def generated_conference_paper(scrape_pos_conference_paper_page_body):
"""Return results generator from the PoS spider."""
# environmental variables needed for the pipelines payload
os.environ['SCRAPY_JOB'] = 'scrapy_job'
os.environ['SCRAPY_FEED_URI'] = 'scrapy_feed_uri'
os.environ['SCRAPY_LOG_FILE'] = 'scrapy_log_file'
crawler = Crawler(spidercls=pos_spider.POSSpider)
spider = pos_spider.POSSpider.from_crawler(crawler)
request = spider.parse(
fake_response_from_file(
file_name=str('pos/sample_pos_record.xml'), )).next()
response = HtmlResponse(url=request.url,
request=request,
body=scrape_pos_conference_paper_page_body,
**{'encoding': 'utf-8'})
assert response
pipeline = InspireCeleryPushPipeline()
pipeline.open_spider(spider)
parsed_item = request.callback(response).next()
parsed_record = pipeline.process_item(parsed_item, spider)
assert parsed_record
yield parsed_record
clean_dir()
def generated_conference_paper(scrape_pos_conference_paper_page_body):
"""Return results generator from the PoS spider."""
# environmental variables needed for the pipelines payload
os.environ['SCRAPY_JOB'] = 'scrapy_job'
os.environ['SCRAPY_FEED_URI'] = 'scrapy_feed_uri'
os.environ['SCRAPY_LOG_FILE'] = 'scrapy_log_file'
crawler = Crawler(spidercls=pos_spider.POSSpider)
spider = pos_spider.POSSpider.from_crawler(crawler)
request = spider.parse(
fake_response_from_file(
file_name=str('pos/sample_pos_record.xml'),
)
).next()
response = HtmlResponse(
url=request.url,
request=request,
body=scrape_pos_conference_paper_page_body,
**{'encoding': 'utf-8'}
)
assert response
pipeline = InspireCeleryPushPipeline()
pipeline.open_spider(spider)
parsed_item = request.callback(response).next()
crawl_result = pipeline.process_item(parsed_item, spider)
assert crawl_result['record']
yield crawl_result['record']
clean_dir()
def authors():
"""Returns get_authors() output."""
spider = phil_spider.PhilSpider()
response = fake_response_from_file('phil/test_thesis.json')
jsonrecord = json.loads(response.body_as_unicode())
response.meta["jsonrecord"] = jsonrecord[0]
return spider.get_authors(jsonrecord[0]['authors'])
def many_results(spider):
"""Return results generator from the arxiv spider. Tricky fields, many
records.
"""
def _get_processed_record(item, spider):
record = pipeline.process_item(item, spider)
return record
parsed_items = list(
spider.parse(
fake_response_from_file(
'arxiv/sample_arxiv_record.xml',
response_type=TextResponse,
)))
assert parsed_items
pipeline = InspireCeleryPushPipeline()
pipeline.open_spider(spider)
yield [
_get_processed_record(parsed_item, spider)
for parsed_item in parsed_items
]
clean_dir()
def results():
"""Return results generator from the arxiv spider. All fields, one record.
"""
def _get_processed_item(item, spider):
record = pipeline.process_item(item, spider)
validate(record, 'hep')
assert record
return record
crawler = Crawler(spidercls=arxiv_spider.ArxivSpider)
spider = arxiv_spider.ArxivSpider.from_crawler(crawler)
parsed_items = list(
spider.parse(
fake_response_from_file(
'arxiv/sample_arxiv_record0.xml',
response_type=TextResponse,
)))
pipeline = InspireCeleryPushPipeline()
pipeline.open_spider(spider)
return [
_get_processed_item(parsed_item, spider)
for parsed_item in parsed_items
]
def urls():
spider = base_spider.BaseSpider()
response = fake_response_from_file('base/test_1.xml')
selector = Selector(response, type='xml')
spider._register_namespaces(selector)
nodes = selector.xpath('.//%s' % spider.itertag)
return spider.get_urls_in_record(nodes[0])
def record(scrape_pos_page_body):
"""Return the results of the spider."""
spider = dnb_spider.DNBSpider()
with requests_mock.Mocker() as mock:
mock.head('http://nbn-resolving.de/urn:nbn:de:hebis:30:3-386257',
headers={
'Content-Type': 'text/html',
})
mock.head('http://d-nb.info/1079912991/34',
headers={
'Content-Type': 'application/pdf;charset=base64',
})
mock.head(
'http://publikationen.ub.uni-frankfurt.de/frontdoor/index/index/docId/38625',
headers={
'Content-Type': 'text/html',
})
request = spider.parse(
fake_response_from_file('dnb/test_1.xml')).next()
response = HtmlResponse(url=request.url,
request=request,
body=scrape_pos_page_body,
**{'encoding': 'utf-8'})
parsed_item = request.callback(response)
assert parsed_item
assert parsed_item.record
return parsed_item.record
def results():
"""Return results generator from the arxiv spider. All fields, one record.
"""
def _get_processed_item(item, spider):
record = pipeline.process_item(item, spider)
validate(record, 'hep')
assert record
return record
crawler = Crawler(spidercls=arxiv_spider.ArxivSpider)
spider = arxiv_spider.ArxivSpider.from_crawler(crawler)
fake_response = fake_response_from_file(
'arxiv/sample_arxiv_record0.xml',
response_type=TextResponse,
)
test_selectors = fake_response.xpath('.//record')
parsed_items = [spider.parse_record(sel) for sel in test_selectors]
pipeline = InspireCeleryPushPipeline()
pipeline.open_spider(spider)
yield [
_get_processed_item(parsed_item, spider)
for parsed_item in parsed_items
]
clean_dir()
def parse_requests():
"""Returns a fake request to the record file.
With links.
"""
spider = phil_spider.PhilSpider()
response = fake_response_from_file('phil/test_thesis.json')
return spider.parse(response)
def test_results_jats_parser_handle_date_absence():
from scrapy.http import XmlResponse
spider = aps_spider.APSSpider(aps_token="secret")
fake_response = fake_response_from_file(
'aps/PhysRevD.96.095036_no_date_nodes.xml',
response_type=XmlResponse,
)
record = spider._parse_jats(fake_response).record
assert validate(record, 'hep') is None
def record():
"""Return scraping results from the MIT spider."""
spider = mit_spider.MITSpider()
response = fake_response_from_file('mit/test_splash.html')
parsed_item = spider.build_item(response)
assert parsed_item
assert parsed_item.record
return parsed_item.record
def record():
"""Return scraping results from the INFN spider."""
spider = infn_spider.InfnSpider()
response = fake_response_from_file('infn/test_splash.html')
parsed_item = spider.scrape_splash(response)
assert parsed_item
assert parsed_item.record
return parsed_item.record
def results():
"""Return results generator from the Alpha spider."""
spider = alpha_spider.AlphaSpider()
parsed_items = list(
spider.parse(fake_response_from_file('alpha/test_1.htm')))
records = [parsed_item.record for parsed_item in parsed_items]
assert records
return records
def json_spider_record(tmpdir):
from scrapy.http import TextResponse
spider = arxiv_spider.ArxivSpider()
items = spider.parse(
fake_response_from_file(
'arxiv/sample_arxiv_record10.xml',
response_type=TextResponse,
), )
parsed_record = items.next()
assert parsed_record
return spider, parsed_record
def test_results_from_jats():
"""Get and validate results from mocking a JATS response."""
from scrapy.http import XmlResponse
spider = aps_spider.APSSpider()
fake_response = fake_response_from_file(
'aps/PhysRevD.96.095036.xml',
response_type=XmlResponse,
)
record = spider._parse_jats(fake_response).record
assert validate(record, 'hep') == None
def parsed_node():
"""Call parse_node and return its request call."""
spider = mit_spider.MITSpider()
response = fake_response_from_file('mit/test_list.html')
tag = spider.itertag
node = get_node(spider, tag, response, rtype="html")
parsed_item = spider.parse_node(response, node).next()
assert parsed_item
return parsed_item
def record():
"""Return results from the MAGIC spider. First parse node, then scrape,
and finally build the record.
"""
spider = magic_spider.MagicSpider()
response = fake_response_from_file('magic/test_1.html')
selector = Selector(response, type='html')
node = selector.xpath('//%s' % spider.itertag)[0]
spider.domain = "file:///tests/responses/magic/"
parsed_node = spider.parse_node(response, node)
splash_response = fake_response_from_file('magic/test_splash.html')
splash_response.meta["date"] = parsed_node.meta["date"]
splash_response.meta["urls"] = parsed_node.meta["urls"]
parsed_item = spider.scrape_for_pdf(splash_response).next()
assert parsed_item
assert parsed_item.record
return parsed_item.record
def test_results_from_jats():
"""Get and validate results from mocking a JATS response."""
from scrapy.http import XmlResponse
spider = aps_spider.APSSpider(aps_token="secret")
fake_response = fake_response_from_file(
'aps/PhysRevD.96.095036.xml',
response_type=XmlResponse,
)
record = spider._parse_jats(fake_response).record
assert validate(record, 'hep') is None
def record():
"""Return the results from the Hindawi spider."""
spider = hindawi_spider.HindawiSpider()
response = fake_response_from_file("hindawi/test_1.xml")
nodes = get_node(spider, "//marc:record", response)
parsed_item = spider.parse_node(response, nodes[0])
assert parsed_item
assert parsed_item.record
return parsed_item.record
def test_error_handler(crawler):
"""Test ErrorHandler extension."""
handler = ErrorHandler.from_crawler(crawler)
response = crawler.spider.parse(
fake_response_from_file('world_scientific/sample_ws_record.xml'))
assert 'errors' not in crawler.spider.state
handler.spider_error("Some failure", response, crawler.spider)
assert 'errors' in crawler.spider.state
assert crawler.spider.state['errors'][0]["exception"] == "Some failure"
assert crawler.spider.state['errors'][0]["sender"] == response
def record():
"""Return the results from the Hindawi spider."""
spider = hindawi_spider.HindawiSpider()
response = fake_response_from_file("hindawi/test_1.xml")
nodes = get_node(spider, "//marc:record", response)
parsed_item = spider.parse_node(response, nodes[0])
assert parsed_item
assert parsed_item.record
return parsed_item.record
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"]
parsed_item = spider.scrape_for_pdf(splash_response).next()
assert parsed_item
assert parsed_item.record
return parsed_item.record
def test_error_handler(crawler):
"""Test ErrorHandler extension."""
handler = ErrorHandler.from_crawler(crawler)
response = crawler.spider.parse(fake_response_from_file(
'world_scientific/sample_ws_record.xml'
))
assert 'errors' not in crawler.spider.state
handler.spider_error("Some failure", response, crawler.spider)
assert 'errors' in crawler.spider.state
assert crawler.spider.state['errors'][0]["exception"] == "Some failure"
assert crawler.spider.state['errors'][0]["sender"] == response
def record():
"""Return results generator from the Alpha spider."""
spider = phenix_spider.PhenixSpider()
response = fake_response_from_file('phenix/test_1.html')
selector = Selector(response, type='html')
nodes = selector.xpath('//%s' % spider.itertag)
parsed_item = spider.parse_node(response, nodes[0])
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 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 test_parse_node_nolink():
"""Test parse_node function. This time there is no splash page link.
The result should be a HEPRecord with minimal data.
"""
spider = infn_spider.InfnSpider()
response = fake_response_from_file('infn/test_1_nolink.html')
selector = Selector(response, type='html')
node = selector.xpath('//%s' % spider.itertag)[0]
parsed_item = spider.parse_node(response, node).next()
assert parsed_item
assert parsed_item.record
assert isinstance(parsed_item.record, hepcrawl.items.HEPRecord)
def record():
"""Return results from the Brown spider."""
spider = brown_spider.BrownSpider()
with requests_mock.Mocker() as mock:
mock.head(
'http://www.example.com/studio/item/bdr:11303/PDF/',
headers={
'Content-Type': 'text/html',
},
)
response = fake_response_from_file('brown/test_1.json')
jsonresponse = json.loads(response.body_as_unicode())
jsonrecord = jsonresponse["items"]["docs"][0]
jsonrecord["uri"] = "brown/test_splash.html"
splash_response = fake_response_from_file('brown/test_splash.html')
splash_response.meta["jsonrecord"] = jsonrecord
parsed_item = spider.scrape_splash(splash_response)
assert parsed_item
assert parsed_item.record
return parsed_item.record
def splash():
"""Call web scraper function, return final HEPRecord."""
spider = base_spider.BaseSpider()
splash_response = fake_response_from_file('base/test_1_splash.htm')
response = fake_response_from_file('base/test_1.xml')
selector = Selector(response, type='xml')
spider._register_namespaces(selector)
nodes = selector.xpath('.//%s' % spider.itertag)
splash_response.meta["record"] = nodes[0].extract()
with requests_mock.Mocker() as mock:
mock.head(
'http://www.example.com/bitstream/1885/10005/1/Butt_R.D._2003.pdf',
headers={
'Content-Type': 'text/html',
},
)
parsed_item = spider.scrape_for_pdf(splash_response)
assert parsed_item
assert parsed_item.record
return parsed_item.record
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)
parsed_item = spider.parse_node(response, nodes[0]).next()
assert parsed_item
assert parsed_item.record
return parsed_item.record
def json_spider_record(tmpdir):
from scrapy.http import TextResponse
spider = arxiv_spider.ArxivSpider()
fake_response = fake_response_from_file(
'arxiv/sample_arxiv_record10.xml',
response_type=TextResponse,
)
test_selectors = fake_response.xpath('.//record')
items = (spider.parse_record(sel) for sel in test_selectors)
parsed_record = items.next()
assert parsed_record
yield spider, parsed_record
clean_dir()
def journal():
"""Return results generator from the Phil spider.
Journal specific.
"""
spider = phil_spider.PhilSpider()
response = fake_response_from_file('phil/test_journal.json')
jsonrecord = json.loads(response.body_as_unicode())
response.meta["jsonrecord"] = jsonrecord[0]
parsed_item = spider.build_item(response)
assert parsed_item
assert parsed_item.record
return parsed_item.record
def record_rich(package_rich):
"""Return results from the EDP spider with 'rich' format.
This is not an open access journal, so no splash scraping.
"""
spider = edp_spider.EDPSpider()
xml_path = package_rich.url.replace("file://", "")
fake_resp = fake_response_from_file(xml_path)
fake_resp.meta["rich"] = True
node = get_node(spider, "//EDPSArticle", fake_resp)[0]
parsed_item = spider.parse_node(fake_resp, node)
assert parsed_item
assert parsed_item.record
return parsed_item.record
def get_records(response_file_name):
"""Return all results generator from the WSP spider via pipelines."""
# environmental variables needed for the pipelines payload
os.environ['SCRAPY_JOB'] = 'scrapy_job'
os.environ['SCRAPY_FEED_URI'] = 'scrapy_feed_uri'
os.environ['SCRAPY_LOG_FILE'] = 'scrapy_log_file'
spider = create_spider()
records = spider.parse(
fake_response_from_file(file_name=response_file_name,
response_type=TextResponse))
pipeline = InspireCeleryPushPipeline()
pipeline.open_spider(spider)
return (pipeline.process_item(record, spider).record for record in records)
def record_rich(package_rich):
"""Return results from the EDP spider with 'rich' format.
This is not an open access journal, so no splash scraping.
"""
spider = edp_spider.EDPSpider()
xml_path = package_rich.url.replace("file://", "")
fake_resp = fake_response_from_file(xml_path)
fake_resp.meta["rich"] = True
node = get_node(spider, "//EDPSArticle", fake_resp)[0]
parsed_item = spider.parse_node(fake_resp, node)
assert parsed_item
assert parsed_item.record
return parsed_item.record
def record():
"""Return built HEPRecord from the BASE spider."""
spider = base_spider.BaseSpider()
response = fake_response_from_file('base/test_1.xml')
selector = Selector(response, type='xml')
spider._register_namespaces(selector)
nodes = selector.xpath('.//%s' % spider.itertag)
response.meta["record"] = nodes[0].extract()
response.meta["urls"] = ["http://hdl.handle.net/1885/10005"]
parsed_item = spider.build_item(response)
assert parsed_item
assert parsed_item.record
return parsed_item.record
def record_jats(package_jats, scrape_pos_page_body):
"""Return results from the EDP spider with JATS format.
This is an open access journal, so we can scrape the splash page.
"""
spider = edp_spider.EDPSpider()
xml_path = package_jats.url.replace("file://", "")
fake_resp = fake_response_from_file(xml_path)
node = get_node(spider, "//article", fake_resp)[0]
request = spider.parse_node(fake_resp, node)
response = HtmlResponse(
url=request.url,
request=request,
body=scrape_pos_page_body,
**{'encoding': 'utf-8'}
)
parsed_item = request.callback(response)
assert parsed_item
assert parsed_item.record
return parsed_item.record
def get_records(response_file_name):
"""Return all results generator from the WSP spider via pipelines."""
# environmental variables needed for the pipelines payload
os.environ['SCRAPY_JOB'] = 'scrapy_job'
os.environ['SCRAPY_FEED_URI'] = 'scrapy_feed_uri'
os.environ['SCRAPY_LOG_FILE'] = 'scrapy_log_file'
spider = create_spider()
records = spider.parse(
fake_response_from_file(
file_name=response_file_name,
response_type=TextResponse
)
)
pipeline = InspireCeleryPushPipeline()
pipeline.open_spider(spider)
return (
pipeline.process_item(record, spider)['record']
for record in records
)
def results_from_json():
"""Return results by parsing a JSON file."""
from scrapy.http import TextResponse
spider = aps_spider.APSSpider()
parsed_items = list(
spider.parse(
fake_response_from_file(
'aps/aps_single_response.json',
response_type=TextResponse,
)
)
)
class MockFailure:
"""Mock twisted.python.failure.Failure, failure on JATS request."""
def __init__(self):
self.request = parsed_items[0]
records = [spider._parse_json_on_failure(MockFailure()).record]
assert records
return records
def many_results(spider):
"""Return results generator from the arxiv spider. Tricky fields, many
records.
"""
def _get_processed_record(item, spider):
crawl_result = pipeline.process_item(item, spider)
return crawl_result['record']
fake_response = fake_response_from_file(
'arxiv/sample_arxiv_record.xml',
response_type=TextResponse,
)
test_selectors = fake_response.xpath('.//record')
parsed_items = [spider.parse_record(sel) for sel in test_selectors]
pipeline = InspireCeleryPushPipeline()
pipeline.open_spider(spider)
yield [
_get_processed_record(parsed_item, spider)
for parsed_item in parsed_items
]
clean_dir()
def results():
"""Return results generator from the arxiv spider. All fields, one record.
"""
def _get_record_from_processed_item(item, spider):
crawl_result = pipeline.process_item(item, spider)
validate(crawl_result['record'], 'hep')
assert crawl_result
return crawl_result['record']
crawler = Crawler(spidercls=arxiv_spider.ArxivSpider)
spider = arxiv_spider.ArxivSpider.from_crawler(crawler)
fake_response = fake_response_from_file(
'arxiv/sample_arxiv_record0.xml',
response_type=TextResponse,
)
test_selectors = fake_response.xpath('.//record')
parsed_items = [spider.parse_record(sel) for sel in test_selectors]
pipeline = InspireCeleryPushPipeline()
pipeline.open_spider(spider)
yield [_get_record_from_processed_item(parsed_item, spider) for parsed_item in parsed_items]
clean_dir()
