pdf 轉 txt

模塊準備 ：   pip  install pdfminer.six

 

 

import refrom pdfminer.pdfinterp import PDFPageInterpreter, PDFResourceManagerfrom pdfminer.converter import TextConverter, PDFPageAggregatorfrom pdfminer.layout import LAParamsfrom pdfminer.pdfparser import PDFParserfrom pdfminer.pdfdocument import PDFDocumentfrom pdfminer.pdfdevice import PDFDevicefrom pdfminer.pdfpage import PDFPageroot= r'C:\Users\jiaotianhang\Downloads\pdf'# 獲取pdf文檔fp = open('%s/%s'%(root,'ghi.pdf'), 'rb')# 建立一個與文檔相關的解釋器parser = PDFParser(fp)# pdf文檔的對象，與解釋器鏈接起來doc = PDFDocument(parser=parser)parser.set_document(doc=doc)# 若是是加密pdf，則輸入密碼# doc._initialize_password()# 建立pdf資源管理器resource = PDFResourceManager()# 參數分析器laparam = LAParams()# 建立一個聚合器device = PDFPageAggregator(resource, laparams=laparam)# 建立pdf頁面解釋器interpreter = PDFPageInterpreter(resource, device)# 獲取頁面的集合for page in PDFPage.get_pages(fp):    # 使用頁面解釋器來讀取    interpreter.process_page(page)    # 使用聚合器來獲取內容    layout = device.get_result()    for out in layout:        if hasattr(out, 'get_text'):            # print(out.get_text())            ooo = re.sub(r'\(cid:\d+\)','',out.get_text())            # 寫入txt文件            if ooo.strip():                fw = open('exam3.txt', 'a',encoding='utf-8')                fw.write(ooo)                fw.close()            # fw.write(out.get_text())