ranker.py 文件源码

def parse_pdf_doc(self):
        """
        Open a pdf document filetype and parse contents to string variable
        for matching comparison.
        """

        docText = ''
        # open the file, with read/binary priviledges
        f = open(self.file, 'rb')
        pdf = PyPDF2.PdfFileReader(f)
        for page in pdf.pages :
            docText += page.extractText()

        f.close()
        return docText.strip() or None