Use time() as priority

README.md

@@ -1,21 +1,15 @@
-#  changedetection.io
+## Web Site Change Detection, Monitoring and Notification.
+
+[**Try our $6.99/month subscription - Unlimited checks and watches!**](https://lemonade.changedetection.io/start)
+ 
+
+[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot.png" style="max-width:100%;" alt="Self-hosted web page change monitoring"  title="Self-hosted web page change monitoring"  />](https://lemonade.changedetection.io/start)
+
 [![Release Version][release-shield]][release-link] [![Docker Pulls][docker-pulls]][docker-link] [![License][license-shield]](LICENSE.md)
 
 ![changedetection.io](https://github.com/dgtlmoon/changedetection.io/actions/workflows/test-only.yml/badge.svg?branch=master)
 
-## Web Site Change Detection, Monitoring and Notification - Self-Hosted or SaaS.
-
-_Know when web pages change! Stay ontop of new information! get notifications when important website content changes_ 
-
-Live your data-life *pro-actively* instead of *re-actively*.
-
-Free, Open-source web page monitoring, notification and change detection. Don't have time? [**Try our $6.99/month subscription - unlimited checks and watches!**](https://lemonade.changedetection.io/start)
-
-
-[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot.png" style="max-width:100%;" alt="Self-hosted web page change monitoring"  title="Self-hosted web page change monitoring"  />](https://lemonade.changedetection.io/start)
-
-
-**Get your own private instance now! Let us host it for you!**
+Know when important content changes, we support notifications via Discord, Telegram, Home-Assistant, Slack, Email and 70+ more
 
 [**Try our $6.99/month subscription - unlimited checks and watches!**](https://lemonade.changedetection.io/start) , _half the price of other website change monitoring services and comes with unlimited watches & checks!_
 

changedetectionio/__init__.py

@@ -1385,13 +1385,18 @@ def ticker_thread_check_time_launch_checks():
             seconds_since_last_recheck = now - watch['last_checked']
             if seconds_since_last_recheck >= (threshold + watch.jitter_seconds) and seconds_since_last_recheck >= recheck_time_minimum_seconds:
                 if not uuid in running_uuids and uuid not in [q_uuid for p,q_uuid in update_q.queue]:
-                    print("> Queued watch UUID {} last checked at {} queued at {:0.2f} jitter {:0.2f}s, {:0.2f}s since last checked".format(uuid,
-                                                                                                         watch['last_checked'],
-                                                                                                         now,
-                                                                                                         watch.jitter_seconds,
-                                                                                                         now - watch['last_checked']))
+                    # Use Epoch time as priority, so we get a "sorted" PriorityQueue, but we can still push a priority 1 into it.
+                    priority = int(time.time())
+                    print(
+                        "> Queued watch UUID {} last checked at {} queued at {:0.2f} priority {} jitter {:0.2f}s, {:0.2f}s since last checked".format(
+                            uuid,
+                            watch['last_checked'],
+                            now,
+                            priority,
+                            watch.jitter_seconds,
+                            now - watch['last_checked']))
                     # Into the queue with you
-                    update_q.put((5, uuid))
+                    update_q.put((priority, uuid))
 
                     # Reset for next time
                     watch.jitter_seconds = 0

changedetectionio/content_fetcher.py

@@ -31,11 +31,12 @@ class JSActionExceptions(Exception):
         return
 
 class PageUnloadable(Exception):
-    def __init__(self, status_code, url, screenshot=False):
+    def __init__(self, status_code, url, screenshot=False, message=False):
         # Set this so we can use it in other parts of the app
         self.status_code = status_code
         self.url = url
         self.screenshot = screenshot
+        self.message = message
         return
 
 class EmptyReply(Exception):
@@ -292,7 +293,15 @@ class base_html_playwright(Fetcher):
 
         # allow per-watch proxy selection override
         if proxy_override:
-            self.proxy = {'server': proxy_override}
+            # https://playwright.dev/docs/network#http-proxy
+            from urllib.parse import urlparse
+            parsed = urlparse(proxy_override)
+            proxy_url = "{}://{}:{}".format(parsed.scheme, parsed.hostname, parsed.port)
+            self.proxy = {'server': proxy_url}
+            if parsed.username:
+                self.proxy['username'] = parsed.username
+            if parsed.password:
+                self.proxy['password'] = parsed.password
 
     def run(self,
             url,
@@ -356,7 +365,7 @@ class base_html_playwright(Fetcher):
                 print(str(e))
                 context.close()
                 browser.close()
-                raise PageUnloadable(url=url, status_code=None)
+                raise PageUnloadable(url=url, status_code=None, message=e.message)
 
             if response is None:
                 context.close()

changedetectionio/fetch_site_status.py

@@ -13,6 +13,8 @@ urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 # Some common stuff here that can be moved to a base class
 # (set_proxy_from_list)
 class perform_site_check():
+    screenshot = None
+    xpath_data = None
 
     def __init__(self, *args, datastore, **kwargs):
         super().__init__(*args, **kwargs)
@@ -127,6 +129,9 @@ class perform_site_check():
         fetcher.run(url, timeout, request_headers, request_body, request_method, ignore_status_codes, watch['css_filter'])
         fetcher.quit()
 
+        self.screenshot = fetcher.screenshot
+        self.xpath_data = fetcher.xpath_data
+
         # Fetching complete, now filters
         # @todo move to class / maybe inside of fetcher abstract base?
 
@@ -312,4 +317,4 @@ class perform_site_check():
         if not watch.get('previous_md5'):
             watch['previous_md5'] = fetched_md5
 
-        return changed_detected, update_obj, text_content_before_ignored_filter, fetcher.screenshot, fetcher.xpath_data
+        return changed_detected, update_obj, text_content_before_ignored_filter

changedetectionio/run_all_tests.sh

@@ -38,13 +38,14 @@ docker kill $$-test_selenium
 
 echo "TESTING WEBDRIVER FETCH > PLAYWRIGHT/BROWSERLESS..."
 # Not all platforms support playwright (not ARM/rPI), so it's not packaged in requirements.txt
-pip3 install playwright~=1.22
+pip3 install playwright~=1.24
 docker run -d --name $$-test_browserless -e "DEFAULT_LAUNCH_ARGS=[\"--window-size=1920,1080\"]" --rm  -p 3000:3000  --shm-size="2g"  browserless/chrome:1.53-chrome-stable
 # takes a while to spin up
 sleep 5
 export PLAYWRIGHT_DRIVER_URL=ws://127.0.0.1:3000
 pytest tests/fetchers/test_content.py
 pytest tests/test_errorhandling.py
+pytest tests/visualselector/test_fetch_data.py
 
 unset PLAYWRIGHT_DRIVER_URL
 docker kill $$-test_browserless

changedetectionio/store.py

@@ -363,9 +363,9 @@ class ChangeDetectionStore:
     def save_xpath_data(self, watch_uuid, data, as_error=False):
 
         if as_error:
-            target_path = os.path.join(self.datastore_path, watch_uuid, "elements.json")
-        else:
             target_path = os.path.join(self.datastore_path, watch_uuid, "elements-error.json")
+        else:
+            target_path = os.path.join(self.datastore_path, watch_uuid, "elements.json")
 
         with open(target_path, 'w') as f:
             f.write(json.dumps(data))

changedetectionio/tests/fetchers/test_content.py

@@ -2,7 +2,7 @@
 
 import time
 from flask import url_for
-from ..util import live_server_setup
+from ..util import live_server_setup, wait_for_all_checks
 import logging
 
 
@@ -29,14 +29,8 @@ def test_fetch_webdriver_content(client, live_server):
 
     assert b"1 Imported" in res.data
     time.sleep(3)
-    attempt = 0
-    while attempt < 20:
-        res = client.get(url_for("index"))
-        if not b'Checking now' in res.data:
-            break
-        logging.getLogger().info("Waiting for check to not say 'Checking now'..")
-        time.sleep(3)
-        attempt += 1
+
+    wait_for_all_checks(client)
 
 
     res = client.get(

changedetectionio/tests/util.py

@@ -2,6 +2,8 @@
 
 from flask import make_response, request
 from flask import url_for
+import logging
+import time
 
 def set_original_response():
     test_return_data = """<html>
@@ -68,6 +70,31 @@ def extract_api_key_from_UI(client):
     api_key = m.group(1)
     return api_key.strip()
 
+
+# kinda funky, but works for now
+def extract_UUID_from_client(client):
+    import re
+    res = client.get(
+        url_for("index"),
+    )
+    # <span id="api-key">{{api_key}}</span>
+
+    m = re.search('edit/(.+?)"', str(res.data))
+    uuid = m.group(1)
+    return uuid.strip()
+
+def wait_for_all_checks(client):
+    # Loop waiting until done..
+    attempt=0
+    while attempt < 60:
+        time.sleep(1)
+        res = client.get(url_for("index"))
+        if not b'Checking now' in res.data:
+            break
+        logging.getLogger().info("Waiting for watch-list to not say 'Checking now'.. {}".format(attempt))
+
+        attempt += 1
+
 def live_server_setup(live_server):
 
     @live_server.app.route('/test-endpoint')
@@ -133,3 +160,4 @@ def live_server_setup(live_server):
         return ret
 
     live_server.start()
+

changedetectionio/tests/visualselector/__init__.py

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

changedetectionio/tests/visualselector/conftest.py

@@ -0,0 +1,3 @@
+#!/usr/bin/python3
+
+from .. import conftest

changedetectionio/tests/visualselector/test_fetch_data.py

@@ -0,0 +1,35 @@
+#!/usr/bin/python3
+
+import time
+from flask import url_for
+from ..util import live_server_setup, wait_for_all_checks, extract_UUID_from_client
+
+# Add a site in paused mode, add an invalid filter, we should still have visual selector data ready
+def test_visual_selector_content_ready(client, live_server):
+    import os
+
+    assert os.getenv('PLAYWRIGHT_DRIVER_URL'), "Needs PLAYWRIGHT_DRIVER_URL set for this test"
+    live_server_setup(live_server)
+    time.sleep(1)
+
+    # Add our URL to the import page, maybe better to use something we control?
+    # We use an external URL because the docker container is too difficult to setup to connect back to the pytest socket
+    test_url = 'https://news.ycombinator.com'
+    res = client.post(
+        url_for("form_quick_watch_add"),
+        data={"url": test_url, "tag": '', 'edit_and_watch_submit_button': 'Edit > Watch'},
+        follow_redirects=True
+    )
+    assert b"Watch added in Paused state, saving will unpause" in res.data
+
+    res = client.post(
+        url_for("edit_page", uuid="first", unpause_on_save=1),
+        data={"css_filter": ".does-not-exist", "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_webdriver"},
+        follow_redirects=True
+    )
+    assert b"unpaused" in res.data
+    time.sleep(1)
+    wait_for_all_checks(client)
+    uuid = extract_UUID_from_client(client)
+    assert os.path.isfile(os.path.join('test-datastore', uuid, 'last-screenshot.png')), "last-screenshot.png should exist"
+    assert os.path.isfile(os.path.join('test-datastore', uuid, 'elements.json')), "xpath elements.json data should exist"

changedetectionio/update_worker.py

@@ -142,7 +142,7 @@ class update_worker(threading.Thread):
                     now = time.time()
 
                     try:
-                        changed_detected, update_obj, contents, screenshot, xpath_data = update_handler.run(uuid)
+                        changed_detected, update_obj, contents = update_handler.run(uuid)
                         # Re #342
                         # In Python 3, all strings are sequences of Unicode characters. There is a bytes type that holds raw bytes.
                         # We then convert/.decode('utf-8') for the notification etc
@@ -223,6 +223,9 @@ class update_worker(threading.Thread):
                                                                            'last_check_status': e.status_code})
                     except content_fetcher.PageUnloadable as e:
                         err_text = "Page request from server didnt respond correctly"
+                        if e.message:
+                            err_text = "{} - {}".format(err_text, e.message)
+
                         if e.screenshot:
                             self.datastore.save_screenshot(watch_uuid=uuid, screenshot=e.screenshot, as_error=True)
 
@@ -234,6 +237,9 @@ class update_worker(threading.Thread):
                         # Other serious error
                         process_changedetection_results = False
                     else:
+                        # Crash protection, the watch entry could have been removed by this point (during a slow chrome fetch etc)
+                        if not self.datastore.data['watching'].get(uuid):
+                            continue
 
                         # Mark that we never had any failures
                         if not self.datastore.data['watching'][uuid].get('ignore_status_codes'):
@@ -241,10 +247,6 @@ class update_worker(threading.Thread):
 
                         self.cleanup_error_artifacts(uuid)
 
-                    # Crash protection, the watch entry could have been removed by this point (during a slow chrome fetch etc)
-                    if not self.datastore.data['watching'].get(uuid):
-                        continue
-
                     # Different exceptions mean that we may or may not want to bump the snapshot, trigger notifications etc
                     if process_changedetection_results:
                         try:
@@ -280,10 +282,10 @@ class update_worker(threading.Thread):
                                                                        'last_checked': round(time.time())})
 
                     # Always save the screenshot if it's available
-                    if screenshot:
-                        self.datastore.save_screenshot(watch_uuid=uuid, screenshot=screenshot)
-                    if xpath_data:
-                        self.datastore.save_xpath_data(watch_uuid=uuid, data=xpath_data)
+                    if update_handler.screenshot:
+                        self.datastore.save_screenshot(watch_uuid=uuid, screenshot=update_handler.screenshot)
+                    if update_handler.xpath_data:
+                        self.datastore.save_xpath_data(watch_uuid=uuid, data=update_handler.xpath_data)
 
 
                 self.current_uuid = None  # Done