Tidy up proxies.json logic, adding tests (#955)

changedetectionio/__init__.py

@@ -1444,12 +1444,7 @@ def ticker_thread_check_time_launch_checks():
                 if not uuid in running_uuids and uuid not in [q_uuid for p,q_uuid in update_q.queue]:
 
                     # Proxies can be set to have a limit on seconds between which they can be called
-                    watch_proxy = watch.get('proxy')
-                    if not watch_proxy:
-                        watch_proxy = datastore.data['settings']['requests']['proxy']
-                        if not watch_proxy:
-                            watch_proxy = list(datastore.proxy_list.keys())[0]
-
+                    watch_proxy = datastore.get_preferred_proxy_for_watch(uuid=uuid)
                     if watch_proxy and watch_proxy in list(datastore.proxy_list.keys()):
                         # Proxy may also have some threshold minimum
                         proxy_list_reuse_time_minimum = int(datastore.proxy_list.get(watch_proxy, {}).get('reuse_time_minimum', 0))

changedetectionio/fetch_site_status.py

@@ -20,36 +20,6 @@ class perform_site_check():
         super().__init__(*args, **kwargs)
         self.datastore = datastore
 
-    # If there was a proxy list enabled, figure out what proxy_args/which proxy to use
-    # Returns the proxy as a URL
-    # if watch.proxy use that
-    # fetcher.proxy_override = watch.proxy or main config proxy
-    # Allows override the proxy on a per-request basis
-    # ALWAYS use the first one is nothing selected
-
-    def set_proxy_from_list(self, watch):
-        proxy_args = None
-        if self.datastore.proxy_list is None:
-            return None
-
-        # If its a valid one
-        if watch['proxy'] and watch['proxy'] in list(self.datastore.proxy_list.keys()):
-            proxy_args = self.datastore.proxy_list.get(watch['proxy']).get('url')
-
-        # not valid (including None), try the system one
-        else:
-            system_proxy = self.datastore.data['settings']['requests']['proxy']
-            # Is not None and exists
-            if self.datastore.proxy_list.get(system_proxy):
-                proxy_args = self.datastore.proxy_list.get(system_proxy).get('url')
-
-        # Fallback - Did not resolve anything, use the first available
-        if proxy_args is None:
-            first_default = list(self.datastore.proxy_list)[0]
-            proxy_args = self.datastore.proxy_list.get(first_default).get('url')
-
-        return proxy_args
-
     # Doesn't look like python supports forward slash auto enclosure in re.findall
     # So convert it to inline flag "foobar(?i)" type configuration
     def forward_slash_enclosed_regex_to_options(self, regex):
@@ -114,9 +84,12 @@ class perform_site_check():
             # If the klass doesnt exist, just use a default
             klass = getattr(content_fetcher, "html_requests")
 
-        proxy_url = self.set_proxy_from_list(watch)
-        if proxy_url:
+        proxy_id = self.datastore.get_preferred_proxy_for_watch(uuid=uuid)
+        proxy_url = None
+        if proxy_id:
+            proxy_url = self.datastore.proxy_list.get(proxy_id).get('url')
             print ("UUID {} Using proxy {}".format(uuid, proxy_url))
+
         fetcher = klass(proxy_override=proxy_url)
 
         # Configurable per-watch or global extra delay before extracting text (for webDriver types)

changedetectionio/run_all_tests.sh

@@ -49,3 +49,47 @@ pytest tests/visualselector/test_fetch_data.py
 
 unset PLAYWRIGHT_DRIVER_URL
 docker kill $$-test_browserless
+
+# Test proxy list handling, starting two squids on different ports
+# Each squid adds a different header to the response, which is the main thing we test for.
+docker run -d --name $$-squid-one --rm -v `pwd`/tests/proxy_list/squid.conf:/etc/squid/conf.d/debian.conf -p 3128:3128 ubuntu/squid:4.13-21.10_edge
+docker run -d --name $$-squid-two --rm -v `pwd`/tests/proxy_list/squid.conf:/etc/squid/conf.d/debian.conf -p 3129:3128 ubuntu/squid:4.13-21.10_edge
+
+
+# So, basic HTTP as env var test
+export HTTP_PROXY=http://localhost:3128
+export HTTPS_PROXY=http://localhost:3128
+pytest tests/proxy_list/test_proxy.py
+docker logs $$-squid-one 2>/dev/null|grep one.changedetection.io
+if [ $? -ne 0 ]
+then
+  echo "Did not see a request to one.changedetection.io in the squid logs (while checking env vars HTTP_PROXY/HTTPS_PROXY)"
+fi
+unset HTTP_PROXY
+unset HTTPS_PROXY
+
+
+# 2nd test actually choose the preferred proxy from proxies.json
+cp tests/proxy_list/proxies.json-example ./test-datastore/proxies.json
+# Makes a watch use a preferred proxy
+pytest tests/proxy_list/test_multiple_proxy.py
+
+# Should be a request in the default "first" squid
+docker logs $$-squid-one 2>/dev/null|grep chosen.changedetection.io
+if [ $? -ne 0 ]
+then
+  echo "Did not see a request to chosen.changedetection.io in the squid logs (while checking preferred proxy)"
+fi
+
+# And one in the 'second' squid (user selects this as preferred)
+docker logs $$-squid-two 2>/dev/null|grep chosen.changedetection.io
+if [ $? -ne 0 ]
+then
+  echo "Did not see a request to chosen.changedetection.io in the squid logs (while checking preferred proxy)"
+fi
+
+# @todo - test system override proxy selection and watch defaults, setup a 3rd squid?
+docker kill $$-squid-one
+docker kill $$-squid-two
+
+

changedetectionio/store.py

@@ -440,6 +440,36 @@ class ChangeDetectionStore:
             print ("Registered proxy list", list(self.proxy_list.keys()))
 
 
+    def get_preferred_proxy_for_watch(self, uuid):
+        """
+        Returns the preferred proxy by ID key
+        :param uuid: UUID
+        :return: proxy "key" id
+        """
+
+        proxy_id = None
+        if self.proxy_list is None:
+            return None
+
+        # If its a valid one
+        watch = self.data['watching'].get(uuid)
+
+        if watch.get('proxy') and watch.get('proxy') in list(self.proxy_list.keys()):
+            return watch.get('proxy')
+
+        # not valid (including None), try the system one
+        else:
+            system_proxy_id = self.data['settings']['requests'].get('proxy')
+            # Is not None and exists
+            if self.proxy_list.get(system_proxy_id):
+                return system_proxy_id
+
+        # Fallback - Did not resolve anything, use the first available
+        if system_proxy_id is None:
+            first_default = list(self.proxy_list)[0]
+            return first_default
+
+        return None
 
     # Run all updates
     # IMPORTANT - Each update could be run even when they have a new install and the schema is correct

changedetectionio/tests/proxy_list/__init__.py

@@ -0,0 +1,2 @@
+"""Tests for the app."""
+

changedetectionio/tests/proxy_list/conftest.py

@@ -0,0 +1,14 @@
+#!/usr/bin/python3
+
+from .. import conftest
+
+#def pytest_addoption(parser):
+#    parser.addoption("--url_suffix", action="store", default="identifier for request")
+
+
+#def pytest_generate_tests(metafunc):
+#    # This is called for every test. Only get/set command line arguments
+#    # if the argument is specified in the list of test "fixturenames".
+#    option_value = metafunc.config.option.url_suffix
+#    if 'url_suffix' in metafunc.fixturenames and option_value is not None:
+#        metafunc.parametrize("url_suffix", [option_value])

changedetectionio/tests/proxy_list/proxies.json-example

@@ -0,0 +1,10 @@
+{
+  "proxy-one": {
+    "label": "One",
+    "url": "http://127.0.0.1:3128"
+  },
+  "proxy-two": {
+    "label": "two",
+    "url": "http://127.0.0.1:3129"
+  }
+}

changedetectionio/tests/proxy_list/squid.conf

@@ -0,0 +1,41 @@
+acl localnet src 0.0.0.1-0.255.255.255  # RFC 1122 "this" network (LAN)
+acl localnet src 10.0.0.0/8             # RFC 1918 local private network (LAN)
+acl localnet src 100.64.0.0/10          # RFC 6598 shared address space (CGN)
+acl localnet src 169.254.0.0/16         # RFC 3927 link-local (directly plugged) machines
+acl localnet src 172.16.0.0/12          # RFC 1918 local private network (LAN)
+acl localnet src 192.168.0.0/16         # RFC 1918 local private network (LAN)
+acl localnet src fc00::/7               # RFC 4193 local private network range
+acl localnet src fe80::/10              # RFC 4291 link-local (directly plugged) machines
+acl localnet src 159.65.224.174
+acl SSL_ports port 443
+acl Safe_ports port 80          # http
+acl Safe_ports port 21          # ftp
+acl Safe_ports port 443         # https
+acl Safe_ports port 70          # gopher
+acl Safe_ports port 210         # wais
+acl Safe_ports port 1025-65535  # unregistered ports
+acl Safe_ports port 280         # http-mgmt
+acl Safe_ports port 488         # gss-http
+acl Safe_ports port 591         # filemaker
+acl Safe_ports port 777         # multiling http
+acl CONNECT method CONNECT
+
+http_access deny !Safe_ports
+http_access deny CONNECT !SSL_ports
+http_access allow localhost manager
+http_access deny manager
+http_access allow localhost
+http_access allow localnet
+http_access deny all
+http_port 3128
+coredump_dir /var/spool/squid
+refresh_pattern ^ftp:           1440    20%     10080
+refresh_pattern ^gopher:        1440    0%      1440
+refresh_pattern -i (/cgi-bin/|\?) 0     0%      0
+refresh_pattern \/(Packages|Sources)(|\.bz2|\.gz|\.xz)$ 0 0% 0 refresh-ims
+refresh_pattern \/Release(|\.gpg)$ 0 0% 0 refresh-ims
+refresh_pattern \/InRelease$ 0 0% 0 refresh-ims
+refresh_pattern \/(Translation-.*)(|\.bz2|\.gz|\.xz)$ 0 0% 0 refresh-ims
+refresh_pattern .               0       20%     4320
+logfile_rotate 0
+

changedetectionio/tests/proxy_list/test_multiple_proxy.py

@@ -0,0 +1,38 @@
+#!/usr/bin/python3
+
+import time
+from flask import url_for
+from ..util import live_server_setup
+
+def test_preferred_proxy(client, live_server):
+    time.sleep(1)
+    live_server_setup(live_server)
+    time.sleep(1)
+    url = "http://chosen.changedetection.io"
+
+    res = client.post(
+        url_for("import_page"),
+        # Because a URL wont show in squid/proxy logs due it being SSLed
+        # Use plain HTTP or a specific domain-name here
+        data={"urls": url},
+        follow_redirects=True
+    )
+
+    assert b"1 Imported" in res.data
+
+    time.sleep(2)
+    res = client.post(
+        url_for("edit_page", uuid="first"),
+        data={
+                "css_filter": "",
+                "fetch_backend": "html_requests",
+                "headers": "",
+                "proxy": "proxy-two",
+                "tag": "",
+                "url": url,
+              },
+        follow_redirects=True
+    )
+    assert b"Updated watch." in res.data
+    time.sleep(2)
+    # Now the request should appear in the second-squid logs

changedetectionio/tests/proxy_list/test_proxy.py

@@ -0,0 +1,19 @@
+#!/usr/bin/python3
+
+import time
+from flask import url_for
+from ..util import live_server_setup, wait_for_all_checks, extract_UUID_from_client
+
+# just make a request, we will grep in the docker logs to see it actually got called
+def test_check_basic_change_detection_functionality(client, live_server):
+    live_server_setup(live_server)
+    res = client.post(
+        url_for("import_page"),
+        # Because a URL wont show in squid/proxy logs due it being SSLed
+        # Use plain HTTP or a specific domain-name here
+        data={"urls": "http://one.changedetection.io"},
+        follow_redirects=True
+    )
+
+    assert b"1 Imported" in res.data
+    time.sleep(3)

docker-compose.yml

@@ -6,6 +6,8 @@ services:
       hostname: changedetection
       volumes:
         - changedetection-data:/datastore
+# Configurable proxy list support, see https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#proxy-list-support
+#        - ./proxies.json:/datastore/proxies.json
 
   #    environment:
   #        Default listening port, can also be changed with the -p option