library/util/convert2text.py

#!/usr/bin/python3.6
# -*- coding: utf-8 -*-
# @Time    : 2021/3/15 9:22
# @Author  : lijunliang
# @Email   : lijunliang@topnet.net.cn
# @File    : convert2text.py
# @Software: PyCharm

import pdfplumber
# from loguru import logger
# import docx

from pdfminer.pdfparser import PDFParser
from pdfminer.pdfdocument import PDFDocument
from pdfminer.pdfpage import PDFPage
from pdfminer.pdfdevice import PDFDevice
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import PDFPageAggregator
from pdfminer.layout import LTTextBoxHorizontal, LAParams
from pdfminer.pdfpage import PDFTextExtractionNotAllowed


def pdf_get_pages(pdf_path: str) -> (int, str):
    fp = open(pdf_path, 'rb')
    parser = PDFParser(fp)
    document = PDFDocument(parser)
    result = ""
    count = 0
    if not document.is_extractable:
        raise PDFTextExtractionNotAllowed
    else:
        rsrcmgr = PDFResourceManager()
        laparams = LAParams()
        device = PDFPageAggregator(rsrcmgr, laparams=laparams)
        interpreter = PDFPageInterpreter(rsrcmgr, device)
        for page in PDFPage.create_pages(document):
            interpreter.process_page(page)
            layout = device.get_result()
            for x in layout:
                if (isinstance(x, LTTextBoxHorizontal)):
                    result += x.get_text()
            count += 1
    fp.close()
    return count, result


def pdf_get_pages1(pdf_path: str) -> int:
    """
    解析pdf文件，但不保留表格样式
     :param pdf_path: pdf文件
    :return:
    """
    try:
        pdf = pdfplumber.open(pdf_path)
        # 提取pdf文本内容
        pages = pdf.pages
        pageCount = len(pages)
        return pageCount
    except Exception as e:
        logger.warning("pdf获取页数失败--->%s" % e)
        return 0


def word_get_text(word_path: str) -> str:
    '''
    获取docX word文档内容
    :param word_path:
    :return:
    '''
    # 获取文档对象
    try:
        file = docx.Document(word_path)
        content = ""
        for para in file.paragraphs:
            content += para.text
    except Exception as e:
        logger.warning("获取docx文本失败--->%s" % e)
        return ""
    return content


if __name__ == '__main__':
    # pdf_path = ""
    pdf_path = "../data/1234.pdf"
    pdf_data = pdf_get_pages(pdf_path)
    print(pdf_data)