def convert(self, data):
# convert binary pdf data into a file like structure
pdfdata = StringIO(data)
# I have no idea why this is needed
CMapDB.initialize('CMap', 'CDBCMap')
# create the converter and resource manager
rsrc = PDFResourceManager()
converter = TextConverter(rsrc)
# setup the parser
doc = PDFDocument()
parser = PDFParser(doc, pdfdata)
# initialize the pdf
try:
# use empty password
doc.initialize('')
except PDFPasswordIncorrect:
return ''
# check if we can extract the contents of this file
if not doc.is_extractable:
return ''
# do the conversion
interpreter = PDFPageInterpreter(rsrc, converter)
for page in doc.get_pages():
interpreter.process_page(page)
converter.close()
pdfdata.close()
return converter.get_text()
def convert(self, data):
# convert binary pdf data into a file like structure
pdfdata = StringIO(data)
# I have no idea why this is needed
CMapDB.initialize('CMap', 'CDBCMap')
# create the converter and resource manager
rsrc = PDFResourceManager()
converter = TextConverter(rsrc)
# setup the parser
doc = PDFDocument()
parser = PDFParser(doc, pdfdata)
# initialize the pdf
try:
# use empty password
doc.initialize('')
except PDFPasswordIncorrect:
return ''
# check if we can extract the contents of this file
if not doc.is_extractable:
return ''
# do the conversion
interpreter = PDFPageInterpreter(rsrc, converter)
for page in doc.get_pages():
interpreter.process_page(page)
converter.close()
pdfdata.close()
return converter.get_text()
def convert(rsrc, device, fname, pagenos=None, maxpages=0, password=''):
doc = PDFDocument()
fp = file(fname, 'rb')
parser = PDFParser(doc, fp)
try:
doc.initialize(password)
except PDFPasswordIncorrect:
raise TextExtractionNotAllowed('Incorrect password')
if not doc.is_extractable:
raise TextExtractionNotAllowed('Text extraction is not allowed: %r' % fname)
interpreter = PDFPageInterpreter(rsrc, device)
for (pageno,page) in enumerate(doc.get_pages()):
if pagenos and (pageno not in pagenos): continue
interpreter.process_page(page)
if maxpages and maxpages <= pageno+1: break
device.close()
fp.close()
return
def convert(rsrc, device, fname, pagenos=None, maxpages=0, password=''):
doc = PDFDocument()
fp = file(fname, 'rb')
parser = PDFParser(doc, fp)
try:
doc.initialize(password)
except PDFPasswordIncorrect:
raise TextExtractionNotAllowed('Incorrect password')
if not doc.is_extractable:
raise TextExtractionNotAllowed('Text extraction is not allowed: %r' %
fname)
interpreter = PDFPageInterpreter(rsrc, device)
for (pageno, page) in enumerate(doc.get_pages()):
if pagenos and (pageno not in pagenos): continue
interpreter.process_page(page)
if maxpages and maxpages <= pageno + 1: break
device.close()
fp.close()
return