def process_pdf(rsrcmgr,
device,
fp,
pagenos=None,
maxpages=0,
password='',
check_extractable=True):
# Create a PDF parser object associated with the file object.
parser = PDFParser(fp)
# Create a PDF document object that stores the document structure.
doc = PDFDocument()
# Connect the parser and document objects.
parser.set_document(doc)
doc.set_parser(parser)
# Supply the document password for initialization.
# (If no password is set, give an empty string.)
doc.initialize(password)
# Check if the document allows text extraction. If not, abort.
if check_extractable and not doc.is_extractable:
raise PDFTextExtractionNotAllowed(
'Text extraction is not allowed: %r' % fp)
# Create a PDF interpreter object.
interpreter = PDFPageInterpreter(rsrcmgr, device)
# Process each page contained in the document.
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
return
def process_pdf(rsrc, device, fp, pagenos=None, maxpages=0, password=''):
doc = PDFDocument()
parser = PDFParser(fp)
parser.set_document(doc)
doc.set_parser(parser)
doc.initialize(password)
if not doc.is_extractable:
raise PDFTextExtractionNotAllowed('Text extraction is not allowed: %r' % fp)
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
return
def process_pdf(rsrc, device, fp, pagenos=None, maxpages=0, password=''):
doc = PDFDocument()
parser = PDFParser(fp)
parser.set_document(doc)
doc.set_parser(parser)
doc.initialize(password)
if not doc.is_extractable:
raise PDFTextExtractionNotAllowed('Text extraction is not allowed: %r' % fp)
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
return
def get_pages(klass,
fp,
pagenos=None,
maxpages=0,
password='',
caching=True,
check_extractable=True):
# Create a PDF parser object associated with the file object.
parser = PDFParser(fp)
# Create a PDF document object that stores the document structure.
doc = PDFDocument(parser, caching=caching)
# Supply the document password for initialization.
# (If no password is set, give an empty string.)
doc.initialize(password)
# Check if the document allows text extraction. If not, abort.
if check_extractable and not doc.is_extractable:
raise klass.PDFTextExtractionNotAllowed(
'Text extraction is not allowed: %r' % fp)
# Process each page contained in the document.
for (pageno, page) in enumerate(klass.create_pages(doc)):
if pagenos and (pageno not in pagenos):
continue
yield page
if maxpages and maxpages <= pageno + 1:
break
return
def process_pdf(rsrcmgr, device, fp, pagenos=None, maxpages=0, password='',
caching=True, check_extractable=True):
# Create a PDF parser object associated with the file object.
parser = PDFParser(fp)
# Create a PDF document object that stores the document structure.
doc = PDFDocument(caching=caching)
# Connect the parser and document objects.
parser.set_document(doc)
doc.set_parser(parser)
# Supply the document password for initialization.
# (If no password is set, give an empty string.)
doc.initialize(password)
# Check if the document allows text extraction. If not, abort.
if check_extractable and not doc.is_extractable:
raise PDFTextExtractionNotAllowed('Text extraction is not allowed: %r' % fp)
# Create a PDF interpreter object.
interpreter = PDFPageInterpreter(rsrcmgr, device)
# Process each page contained in the document.
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
return
def pdf_test():
pdf_parser = PDFParser()
pdf_parser.parse(r'D:\Test3.pdf')
print(pdf_parser.get_text())
def pdf():
pdf_parser = PDFParser()
pdf_parser.parse(r'files/Test3.pdf')
print('pdf parser', pdf_parser.get_processed_stems(),
len(pdf_parser.get_processed_stems()))
def test_PDFParser(self):
pdf = PDFParser()
pdf.parse('files/Test.pdf')
text = []
assert pdf.get_processed_stems() == text