python(6) : 读取pdf的文本, 读取pdf每一页为文件

参考 : 解决fitz模块报错RuntimeError: Directory ‘static/‘ does not exist_directory 'static' does not exist-CSDN博客 

 read_pdf.py

# -*- coding: utf-8 -*-
import PyPDF2
import fitz
import pdfplumber

'''
pip install PyPDF2
pip install pdfplumber
'''


# 读取pdf每一页保存为图片
def pdf2img(pdf_file, output_folder):
    pdf_document = fitz.open(pdf_file)
    for page_number in range(pdf_document.page_count):
        page = pdf_document.load_page(page_number)
        image = page.get_pixmap(matrix=fitz.Matrix(3, 3))
        image.save(output_folder + f'page_{page_number + 1}.jpg')
    pdf_document.close()


# 读取pdf内的文本
def read_pdf_handle2(file_path):
    text = ""
    with pdfplumber.open(file_path) as pdf:
        for page in pdf.pages:
            text += page.extract_text() + "\n"
    return text


# 读取pdf内的文本
def read_pdf_handle(file_path):
    # 打开 PDF 文件
    texts = ""
    with open(file_path, 'rb') as file:
        reader = PyPDF2.PdfReader(file)
        # 获取 PDF 文件中的页面数量
        num_pages = len(reader.pages)
        print(f'此PDF文件共有 {num_pages} 页')
        # 读取每一页的内容
        for page_number in range(num_pages):
            page = reader.pages[page_number]
            text = page.extract_text()
            texts += text
    return texts


if __name__ == '__main__':
    print(read_pdf_handle("F:test\\5.pdf"))