port = '8080'
output_dict = parse_pdf(host, test_pdf_paper, port=port)
pp = pprint.PrettyPrinter(indent=4)
pp.pprint(output_dict)
{ 'abstractText': 'The abstract which is normally short.',
'authors': [{'affiliations': [], 'name': 'Andrew Moore'}],
'id': 'SP:045daa3afe8335ca973de6dbed366626376434da',
'references': [ { 'authors': [ 'Tomas Mikolov',
'Greg Corrado',
'Kai Chen',
'Jeffrey Dean.'],
'title': 'Efficient estimation of word '
'representations in vector space',
'venue': 'Proceedings of the International '
'Conference on Learning Representations, '
'pages 1–12.',
'year': 2013}],
'sections': [ { 'text': 'The abstract which is normally short.\n'
'1 Introduction\n'
'Some introduction text.\n'
'2 Section 1\n'
'Here is some example text.'},
{ 'heading': '2.1 Sub Section 1',
'text': 'Some more text but with a reference (Mikolov '
'et al., 2013).\n'
'3 Section 2\n'
'The last section\n'
'References\n'
'Tomas Mikolov, Greg Corrado, Kai Chen, and '
'Jeffrey Dean. 2013. Efficient estimation of '
'word representations in vector space. '
'Proceedings of the International Conference '
'on Learning Representations, pages 1–12.'}],
'title': 'Example paper for testing',
'year': 2021}