def test_model_based_harvesting(self): """Test harvesting using model.""" raw_xml = open(os.path.join( os.path.dirname(__file__), "data/sample_arxiv_response.xml" )).read() responses.add( responses.GET, 'http://export.arxiv.org/oai2', body=raw_xml, content_type='text/xml' ) _, records = get_records(['oai:arXiv.org:1507.03011'], name='arXiv') self.assertTrue(len(records) == 1)
def test_get_from_identifiers_with_prefix(self): raw_xml = open( os.path.join(os.path.dirname(__file__), "data/sample_arxiv_response.xml")).read() httpretty.register_uri(httpretty.GET, 'http://export.arxiv.org/oai2', body=raw_xml, content_type='text/xml') for rec in get_records(['oai:arXiv.org:1507.03011'], metadata_prefix="arXiv", url='http://export.arxiv.org/oai2'): identifier_in_request = rec.xml.xpath( "//arXiv:id", namespaces={"arXiv": "http://arxiv.org/OAI/arXiv/"})[0].text self.assertEqual(identifier_in_request, "1507.03011")
def test_get_from_identifiers(self): raw_xml = open( os.path.join(os.path.dirname(__file__), "data/sample_oai_dc_response.xml")).read() httpretty.register_uri(httpretty.GET, 'http://export.arxiv.org/oai2', body=raw_xml, content_type='text/xml') for rec in get_records(['oai:arXiv.org:1507.03011'], url='http://export.arxiv.org/oai2'): identifier_in_request = rec.xml.xpath( "//dc:identifier", namespaces={"dc": "http://purl.org/dc/elements/1.1/"})[0].text self.assertEqual(identifier_in_request, "http://arxiv.org/abs/1507.03011")
def test_get_from_identifiers(self): raw_xml = open(os.path.join( os.path.dirname(__file__), "data/sample_oai_dc_response.xml" )).read() responses.add( responses.GET, 'http://export.arxiv.org/oai2', body=raw_xml, content_type='text/xml' ) for rec in get_records(['oai:arXiv.org:1507.03011'], url='http://export.arxiv.org/oai2'): identifier_in_request = rec.xml.xpath( "//dc:identifier", namespaces={"dc": "http://purl.org/dc/elements/1.1/"} )[0].text self.assertEqual(identifier_in_request, "http://arxiv.org/abs/1507.03011")
def test_get_from_identifiers_with_prefix(self): raw_xml = open(os.path.join( os.path.dirname(__file__), "data/sample_arxiv_response.xml" )).read() responses.add( responses.GET, 'http://export.arxiv.org/oai2', body=raw_xml, content_type='text/xml' ) for rec in get_records(['oai:arXiv.org:1507.03011'], metadata_prefix="arXiv", url='http://export.arxiv.org/oai2'): identifier_in_request = rec.xml.xpath( "//arXiv:id", namespaces={"arXiv": "http://arxiv.org/OAI/arXiv/"} )[0].text self.assertEqual(identifier_in_request, "1507.03011")