convert_pdf_to_txt.py

#coding=utf-8
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfpage import PDFPage
from cStringIO import StringIO
import os

def convert_pdf_to_txt(path,save_name):
    try:
        rsrcmgr = PDFResourceManager()
        retstr = StringIO()
        codec = 'utf-8'
        laparams = LAParams()
        device = TextConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)
        fp = file(path, 'rb')
        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()
        try:
            with open(save_name,"w") as f:
                for i in str:
                    f.write(i)
            print "%s Writing Succeed!"%save_name
        except:
            print "Writing Failed!"
    except:
        print "Writing Failed!......"

if __name__ == '__main__':

    convert_pdf_to_txt("pdf_test.pdf","txt_test.txt")