Improved tests

maigret/checking.py

@@ -26,7 +26,7 @@ from .executors import (
 from .result import QueryResult, QueryStatus
 from .sites import MaigretDatabase, MaigretSite
 from .types import QueryOptions, QueryResultWrapper
-from .utils import get_random_user_agent
+from .utils import get_random_user_agent, ascii_data_display
 
 
 SUPPORTED_IDS = (
@@ -233,9 +233,9 @@ def process_site_result(
             result = build_result(QueryStatus.CLAIMED)
         else:
             result = build_result(QueryStatus.AVAILABLE)
-    elif check_type == "status_code":
+    elif check_type in "status_code":
         # Checks if the status code of the response is 2XX
-        if is_presense_detected and (not status_code >= 300 or status_code < 200):
+        if 200 <= status_code < 300:
             result = build_result(QueryStatus.CLAIMED)
         else:
             result = build_result(QueryStatus.AVAILABLE)
@@ -272,7 +272,7 @@ def process_site_result(
                     new_usernames[v] = k
 
             results_info["ids_usernames"] = new_usernames
-            links = eval(extracted_ids_data.get("links", "[]"))
+            links = ascii_data_display(extracted_ids_data.get("links", "[]"))
             if "website" in extracted_ids_data:
                 links.append(extracted_ids_data["website"])
             results_info["ids_links"] = links
@@ -456,7 +456,7 @@ async def maigret(
     logger,
     query_notify=None,
     proxy=None,
-    timeout=None,
+    timeout=3,
     is_parsing_enabled=False,
     id_type="username",
     debug=False,
@@ -478,7 +478,7 @@ async def maigret(
                               query results.
     logger                 -- Standard Python logger object.
     timeout                -- Time in seconds to wait before timing out request.
-                              Default is no timeout.
+                              Default is 3 seconds.
     is_parsing_enabled     -- Extract additional info from account pages.
     id_type                -- Type of username to search.
                               Default is 'username', see all supported here:

maigret/resources/data.json

@@ -13035,7 +13035,7 @@
                 "us"
             ],
             "headers": {
-                "authorization": "Bearer BQBeVMTwloR4yQEzyayWE7uYo1A4OHV3Oe3Uuv8nHCIJqj73fH6UOJoSfNbzqeSSfLXAFNABEUSHxTZmPe0"
+                "authorization": "Bearer BQBFMMVu1dPwJPlnzUteNyF8xlZy7545QnhHizEHWEUQGQrRLznY5k9B9v7JdAsL-wU-Tcep51JTqBesKKY"
             },
             "errors": {
                 "Spotify is currently not available in your country.": "Access denied in your country, use proxy/vpn"
@@ -14463,7 +14463,7 @@
                 "sec-ch-ua": "Google Chrome\";v=\"87\", \" Not;A Brand\";v=\"99\", \"Chromium\";v=\"87\"",
                 "authorization": "Bearer AAAAAAAAAAAAAAAAAAAAANRILgAAAAAAnNwIzUejRCOuH5E6I8xnZz4puTs%3D1Zv7ttfk8LF81IUq16cHjhLTvJu4FA33AGWWjCpTnA",
                 "user-agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36",
-                "x-guest-token": "1393906084428107777"
+                "x-guest-token": "1394397954526560260"
             },
             "errors": {
                 "Bad guest token": "x-guest-token update required"
@@ -14870,7 +14870,7 @@
                 "video"
             ],
             "headers": {
-                "Authorization": "jwt eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJleHAiOjE2MjExNjkwNDAsInVzZXJfaWQiOm51bGwsImFwcF9pZCI6NTg0NzksInNjb3BlcyI6InB1YmxpYyIsInRlYW1fdXNlcl9pZCI6bnVsbH0.uANToRPWBXHTZwnk-qucbJf-7ObHhCTwu87uJbEOj-I"
+                "Authorization": "jwt eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJleHAiOjE2MjEyODYyODAsInVzZXJfaWQiOm51bGwsImFwcF9pZCI6NTg0NzksInNjb3BlcyI6InB1YmxpYyIsInRlYW1fdXNlcl9pZCI6bnVsbH0.mxLdaOuP260WcxBvhadTTUQyn8t75pWNhTmtZLFS-W4"
             },
             "activation": {
                 "url": "https://vimeo.com/_rv/viewer",
@@ -15806,7 +15806,8 @@
             "url": "https://yandex.ru/bugbounty/researchers/{username}/",
             "source": "Yandex",
             "usernameClaimed": "pyrk1",
-            "usernameUnclaimed": "noonewouldeverusethis7"
+            "usernameUnclaimed": "noonewouldeverusethis7",
+            "disabled": true
         },
         "YandexCollections API": {
             "tags": [
@@ -16274,7 +16275,8 @@
         },
         "author.today": {
             "tags": [
-                "ru"
+                "ru",
+                "reading"
             ],
             "checkType": "status_code",
             "alexaRank": 12218,

maigret/utils.py

@@ -1,5 +1,7 @@
+import ast
 import re
 import random
+from typing import Any
 
 
 DEFAULT_USER_AGENTS = [
@@ -65,6 +67,10 @@ class URLMatcher:
         return re.compile(regexp_str)
 
 
+def ascii_data_display(data: str) -> Any:
+    return ast.literal_eval(data)
+
+
 def get_dict_ascii_tree(items, prepend="", new_line=True):
     text = ""
     for num, item in enumerate(items):
@@ -75,7 +81,8 @@ def get_dict_ascii_tree(items, prepend="", new_line=True):
             if field_value.startswith("['"):
                 is_last_item = num == len(items) - 1
                 prepend_symbols = " " * 3 if is_last_item else " ┃ "
-                field_value = get_dict_ascii_tree(eval(field_value), prepend_symbols)
+                data = ascii_data_display(field_value)
+                field_value = get_dict_ascii_tree(data, prepend_symbols)
             text += f"\n{prepend}{box_symbol}{field_name}: {field_value}"
         else:
             text += f"\n{prepend}{box_symbol} {item}"

tests/conftest.py

@@ -12,6 +12,7 @@ from maigret.maigret import setup_arguments_parser
 CUR_PATH = os.path.dirname(os.path.realpath(__file__))
 JSON_FILE = os.path.join(CUR_PATH, '../maigret/resources/data.json')
 TEST_JSON_FILE = os.path.join(CUR_PATH, 'db.json')
+LOCAL_TEST_JSON_FILE = os.path.join(CUR_PATH, 'local.json')
 empty_mark = Mark('', (), {})
 
 
@@ -36,16 +37,17 @@ def remove_test_reports():
 
 @pytest.fixture(scope='session')
 def default_db():
-    db = MaigretDatabase().load_from_file(JSON_FILE)
-
-    return db
+    return MaigretDatabase().load_from_file(JSON_FILE)
 
 
 @pytest.fixture(scope='function')
 def test_db():
-    db = MaigretDatabase().load_from_file(TEST_JSON_FILE)
+    return MaigretDatabase().load_from_file(TEST_JSON_FILE)
 
-    return db
+
+@pytest.fixture(scope='function')
+def local_test_db():
+    return MaigretDatabase().load_from_file(LOCAL_TEST_JSON_FILE)
 
 
 @pytest.fixture(autouse=True)
@@ -58,3 +60,8 @@ def reports_autoclean():
 @pytest.fixture(scope='session')
 def argparser():
     return setup_arguments_parser()
+
+
+@pytest.fixture(scope="session")
+def httpserver_listen_address():
+    return ("localhost", 8989)

tests/local.json

@@ -0,0 +1,21 @@
+{
+    "engines": {},
+    "sites": {
+        "StatusCode": {
+            "checkType": "status_code",
+            "url": "http://localhost:8989/url?id={username}",
+            "urlMain": "http://localhost:8989/",
+            "usernameClaimed": "claimed",
+            "usernameUnclaimed": "unclaimed"
+        },
+        "Message": {
+            "checkType": "message",
+            "url": "http://localhost:8989/url?id={username}",
+            "urlMain": "http://localhost:8989/",
+            "presenseStrs": ["user", "profile"],
+            "absenseStrs": ["not found", "404"],
+            "usernameClaimed": "claimed",
+            "usernameUnclaimed": "unclaimed"
+        }
+    }
+}

tests/test_checking.py

@@ -0,0 +1,65 @@
+from mock import Mock
+import pytest
+
+from maigret import search
+
+
+def site_result_except(server, username, **kwargs):
+    query = f'id={username}'
+    server.expect_request('/url', query_string=query).respond_with_data(**kwargs)
+
+
+@pytest.mark.asyncio
+async def test_checking_by_status_code(httpserver, local_test_db):
+    sites_dict = local_test_db.sites_dict
+
+    site_result_except(httpserver, 'claimed', status=200)
+    site_result_except(httpserver, 'unclaimed', status=404)
+
+    result = await search('claimed', site_dict=sites_dict, logger=Mock())
+    assert result['StatusCode']['status'].is_found() is True
+
+    result = await search('unclaimed', site_dict=sites_dict, logger=Mock())
+    assert result['StatusCode']['status'].is_found() is False
+
+
+@pytest.mark.asyncio
+async def test_checking_by_message_positive_full(httpserver, local_test_db):
+    sites_dict = local_test_db.sites_dict
+
+    site_result_except(httpserver, 'claimed', response_data="user profile")
+    site_result_except(httpserver, 'unclaimed', response_data="404 not found")
+
+    result = await search('claimed', site_dict=sites_dict, logger=Mock())
+    assert result['Message']['status'].is_found() is True
+
+    result = await search('unclaimed', site_dict=sites_dict, logger=Mock())
+    assert result['Message']['status'].is_found() is False
+
+
+@pytest.mark.asyncio
+async def test_checking_by_message_positive_part(httpserver, local_test_db):
+    sites_dict = local_test_db.sites_dict
+
+    site_result_except(httpserver, 'claimed', response_data="profile")
+    site_result_except(httpserver, 'unclaimed', response_data="404")
+
+    result = await search('claimed', site_dict=sites_dict, logger=Mock())
+    assert result['Message']['status'].is_found() is True
+
+    result = await search('unclaimed', site_dict=sites_dict, logger=Mock())
+    assert result['Message']['status'].is_found() is False
+
+
+@pytest.mark.asyncio
+async def test_checking_by_message_negative(httpserver, local_test_db):
+    sites_dict = local_test_db.sites_dict
+
+    site_result_except(httpserver, 'claimed', response_data="")
+    site_result_except(httpserver, 'unclaimed', response_data="user 404")
+
+    result = await search('claimed', site_dict=sites_dict, logger=Mock())
+    assert result['Message']['status'].is_found() is False
+
+    result = await search('unclaimed', site_dict=sites_dict, logger=Mock())
+    assert result['Message']['status'].is_found() is True

tests/test_utils.py

@@ -57,6 +57,11 @@ def test_enrich_link_str():
     )
 
 
+def test_url_extract_main_part_negative():
+    url_main_part = 'None'
+    assert URLMatcher.extract_main_part(url_main_part) == ''
+
+
 def test_url_extract_main_part():
     url_main_part = 'flickr.com/photos/alexaimephotography'