def test_get_publication_id_list_wrong_status_code(mock_get):
mock_get.return_value.status_code = 400
scrapper = NCBIPubScrapper()
publication_list = scrapper.get_publication_id_list(0, 2)
assert publication_list == []
def test_get_publication_content_wrong_status_code(mock_get):
mock_get.return_value.status_code = 400
publication_id = '12345'
scrapper = NCBIPubScrapper()
publication_content = scrapper.get_publication_content(publication_id)
assert publication_content is None
def test_get_publication_id_list_ok(mock_get, example_search_response):
mock_get.return_value.json.return_value = example_search_response
mock_get.return_value.status_code = 200
scrapper = NCBIPubScrapper()
publication_list = scrapper.get_publication_id_list(0, 2)
assert '31782494' in publication_list
assert '31782426' in publication_list
def test_get_extracted_emails_no_mails():
publication_content = """
test test test
another test string
lorem ipsum.
"""
scrapper = NCBIPubScrapper()
emails = scrapper.get_extracted_emails(publication_content)
assert len(emails) == 0
def test_get_publication_content_ok(mock_get, example_publication_content):
mock_get.return_value.content.decode.return_value = example_publication_content
mock_get.return_value.status_code = 200
publication_id = '12345'
scrapper = NCBIPubScrapper()
publication_content = scrapper.get_publication_content(publication_id)
assert 'Baylor College of Medicine' in publication_content
def test_get_extracted_emails_multiple_mails():
publication_content = """
test test test
[email protected]
another test string
[email protected], lorem ipsum.
[email protected]
"""
scrapper = NCBIPubScrapper()
emails = scrapper.get_extracted_emails(publication_content)
assert '*****@*****.**' in emails
assert '*****@*****.**' in emails
assert '*****@*****.**' in emails
assert len(emails) == 3
def test_create_ncbi_object():
test_email = '*****@*****.**'
test_publication_id = '12345'
test_ncbi_object = NCBIObject(
email=test_email,
publication_id=test_publication_id,
publication_url=f'https://www.ncbi.nlm.nih.gov/pubmed/{test_publication_id}',
)
scrapper = NCBIPubScrapper()
ncbi_object = scrapper.create_ncbi_object(test_email, test_publication_id)
assert ncbi_object.email == test_ncbi_object.email
assert ncbi_object.publication_id == test_ncbi_object.publication_id
assert ncbi_object.publication_url == test_ncbi_object.publication_url
def ncbi_scrapper_run_view():
form = NCBIScrapperForm()
form.mail_package.choices = get_mail_package_choices()
if form.validate_on_submit():
scrapper = NCBIPubScrapper()
ncbi_objects = scrapper.run(0, form.publication_number.data)
objects_to_add = []
for ncbi_object in ncbi_objects:
ncbi_mail = NCBIMail(
publication_id=ncbi_object.publication_id,
ncbi_publication_url=ncbi_object.publication_url,
email=ncbi_object.email,
package_id=form.mail_package.data,
)
exist = NCBIMail.query.filter_by(email=ncbi_mail.email).first()
if not exist:
objects_to_add.append(ncbi_mail)
flash(f'Successfully added {ncbi_mail.email}', 'info')
else:
flash(f'E-mail {ncbi_mail.email} already exist in DB', 'danger')
if objects_to_add:
db.session.add_all(objects_to_add)
db.session.commit()
flash(
f'You have successfully scrapped {len(objects_to_add)} e-mails ',
f'form {form.publication_number.data} NCBI publications success',
)
return redirect(url_for('userpanel.ncbi_scrapper_run_view'))
return render_template('userpanel/ncbi_scrapper/scrapper.html', form=form)
def test_get_extracted_emails_ok(example_publication_content):
scrapper = NCBIPubScrapper()
emails = scrapper.get_extracted_emails(example_publication_content)
assert '*****@*****.**' in emails