ( vectorizer, 'vectorizer.pkl' )
joblib.dump ( model, 'model.pkl' )


@app.route ( "/predict", methods=["POST"] )
def predict():
    data = request.get_json ()
    text = data.get ( "text", "" )
    X_new = vectorizer.transform ( [text] )
    pred = model.predict ( X_new )[0]
    return jsonify ( {"sensitive": bool ( pred )} )


if __name__ == "__main__":
    app.run ( port=5001 )