Python PDF文件转文本

比较简单的实现，代码用到了PyPDF2，函数返回一个json结构

import PyPDF2
import json

def convert_pdf_to_text(pdf_file, text_file):
    # Open the PDF file in binary mode
    with open(pdf_file, 'rb') as file:
        pdf_reader = PyPDF2.PdfReader(file)

        # Get the total number of pages in the PDF
        pages = pdf_reader.pages

        # Initialize counters
        word_count = 0
        graph_count = 0

        # Extract text from each page and count words and graphs
        text = ''
        for page in pages:
            #page = pdf_reader.getPage(page_number)
            text += page.extract_text()
            # Count words
            word_count += len(text.split())

    # Save the text to a text file
    with open(text_file, 'w', encoding='utf-8') as file:
        file.write(text)

    # Create a dictionary with the counts
    counts = {
        'word_count': word_count,
        'page_count': len(pages)
    }

    # Save the counts to a JSON file
    json_file = text_file.replace('.txt', '.json')
    with open(json_file, 'w') as file:
        json.dump(counts, file)