[BangPypers] Help in reading the pdf file
Ruchir Shukla
ruchiryshukla at gmail.com
Fri Mar 27 12:27:15 CET 2009
previous was not good sorry.........
i have used this to to read pdf file
import popen2
from StringIO import StringIO
class InputStreamReader(object):
def __init__(self, inputStream, encoding):
super(InputStreamReader, self).__init__()
self.inputStream = inputStream
self.encoding = encoding or 'utf-8'
def _read(self, length):
return self.inputStream.read(length)
def read(self, length=-1):
text = self._read(length)
text = unicode(text, self.encoding)
return text
def close(self):
self.inputStream.close()
process = popen2.Popen4(["pdftotext", "-enc", "UTF-8", 'Full_Path', "-"])
data=InputStreamReader(process.fromchild, 'utf-8').read()
print data
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mail.python.org/pipermail/bangpypers/attachments/20090327/9ae98f78/attachment.htm>
More information about the BangPypers
mailing list