def getPDFInfoForTestString(self, filename):
fp = open(filename, 'rb')
codec = 'utf-8'
laparams = LAParams()
parser = PDFParser(fp)
doc = PDFDocument()
parser.set_document(doc)
doc.set_parser(parser)
doc.initialize('')
if not doc.is_extractable:
raise PDFTextExtractionNotAllowed
rsrcmgr = PDFResourceManager()
device = TagExtractor2Memory(rsrcmgr, codec=codec)
interpreter = PDFPageInterpreter(rsrcmgr, device)
#outfp.write(filename[-11:-4]+"\n")
#print filename[-11:-4]+"\n"#uncomment for testing
PDFInfo=''
for i,page in enumerate(doc.get_pages()):
PDFInfo+=interpreter.process_page_to_mem(page)
if i==10:
return PDFInfo
