第六章 读取pdf文件

#!/usr/bin/env python
# _*_ coding:utf-8 _*_
from io import StringIO
from urllib.request import urlopen

from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfinterp import PDFResourceManager, process_pdf


def readPDF(pdfFile):
    rsrcmgr=PDFResourceManager
    retstr=StringIO
    laparams=LAParams()
    device=TextConverter(rsrcmgr,retstr,laparams=laparams)

    process_pdf(rsrcmgr,device,pdfFile)
    device.close()

    content=retstr.getvalue()
    retstr.close()
    return content
pdfFile=urlopen("http://pythonscraping.com/pages/waranpeace/chapter1.pdf")
outputString=readPDF(pdfFile)
print(outputString)
pdfFile.close()