def get_result(self, url, html_str, keyword, last_modified):
'''
To calculate the number of keyword in html_str, and before doing real analyzing,
fetch the record by using last_modified to find whether the record had already done
before, to save the computing power of server
Args:
url (str): The url that you want to analyze
html_str (str): The html string that requested from url
keyword (str): The keyword that you want to find in url
last_modified (str): HTTP last_modified of website
Returns:
tuple: (The count number (int), need_to_save_db (boolean))
'''
record_query_cache = model.Record(url, keyword)
record_query_cache.query()
if last_modified is not None and record_query_cache.result is not None:
if record_query_cache.last_modified == last_modified:
return (record_query_cache.result, False)
return (self.count_from_string(html_str, keyword), True)
def test_add_record(self):
print("make a fake test record db")
r = model.Record('test', 'www.google.com', 99,
'Sat, 09 Mar 2019 13:44:12 GMT')
r.add()
def test_query_no_record(self):
r = model.Record('test2', 'www.googlegoogle.com')
r.query()
self.assertIs(r.result, None, 'Not none for dismatch')
def test_query_record(self):
print("test query")
r = model.Record('test', 'www.google.com')
r.query()
self.assertEqual(r.result, 99, 'write db and read db are not the same')
def save_record_to_db(url, keyword, result, last_modified):
'''
Save the record of analyzing to the Record DB
'''
record = model.Record(url, keyword, result, last_modified)
record.add()