python读取pdf文件并转换成txt文件

女爷i 2022-02-15 04:29 616阅读 0赞

# 将pdf文件转换成txt文件 #

[官网][Link 1]  
[文档][Link 2]  
中英文pdf都可以，而且处理速度很快，一秒可以处理10页左右  
python2：

pip install pdfminer

python3:

pip install pdfminer3k

[pdf2txt.py][]

from pdfminer.pdfparser import PDFParser, PDFDocument
    from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
    from pdfminer.converter import PDFPageAggregator
    from pdfminer.layout import LTTextBoxHorizontal, LAParams
    from pdfminer.pdfinterp import PDFTextExtractionNotAllowed
    import logging
    
    # 不显示warning
    logging.propagate = False
    logging.getLogger().setLevel(logging.ERROR)
    
    pdf_filename = "1.pdf"
    txt_filename = "out.txt"
    
    device = PDFPageAggregator(PDFResourceManager(), laparams=LAParams())
    interpreter = PDFPageInterpreter(PDFResourceManager(), device)
    
    doc = PDFDocument()
    parser = PDFParser(open(pdf_filename, 'rb'))
    parser.set_document(doc)
    doc.set_parser(parser)
    doc.initialize()
    
    # 检测文档是否提供txt转换，不提供就忽略
    if not doc.is_extractable:
        raise PDFTextExtractionNotAllowed
    else:
        with open(txt_filename, 'w', encoding="utf-8") as fw:
            print("num page:{}".format(len(list(doc.get_pages()))))
            for page in doc.get_pages():
                interpreter.process_page(page)
                # 接受该页面的LTPage对象
                layout = device.get_result()
                # 这里layout是一个LTPage对象 里面存放着 这个page解析出的各种对象
                # 一般包括LTTextBox, LTFigure, LTImage, LTTextBoxHorizontal 等等
                # 想要获取文本就获得对象的text属性，
                for x in layout:
                    if isinstance(x, LTTextBoxHorizontal):
                        results = x.get_text()
                        fw.write(results)

[Link 1]: https://pypi.org/project/pdfminer/
[Link 2]: https://download.csdn.net/download/smilife_/11140923
[pdf2txt.py]: http://pdf2txt.py