python读取pdf文档-实战

# -*- coding: utf-8 -*-
#读取pdf文档
from pdfminer.converter import PDFPageAggregator
from pdfminer.layout import LAParams
from pdfminer.pdfparser import PDFParser,PDFDocument
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.pdfdevice import PDFDevice
import pdfminer.pdfinterp


#获取文档对象
fp = open("naacl06-shinyama.pdf","rb")
#创建一个与文档关联的解释器
parser=PDFParser(fp)
#PDF文档对象
doc = PDFDocument()