Add basic import implementation

1 files changed, 37 insertions, 0 deletions

diff --git a/bibtool/extract.py b/bibtool/extract.py
new file mode 100644
index 0000000..6409f1b
--- /dev/null
+++ b/bibtool/extract.py
@@ -0,0 +1,37 @@
+# Copyright (C) 2018 Robin Krahl <robin.krahl@ireas.org>
+# SPDX-License-Identifier: MIT
+
+import mimetypes
+import urllib.request
+
+import bibtexparser
+import PyPDF2.pdf
+
+
+PDF_INFO_DOI = '/doi'
+
+
+def _get_data_for_doi(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)
+
+
+def _handle_pdf(filename):
+    with open(filename, 'rb') as f:
+        reader = PyPDF2.pdf.PdfFileReader(f)
+        if PDF_INFO_DOI not in reader.documentInfo:
+            raise Exception('PDF file does not have doi header')
+        doi = reader.documentInfo[PDF_INFO_DOI]
+
+    return _get_data_for_doi(doi)
+
+
+def get_bibtex_data(filename):
+    mtype, _ = mimetypes.guess_type(filename)
+    if mtype == 'application/pdf':
+        return _handle_pdf(filename)
+    raise Exception('Unsupported file type ' + str(mtype))