summaryrefslogtreecommitdiff
path: root/bibtool/extract.py
blob: 5793da603c435088c247a9f01ee829061e5732fe (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
# Copyright (C) 2018 Robin Krahl <robin.krahl@ireas.org>
# SPDX-License-Identifier: MIT

import mimetypes
import re
import urllib.request

import bibtexparser
import pdftotext
import PyPDF2.pdf


PDF_INFO_DOI = '/doi'


def _unique(iterable):
    elems = set()
    for value in iterable:
        if value not in elems:
            elems.add(value)
            yield value


def _get_doi_generator_pdf(filename):
    with open(filename, 'rb') as f:
        reader = PyPDF2.pdf.PdfFileReader(f)
        if PDF_INFO_DOI in reader.documentInfo:
            yield reader.documentInfo[PDF_INFO_DOI]

    with open(filename, 'rb') as f:
        pdf = pdftotext.PDF(f)

    if len(pdf):
        text = pdf[0]

        pattern = re.compile(r'\b(10\.\d{4,}(?:\.\d+)*/(?:(?!["&\'<>])\S)+)\b')
        m = pattern.search(text)
        if m:
            yield m.group(1)


def get_doi_generator(filename):
    mtype, _ = mimetypes.guess_type(filename)
    generator = None
    if mtype == 'application/pdf':
        generator = _get_doi_generator_pdf(filename)

    if not generator:
        raise Exception('Unsupported file type ' + str(mtype))

    return _unique(generator)


def get_bibtex_data(doi):
    url = 'http://dx.doi.org/{}'.format(doi)
    headers = {'Accept': 'text/bibliography; style=bibtex'}
    request = urllib.request.Request(url, headers=headers)
    with urllib.request.urlopen(request) as response:
        bibtex = response.read().decode('utf-8')
    return bibtexparser.loads(bibtex)