def non_url():
"""Parse the node without any links. Should
take straight to `build_item` and build the HEPRecord.
"""
spider = t2k_spider.T2kSpider()
response = fake_response_from_file('t2k/test_1_nourl.html')
selector = Selector(response, type='html')
nodes = selector.xpath('//%s' % spider.itertag)
return spider.parse_node(response, nodes[0]).next()
def record():
"""Return results from the T2K spider."""
spider = t2k_spider.T2kSpider()
response = fake_response_from_file('t2k/test_1.html')
selector = Selector(response, type='html')
nodes = selector.xpath('//%s' % spider.itertag)
spider.domain = "file:///tests/responses/t2k/"
parsed_node = spider.parse_node(response, nodes[0])
splash_response = fake_response_from_file('t2k/001.html')
splash_response.meta["date"] = parsed_node.meta["date"]
splash_response.meta["title"] = parsed_node.meta["title"]
splash_response.meta["urls"] = parsed_node.meta["urls"]
splash_response.meta["authors"] = parsed_node.meta["authors"]
return spider.scrape_for_pdf(splash_response).next()