python PDF data extraction

 from pdfminer.pdfparser import PDFParser
from pdfminer.pdfparser import PDFDocument
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import PDFPageAggregator
from pdfminer.layout import LAParams
from pdfminer.layout import LTTextBoxHorizontal

# Open a PDF file.
fp = open ('TEST.pdf', 'rb')
# Create a PDF parser object associated with the file object.
parser = PDFParser(fp)
document=PDFDocument()
parser.set_document(document)
# Create a PDF document object that stores the document structure.
document.set_parser(parser)
# Create a PDF resource manager object that stores shared resources.
rsrcmgr = PDFResourceManager()
# Set parameters for analysis.
laparams=LAParams()
# Create a PDF page aggregator object.
device=PDFPageAggregator(rsrcmgr, laparams=laparams)
interpreter=PDFPageInterpreter(rsrcmgr, device)

pages=list( document.get_pages())
pagecontents=[ ]
for i in range (len(pages)):
    page_1 = pages[i] 
    interpreter.process_page(page_1)
    layout=device.get_result()
    For lin layout:
        if isinstance(l,LTTextBoxHorizontal):
            pagecontents.append(l.get_text())

print(pagecontents)

'1.1\n',
'1.2\n',
'1.3\n',
'1.4\n',
'1\n2\n3\n',
'1\n2\n3\n4\n5\n',
'General\nFirst Name\nLast Name\nGender\n',
'Registry\n',
'Number\n',
'Contacts\nTEL number\nFax number\nMobile number\n',
'International number\n',
'Email address\n',
'ABCDE\nXXXX\n',
'JAPAN\n',
'C6S2076\n',
'123456789/123456789\n123456789\n123456789XXXX\n123456789\[email protected]\n']

List [0] = ["1.1", "General" ]
list[1] = ["1", "First Name", "ABCDE" ]
....
List[11] = ["5", "Email address", "[email protected]" ]