def test_handle_package(tarfile):
"""Test getting the target folder name for pdf files."""
spider = iop_spider.IOPSpider()
tarfile = "file://" + tarfile
target_folder = spider.handle_package(tarfile)
assert target_folder
def record():
"""Return results generator from the WSP spider."""
spider = iop_spider.IOPSpider()
response = fake_response_from_file('iop/xml/test_standard.xml')
node = get_node(spider, "Article", response)
spider.pdf_files = test_pdf_dir
return spider.parse_node(response, node)
def erratum_open_access_record():
"""Return results generator from the WSP spider."""
spider = iop_spider.IOPSpider()
body = """
<ArticleSet>
<Article>
<Journal>
<PublisherName>Institute of Physics</PublisherName>
<JournalTitle>J. Phys.: Conf. Ser.</JournalTitle>
<Volume>143</Volume>
<Issue>3</Issue>
</Journal>
<FirstPage LZero="save">336</FirstPage>
<PublicationType>Published Erratum</PublicationType>
</Article>
</ArticleSet>
"""
response = fake_response_from_string(body)
node = get_node(spider, "Article", response)
spider.pdf_files = get_test_suite_path(
'responses',
'iop',
'pdf',
)
parsed_item = spider.parse_node(response, node)
assert parsed_item
assert parsed_item.record
return parsed_item.record
def record():
"""Return results generator from the WSP spider."""
spider = iop_spider.IOPSpider()
response = fake_response_from_file('iop/xml/test_standard.xml')
node = get_node(spider, "Article", response)
spider.pdf_files = TEST_PDF_DIR
parsed_item = spider.parse_node(response, node)
assert parsed_item
assert parsed_item.record
return parsed_item.record
def not_published_record():
"""Test that scraping not-published paper will not build a HEPRecord."""
spider = iop_spider.IOPSpider()
body = """
<ArticleSet>
<Article>
<Journal>
<PubDate PubStatus="aheadofprint">
<Year>2015</Year>
<Month>03</Month>
</PubDate>
</Journal>
</Article>
</ArticleSet>
"""
response = fake_response_from_string(body)
node = get_node(spider, "Article", response)
tests_dir = os.path.dirname(os.path.realpath(__file__))
spider.pdf_files = os.path.join(tests_dir, "responses/iop/pdf/")
return spider.parse_node(response, node)
def test_not_published_record():
"""Not-published paper should result in nothing."""
spider = iop_spider.IOPSpider()
body = """
<ArticleSet>
<Article>
<Journal>
<PubDate PubStatus="aheadofprint">
<Year>2015</Year>
<Month>03</Month>
</PubDate>
</Journal>
</Article>
</ArticleSet>
"""
response = fake_response_from_string(body)
node = get_node(spider, "Article", response)
tests_dir = os.path.dirname(os.path.realpath(__file__))
spider.pdf_files = os.path.join(tests_dir, "responses/iop/pdf/")
records = spider.parse_node(response, node)
assert records is None
def erratum_open_access_record():
"""Return results generator from the WSP spider."""
spider = iop_spider.IOPSpider()
body = """
<ArticleSet>
<Article>
<Journal>
<PublisherName>Institute of Physics</PublisherName>
<JournalTitle>J. Phys.: Conf. Ser.</JournalTitle>
<Volume>143</Volume>
<Issue>3</Issue>
</Journal>
<FirstPage LZero="save">336</FirstPage>
<PublicationType>Published Erratum</PublicationType>
</Article>
</ArticleSet>
"""
response = fake_response_from_string(body)
node = get_node(spider, "Article", response)
tests_dir = os.path.dirname(os.path.realpath(__file__))
spider.pdf_files = os.path.join(tests_dir, "responses/iop/pdf/")
return spider.parse_node(response, node)
def test_not_published_record():
"""Not-published paper should result in nothing."""
spider = iop_spider.IOPSpider()
body = """
<ArticleSet>
<Article>
<Journal>
<PubDate PubStatus="aheadofprint">
<Year>2015</Year>
<Month>03</Month>
</PubDate>
</Journal>
</Article>
</ArticleSet>
"""
response = fake_response_from_string(body)
node = get_node(spider, "Article", response)
spider.pdf_files = get_test_suite_path(
'responses',
'iop',
'pdf',
)
records = spider.parse_node(response, node)
assert records is None
def test_tarfile(tarfile, tmpdir):
"""Test untarring a tar.gz package with a test PDF file."""
spider = iop_spider.IOPSpider()
pdf_files = spider.untar_files(tarfile, six.text_type(tmpdir))
assert len(pdf_files) == 1
assert "test_143_3_336.pdf" in pdf_files[0]