Python for NLP：如何处理包含多个PDF文件的文本？

pip install PyPDF2 textract

import PyPDF2
import textract
import glob

pdf_folder_path = "path/to/pdf/folder"
pdf_files = glob.glob(pdf_folder_path + "/*.pdf")

for pdf_file in pdf_files:
    with open(pdf_file, 'rb') as file:
        pdf_reader = PyPDF2.PdfFileReader(file)
        num_pages = pdf_reader.numPages
        text = ""
        for page in range(num_pages):
            page_obj = pdf_reader.getPage(page)
            text += page_obj.extractText()

text = textract.process(pdf_file).decode('utf-8')

import re

cleaned_text = re.sub('
', ' ', text)  # 去除换行符
cleaned_text = re.sub('s+', ' ', cleaned_text)  # 去除多余的空格
cleaned_text = re.sub('[^a-zA-Z0-9s]', '', cleaned_text)  # 去除非字母数字字符

output_file_path = "path/to/output/file.txt"
with open(output_file_path, 'w', encoding='utf-8') as file:
    file.write(cleaned_text)