Bagaimana untuk mengekstrak ayat utama daripada fail PDF menggunakan Python untuk NLP?

pip install nltk

pip install pdfminer.six

from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.pdfpage import PDFPage
from io import StringIO

def convert_pdf_to_text(file_path):
    resource_manager = PDFResourceManager()
    string_io = StringIO()
    laparams = LAParams()
    device = TextConverter(resource_manager, string_io, laparams=laparams)
    interpreter = PDFPageInterpreter(resource_manager, device)

    with open(file_path, 'rb') as file:
        for page in PDFPage.get_pages(file):
            interpreter.process_page(page)

    text = string_io.getvalue()
    device.close()
    string_io.close()

    return text

import nltk

def extract_key_sentences(text, num_sentences):
    sentences = nltk.sent_tokenize(text)
    word_frequencies = {}
    for sentence in sentences:
        words = nltk.word_tokenize(sentence)
        for word in words:
            if word not in word_frequencies:
                word_frequencies[word] = 1
            else:
                word_frequencies[word] += 1

    sorted_word_frequencies = sorted(word_frequencies.items(), key=lambda x: x[1], reverse=True)
    top_sentences = [sentence for (sentence, _) in sorted_word_frequencies[:num_sentences]]

    return top_sentences

from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.pdfpage import PDFPage
from io import StringIO
import nltk

def convert_pdf_to_text(file_path):
    resource_manager = PDFResourceManager()
    string_io = StringIO()
    laparams = LAParams()
    device = TextConverter(resource_manager, string_io, laparams=laparams)
    interpreter = PDFPageInterpreter(resource_manager, device)

    with open(file_path, 'rb') as file:
        for page in PDFPage.get_pages(file):
            interpreter.process_page(page)

    text = string_io.getvalue()
    device.close()
    string_io.close()

    return text

def extract_key_sentences(text, num_sentences):
    sentences = nltk.sent_tokenize(text)
    word_frequencies = {}
    for sentence in sentences:
        words = nltk.word_tokenize(sentence)
        for word in words:
            if word not in word_frequencies:
                word_frequencies[word] = 1
            else:
                word_frequencies[word] += 1

    sorted_word_frequencies = sorted(word_frequencies.items(), key=lambda x: x[1], reverse=True)
    top_sentences = [sentence for (sentence, _) in sorted_word_frequencies[:num_sentences]]

    return top_sentences

# 示例使用
pdf_file = 'example.pdf'
text = convert_pdf_to_text(pdf_file)
key_sentences = extract_key_sentences(text, 5)
for sentence in key_sentences:
    print(sentence)