pdfminer获取整页文本

 #! python2
 # coding: utf-8

 import sys
 from cStringIO import StringIO
 from pdfminer import pdfinterp
 from pdfminer import pdfpage
 from pdfminer import converter
 from pdfminer import layout

 with file(path, 'rb') as fp:
     rsrcmgr = pdfinterp.PDFResourceManager()
     retstr = StringIO()
     codec = 'utf-8'
     laparams = layout.LAParams()
     device = converter.TextConverter(
         rsrcmgr, retstr, codec=codec, laparams=laparams)
     # Create a PDF interpreter object.
     interpreter = pdfinterp.PDFPageInterpreter(rsrcmgr, device)
     # Process each page contained in the document.
     pages = pdfpage.PDFPage.get_pages(fp)
     for page in pages:
         interpreter.process_page(page)
         data = retstr.getvalue()