9f435bf8fe
- Switches from pycurl to requests library - Allows for less janky decoding, especially with non-latin character sets - Adds session level management of user configs - Allows for each session to set its own config (people are probably going to complain about this, though not sure if it'll be the same number of people who are upset that their friends/family have to share their config) - Updates key gen/regen to more aggressively swap out keys after each request
68 lines
1.9 KiB
Python
68 lines
1.9 KiB
Python
from bs4 import BeautifulSoup
|
|
from app.filter import Filter
|
|
from app.utils.misc import generate_user_keys
|
|
from datetime import datetime
|
|
from dateutil.parser import *
|
|
|
|
|
|
def get_search_results(data):
|
|
secret_key = generate_user_keys()
|
|
soup = Filter(user_keys=secret_key).clean(BeautifulSoup(data, 'html.parser'))
|
|
|
|
main_divs = soup.find('div', {'id': 'main'})
|
|
assert len(main_divs) > 1
|
|
|
|
result_divs = []
|
|
for div in main_divs:
|
|
# Result divs should only have 1 inner div
|
|
if len(list(div.children)) != 1 or not div.findChild() or 'div' not in div.findChild().name:
|
|
continue
|
|
|
|
result_divs.append(div)
|
|
|
|
return result_divs
|
|
|
|
|
|
def test_get_results(client):
|
|
rv = client.get('/search?q=test')
|
|
assert rv._status_code == 200
|
|
|
|
# Depending on the search, there can be more
|
|
# than 10 result divs
|
|
assert len(get_search_results(rv.data)) >= 10
|
|
assert len(get_search_results(rv.data)) <= 15
|
|
|
|
|
|
def test_post_results(client):
|
|
rv = client.post('/search', data=dict(q='test'))
|
|
assert rv._status_code == 200
|
|
|
|
# Depending on the search, there can be more
|
|
# than 10 result divs
|
|
assert len(get_search_results(rv.data)) >= 10
|
|
assert len(get_search_results(rv.data)) <= 15
|
|
|
|
|
|
def test_recent_results(client):
|
|
times = {
|
|
'past year': 365,
|
|
'past month': 31,
|
|
'past week': 7
|
|
}
|
|
|
|
for time, num_days in times.items():
|
|
rv = client.post('/search', data=dict(q='test :' + time))
|
|
result_divs = get_search_results(rv.data)
|
|
|
|
current_date = datetime.now()
|
|
for div in result_divs:
|
|
date_span = div.find('span').decode_contents()
|
|
if not date_span or len(date_span) > 15 or len(date_span) < 7:
|
|
continue
|
|
|
|
try:
|
|
date = parse(date_span)
|
|
assert (current_date - date).days <= (num_days + 5) # Date can have a little bit of wiggle room
|
|
except ParserError:
|
|
pass
|