pypdfocr_pdffiler.py 文件源码

def iter_pdf_page_text(self, filename):
        self.filename = filename
        reader = PdfFileReader(filename)
        logging.info("pdf scanner found %d pages in %s" % (reader.getNumPages(), filename))
        for pgnum in range(reader.getNumPages()):
            text = reader.getPage(pgnum).extractText()
            text = text.encode('ascii', 'ignore')
            text = text.replace('\n', ' ')
            yield text