python转pdf到文本

# -*- coding: utf-8 -*-
from bs4 import BeautifulSoup
import requests
import re
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from cStringIO  import StringIO
#from io  import StringIO for python3
from io import open
from pdfminer.pdfpage import PDFPage
def pdf_txt(url):
    rsrcmgr = PDFResourceManager()
    retstr = StringIO()
    codec = 'utf-8'
    laparams = LAParams()
    device = TextConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)
    f = requests.get(url).content
    fp = StringIO(f)
    interpreter = PDFPageInterpreter(rsrcmgr, device)
    password = ""
    maxpages = 0
    caching = True
    pagenos = set()
    for page in PDFPage.get_pages(fp,
                                  pagenos,
                                  maxpages=maxpages,
                                  password=password,
                                  caching=caching,
                                  check_extractable=True):
        interpreter.process_page(page)
    fp.close()
    device.close()
    str = retstr.getvalue()
    retstr.close()
    return str
txt=tpdf_txt('http://pythonscraping.com/pages/warandpeace/chapter1.pdf')
print txt
#如果pdf含有中文，输出到文件
#open('pdf.txt','wb').write(txt)