#!/usr/bin/python3
import time
from flask import url_for
from urllib.request import urlopen
from .util import set_original_response, set_modified_response, live_server_setup, wait_for_all_checks
sleep_time_for_fetch_thread = 3
# Basic test to check inscriptus is not adding return line chars, basically works etc
def test_inscriptus():
from inscriptis import get_text
html_content = "test!
ok man"
stripped_text_from_html = get_text(html_content)
assert stripped_text_from_html == 'test!\nok man'
def test_check_basic_change_detection_functionality(client, live_server):
set_original_response()
live_server_setup(live_server)
# Add our URL to the import page
res = client.post(
url_for("import_page"),
data={"urls": url_for('test_endpoint', _external=True)},
follow_redirects=True
)
assert b"1 Imported" in res.data
time.sleep(sleep_time_for_fetch_thread)
# Do this a few times.. ensures we dont accidently set the status
for n in range(3):
client.get(url_for("form_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
wait_for_all_checks(client)
# It should report nothing found (no new 'unviewed' class)
res = client.get(url_for("index"))
assert b'unviewed' not in res.data
assert b'test-endpoint' in res.data
# Default no password set, this stuff should be always available.
assert b"SETTINGS" in res.data
assert b"BACKUP" in res.data
assert b"IMPORT" in res.data
#####################
# Check HTML conversion detected and workd
res = client.get(
url_for("preview_page", uuid="first"),
follow_redirects=True
)
# Check this class does not appear (that we didnt see the actual source)
assert b'foobar-detection' not in res.data
# Make a change
set_modified_response()
res = urlopen(url_for('test_endpoint', _external=True))
assert b'which has this one new line' in res.read()
# Force recheck
res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
assert b'1 watches are queued for rechecking.' in res.data
wait_for_all_checks(client)
# Now something should be ready, indicated by having a 'unviewed' class
res = client.get(url_for("index"))
assert b'unviewed' in res.data
# #75, and it should be in the RSS feed
res = client.get(url_for("rss"))
expected_url = url_for('test_endpoint', _external=True)
assert b' in settings
res = client.post(
url_for("settings_page"),
data={"application-extract_title_as_title": "1", "requests-time_between_check-minutes": 180,
'application-fetch_backend': "html_requests"},
follow_redirects=True
)
client.get(url_for("form_watch_checknow"), follow_redirects=True)
wait_for_all_checks(client)
res = client.get(url_for("index"))
assert b'unviewed' in res.data
assert b'Mark all viewed' in res.data
# It should have picked up the
assert b'head title' in res.data
# hit the mark all viewed link
res = client.get(url_for("mark_all_viewed"), follow_redirects=True)
assert b'Mark all viewed' not in res.data
assert b'unviewed' not in res.data
#
# Cleanup everything
res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data