Python - 小玩意 - 解析本地PDF文本，保存到本地TXT

淡淡的烟草味﹌ 2023-10-16 13:08 23阅读 0赞

from pdfminer.converter import PDFPageAggregator
    from pdfminer.layout import LTTextBoxHorizontal, LAParams
    from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter, PDFTextExtractionNotAllowed
    from pdfminer.pdfparser import PDFParser, PDFDocument
    
    
    def parse_pdf(data_io, save_path):
        try:
            # 创建一个PDF文档分析器
            parser = PDFParser(data_io)
            # 创建一个PDF文档
            doc = PDFDocument()
            parser.set_document(doc)
            doc.set_parser(parser)
            doc.initialize()
    
            if not doc.is_extractable:
                raise PDFTextExtractionNotAllowed
            else:
                rsrcmgr = PDFResourceManager()
                laparams = LAParams()
                device = PDFPageAggregator(rsrcmgr, laparams=laparams)
                interpreter = PDFPageInterpreter(rsrcmgr, device)
    
                with open(save_path, 'a') as f:
                    # 循环遍历每一页PDF文件
                    for page in doc.get_pages():
                        interpreter.process_page(page)
                        layout = device.get_result()
                        for x in layout:
                            try:
                                if isinstance(x, LTTextBoxHorizontal):
                                    result = x.get_text()
                                    print(result)
                                    f.write(result + "\n")
                            except Exception as e:
                                print(f"Failed: {e}")
        except Exception as e:
            print(f"Error: {e}")
    
    
    if __name__ == '__main__':
        # 解析本地PDF文本，保存到本地TXT
        with open('./解析pdf.pdf', 'rb') as pdf_html:
            parse_pdf(pdf_html, '解析pdf.txt')
    
        # 解析网络上的PDF，保存文本到本地
        # 使用 urllib 或其他库下载 PDF 数据并传递给 parse_pdf 函数