【script】python識別pdf文檔

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

def parse(path):
    parser = PDFParser(path)
    document = PDFDocument(parser)

    if not document.is_extractable:
        raise PDFTextExtractionNotAllowed
    else:
        rsrcmgr = PDFResourceManager()
        laparams = LAParams()
        device = PDFPageAggregator(rsrcmgr, laparams=laparams)
        interpreter = PDFPageInterpreter(rsrcmgr, device)
        result = ""
        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()
        return result

def main_pdf(path):
    return parse(open(path, 'rb'))

if __name__ == '__main__':
    print(main_pdf("path.pdf"))