def test_to_ensure_relevant_ads_appear_when_no_ads_available(self):
urls = [
'http://quotes.toscrape.com/page/2/',
'http://quotes.toscrape.com/page/1/'
]
result = scrape('random', urls.copy())
self.assertEqual(result[1].get('zone_id'), 'zone755505698')
def test_to_ensure_relevant_ads_appear_when_ads_available(self):
urls = [
'http://quotes.toscrape.com/page/2/',
'http://quotes.toscrape.com/page/1/'
]
result = scrape('football', urls.copy())
self.assertEqual(result[1].get('zone_id'), 'zone669165852')
def test_a_whole_word_is_not_needed_to_match(self):
urls = [
'http://quotes.toscrape.com/page/2/',
'http://quotes.toscrape.com/page/1/'
]
result = scrape('indifference', urls.copy())
self.assertEqual(len(result[0]), 1)
self.assertEqual(result[0][0].get('url'),
'http://quotes.toscrape.com/page/2/')
def test_every_word_searched_for_gets_accounted_for(self):
urls = [
'http://quotes.toscrape.com/page/2/',
'http://quotes.toscrape.com/page/1/'
]
result = scrape('BOB albert', urls.copy())
self.assertEqual(len(result[0]), 2)
for entry in result[0]:
self.assertTrue(entry.get('url') in urls)
def upload_csv():
if request.method == 'POST':
# check if the post request has the file part
if 'file' not in request.files:
flash('No file part')
return Response("No File", 404)
file = request.files['file']
if file.filename == '':
return Response("No File", 404)
if file and allowed_file(file.filename):
res = insta.scrape(file)
return send_file(res)\
def test_scrape(self):
"""
test case for crawl
"""
items = app.scrape(self.html)
self.assertIsNotNone(items)
# Add parent directory
import os, sys, inspect
currentdir = os.path.dirname(
os.path.abspath(inspect.getfile(inspect.currentframe())))
sys.path.insert(0, os.path.dirname(currentdir))
from app import scrape
WEBSITE = 'http://www.bierbrierdevelopment.com/'
if __name__ == '__main__':
result = scrape(website=WEBSITE)
print('{} Results Found'.format(len(result)))
def tests_all_urls(self):
urls = Urls.urls.copy()
result = scrape('a', Urls.urls)
self.assertEqual(len(result[0]), len(urls))
for entry in result[0]:
self.assertTrue(entry.get('url') in urls)
def test_search_string_return_correct_answer_uppercase(self):
url = 'http://quotes.toscrape.com/page/2/'
result = scrape('BOB', [url])
self.assertEqual(len(result[0]), 1)
self.assertEqual(result[0][0].get('url'), url)