def assert_scrape_result(doi, pdf_url, metadata_url, license, evidence):
my_pub = pub.lookup_product_by_doi(doi)
my_pub.refresh_hybrid_scrape()
logger.info(u"was looking for pdf url {}, got {}".format(
pdf_url, my_pub.scrape_pdf_url))
logger.info(u"was looking for metadata url {}, got {}".format(
metadata_url, my_pub.scrape_metadata_url))
logger.info(u"was looking for license {}, got {}".format(
license, my_pub.scrape_license))
logger.info(u"was looking for evidence {}, got {}".format(
evidence, my_pub.scrape_evidence))
logger.info(u"https://api.unpaywall.org/v2/{}?email=me".format(doi))
logger.info(u"doi: https://doi.org/{}".format(doi))
if my_pub.error:
logger.info(my_pub.error)
assert_equals(my_pub.error, "")
assert_equals_case_insensitive(my_pub.scrape_pdf_url, pdf_url)
assert_equals_case_insensitive(my_pub.scrape_metadata_url, metadata_url)
assert_equals(my_pub.scrape_license, license)
assert_equals(my_pub.scrape_evidence, evidence)
my_pub.ask_hybrid_scrape()
if pdf_url or metadata_url:
location = my_pub.open_locations[0]
assert_equals_case_insensitive(location.pdf_url, pdf_url)
assert_equals_case_insensitive(location.metadata_url, metadata_url)
assert_equals(location.evidence, evidence)
assert_equals(location.license, license)
else:
assert_false(my_pub.open_locations)
def test_chorus_dois(self, test_data):
doi = test_data
# because cookies breaks the cache pickling
# for doi_start in ["10.1109", "10.1161", "10.1093", "10.1007", "10.1039"]:
# if doi.startswith(doi_start):
requests_cache.uninstall_cache()
my_pub = pub.lookup_product_by_doi(doi)
if not my_pub:
logger.info(u"doi {} not in db, skipping".format(doi))
return
my_pub.refresh()
logger.info(u"https://api.unpaywall.org/v2/{}?email=me".format(doi))
logger.info(u"doi: https://doi.org/{}".format(doi))
logger.info(u"license: {}".format(my_pub.best_license))
logger.info(u"evidence: {}".format(my_pub.best_evidence))
logger.info(u"host: {}".format(my_pub.best_host))
if my_pub.error:
logger.info(my_pub.error)
assert_equals(my_pub.error, "")
assert_is_not_none(my_pub.fulltext_url)
def test_active_dois(self, test_data):
(doi, fulltext_url, license, color) = test_data
# because cookies breaks the cache pickling
# for doi_start in ["10.1109", "10.1161", "10.1093", "10.1007", "10.1039"]:
# if doi.startswith(doi_start):
# requests_cache.uninstall_cache()
my_pub = pub.lookup_product_by_doi(doi)
my_pub.refresh()
logger.info(u"\n\nwas looking for {}, got {}".format(
fulltext_url, my_pub.fulltext_url))
logger.info(u"https://api.unpaywall.org/v2/{}?email=me".format(doi))
logger.info(u"doi: https://doi.org/{}".format(doi))
logger.info(u"license: {}".format(my_pub.license))
logger.info(u"oa_color: {}".format(my_pub.oa_color))
logger.info(u"evidence: {}".format(my_pub.evidence))
if my_pub.error:
logger.info(my_pub.error)
assert_equals(my_pub.error, "")
assert_equals(my_pub.fulltext_url, fulltext_url)
assert_not_equals(my_pub.fulltext_url, None)
# assert_equals(my_pub.license, license)
assert_equals(my_pub.error, "")
def test_active_dois(self, test_data):
(doi, fulltext_url, license, color) = test_data
# because cookies breaks the cache pickling
# for doi_start in ["10.1109", "10.1161", "10.1093", "10.1007", "10.1039"]:
# if doi.startswith(doi_start):
# requests_cache.uninstall_cache()
my_pub = pub.lookup_product_by_doi(doi)
my_pub.refresh()
logger.info(u"\n\nwas looking for {}, got {}".format(fulltext_url, my_pub.fulltext_url))
logger.info(u"https://api.unpaywall.org/v2/{}?email=me".format(doi))
logger.info(u"doi: https://doi.org/{}".format(doi))
logger.info(u"license: {}".format(my_pub.license))
logger.info(u"oa_color: {}".format(my_pub.oa_color))
logger.info(u"evidence: {}".format(my_pub.evidence))
if my_pub.error:
logger.info(my_pub.error)
assert_equals(my_pub.error, "")
assert_equals(my_pub.fulltext_url, fulltext_url)
assert_not_equals(my_pub.fulltext_url, None)
# assert_equals(my_pub.license, license)
assert_equals(my_pub.error, "")
def test_chorus_dois(self, test_data):
doi = test_data
# because cookies breaks the cache pickling
# for doi_start in ["10.1109", "10.1161", "10.1093", "10.1007", "10.1039"]:
# if doi.startswith(doi_start):
requests_cache.uninstall_cache()
my_pub = pub.lookup_product_by_doi(doi)
if not my_pub:
logger.info(u"doi {} not in db, skipping".format(doi))
return
my_pub.refresh()
logger.info(u"https://api.unpaywall.org/v2/{}?email=me".format(doi))
logger.info(u"doi: https://doi.org/{}".format(doi))
logger.info(u"license: {}".format(my_pub.best_license))
logger.info(u"evidence: {}".format(my_pub.best_evidence))
logger.info(u"host: {}".format(my_pub.best_host))
if my_pub.error:
logger.info(my_pub.error)
assert_equals(my_pub.error, "")
assert_is_not_none(my_pub.fulltext_url)
def test_open_dois(self, test_data):
(doi, fulltext_url, license) = test_data
my_pub = pub.lookup_product_by_doi(doi)
my_pub.recalculate()
logger.info(u"was looking for {}, got {}\n\n".format(
fulltext_url, my_pub.fulltext_url))
logger.info(u"doi: http://doi.org/{}".format(doi))
logger.info(u"title: {}".format(my_pub.best_title))
logger.info(u"evidence: {}\n\n".format(my_pub.evidence))
if my_pub.error:
logger.info(my_pub.error)
assert_not_equals(my_pub.fulltext_url, None)
def test_open_dois(self, test_data):
(doi, fulltext_url, license) = test_data
my_pub = pub.lookup_product_by_doi(doi)
my_pub.recalculate()
logger.info(u"was looking for {}, got {}\n\n".format(fulltext_url, my_pub.fulltext_url))
logger.info(u"https://api.unpaywall.org/v2/{}?email=me".format(doi))
logger.info(u"doi: https://doi.org/{}".format(doi))
logger.info(u"title: {}".format(my_pub.best_title))
logger.info(u"evidence: {}\n\n".format(my_pub.evidence))
if my_pub.error:
logger.info(my_pub.error)
assert_not_equals(my_pub.fulltext_url, None)
assert_equals(fulltext_url, my_pub.fulltext_url)
def test_arxiv_dois(self, test_data):
(doi, fulltext_url, license) = test_data
my_pub = pub.lookup_product_by_doi(doi)
my_pub.recalculate()
logger.info(u"was looking for {}, got {}\n\n".format(fulltext_url, my_pub.fulltext_url))
logger.info(u"https://api.unpaywall.org/v2/{}?email=me".format(doi))
logger.info(u"doi: https://doi.org/{}".format(doi))
logger.info(u"title: {}".format(my_pub.best_title))
logger.info(u"evidence: {}\n\n".format(my_pub.evidence))
if my_pub.error:
logger.info(my_pub.error)
assert_not_equals(my_pub.fulltext_url, None)
# not sure that the arxiv url will be the best one, but make sure it is one of them
urls = [loc.pdf_url for loc in my_pub.all_oa_locations]
assert_true(fulltext_url in urls)
def test_arxiv_dois(self, test_data):
(doi, fulltext_url, license) = test_data
my_pub = pub.lookup_product_by_doi(doi)
my_pub.recalculate()
logger.info(u"was looking for {}, got {}\n\n".format(fulltext_url, my_pub.fulltext_url))
logger.info(u"https://api.unpaywall.org/v2/{}?email=me".format(doi))
logger.info(u"doi: https://doi.org/{}".format(doi))
logger.info(u"title: {}".format(my_pub.best_title))
logger.info(u"evidence: {}\n\n".format(my_pub.evidence))
if my_pub.error:
logger.info(my_pub.error)
assert_not_equals(my_pub.fulltext_url, None)
# not sure that the arxiv url will be the best one, but make sure it is one of them
urls = [loc.pdf_url for loc in my_pub.all_oa_locations]
assert_true(fulltext_url in urls)
def test_sciencedirect_dois(self, test_data):
(doi, pdf_url, metadata_url, license, evidence) = test_data
my_pub = pub.lookup_product_by_doi(doi)
my_pub.refresh_hybrid_scrape()
logger.info(u"was looking for pdf url {}, got {}".format(pdf_url, my_pub.scrape_pdf_url))
logger.info(u"was looking for metadata url {}, got {}".format(metadata_url, my_pub.scrape_metadata_url))
logger.info(u"was looking for license {}, got {}".format(license, my_pub.scrape_license))
logger.info(u"was looking for evidence {}, got {}".format(evidence, my_pub.scrape_evidence))
logger.info(u"https://api.unpaywall.org/v2/{}?email=me".format(doi))
logger.info(u"doi: https://doi.org/{}".format(doi))
if my_pub.error:
logger.info(my_pub.error)
assert_equals(my_pub.error, "")
assert_equals(my_pub.scrape_pdf_url, pdf_url)
assert_equals(my_pub.scrape_metadata_url, metadata_url)
assert_equals(my_pub.scrape_license, license)
assert_equals(my_pub.scrape_evidence, evidence)