#!/usr/bin/env python#-*- coding:utf-8 -*-from pdfminer.pdfparser import PDFParserfrom pdfminer.pdfdocument import PDFDocumentfrom pdfminer.pdfpage import PDFPagefrom pdfminer.pdfpage import PDFTextExtractionNotAllowedfrom pdfminer.pdfinterp import PDFResourceManagerfrom pdfminer.pdfinterp import PDFPageInterpreterfrom pdfminer.pdfdevice import PDFDevicefrom pdfminer.layout import LAParamsfrom pdfminer.converter import PDFPageAggregator#獲取文檔對象，你把algorithm.pdf換成你自己的文件名即可。fp=open("algorithm.pdf","rb")#創建一個與文檔相關聯的解釋器parser=PDFParser(fp)#PDF文檔對象doc=PDFDocument(parser)#鏈接解釋器和文檔對象parser.set_document(doc)#doc.set_paeser(parser)#初始化文檔#doc.initialize("")#創建PDF資源管理器resource=PDFResourceManager()#參數分析器laparam=LAParams()#創建一個聚合器device=PDFPageAggregator(resource,laparams=laparam)#創建PDF頁面解釋器interpreter=PDFPageInterpreter(resource,device)#使用文檔對象得到頁面集合for page in PDFPage.create_pages(doc):  #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()