def test_id_parser(self):
self.identifier = arxiv_id_parser.arxiv_id_parser(FILE_SOURCE_PDF, FILE_NAME_PDF)
self.assertEqual(self.identifier, u'1305.5767v1')
self.identifier = arxiv_id_parser.arxiv_id_parser(FILE_SOURCE_TXT, FILE_NAME_TXT)
self.assertRaises(Exception('NonArxivPdf'), self.identifier)
def test_id_parser(self):
self.identifier = arxiv_id_parser.arxiv_id_parser(
FILE_SOURCE_PDF, FILE_NAME_PDF)
self.assertEqual(self.identifier, u'1305.5767v1')
self.identifier = arxiv_id_parser.arxiv_id_parser(
FILE_SOURCE_TXT, FILE_NAME_TXT)
self.assertRaises(Exception('NonArxivPdf'), self.identifier)
def arxiv_pyler(path):
if os.path.exists(path):
COUNTER = 0
if path==None:
return
entry_list=[]
print path
for root, dirs, files in os.walk(path):
for pdf in files:
if re.search('.pdf$', pdf):
try:
source = os.path.join(root, pdf)
identifier = arxiv_id_parser(source, pdf)
xml_content = arxiv_query(identifier)
entry_content = xml_parser(xml_content, identifier)
entry_list.append(entry_content)
entry_list[COUNTER].update({'file_source':source})
#shutil.move(source, pdf_dir)
COUNTER += 1
except Exception as inst:
for error in inst.args:
print error
else:
continue
html_generator(entry_list)
print 'complete'
return entry_list
else:
print 'path does not exits.'