如何用Python for NLP自动标记和提取PDF文件中的关键信息？

import pdfplumber

def extract_text_from_pdf(file_path):
    with pdfplumber.open(file_path) as pdf:
        text = []
        for page in pdf.pages:
           text.append(page.extract_text())
    return text

file_path = "example.pdf"
text = extract_text_from_pdf(file_path)
print(text)

import nltk
from nltk.tokenize import word_tokenize
from nltk.corpus import stopwords
from nltk.stem import WordNetLemmatizer

def preprocess_text(text):
    # 分词
    tokens = word_tokenize(text)
    
    # 去除标点符号和停用词
    tokens = [token for token in tokens if token.isalpha() and token.lower() not in stopwords.words("english")]
    
    # 词形还原
    lemmatizer = WordNetLemmatizer()
    tokens = [lemmatizer.lemmatize(token) for token in tokens]
    
    return tokens

preprocessed_text = [preprocess_text(t) for t in text]
print(preprocessed_text)

from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.pipeline import Pipeline

# 假设我们有一个训练集，包含了已标记的文本和对应的标签
train_data = [("This is a positive text", "Positive"), 
              ("This is a negative text", "Negative")]

# 使用管道构建分类器模型
text_classifier = Pipeline([
    ("tfidf", TfidfVectorizer()),
    ("clf", MultinomialNB())
])

# 训练模型
text_classifier.fit(train_data)

# 使用模型进行预测
test_data = ["This is a test text"]
predicted_label = text_classifier.predict(test_data)
print(predicted_label)