locale fix for test

changedetectionio/__init__.py

@@ -2,7 +2,7 @@
 
 # Read more https://github.com/dgtlmoon/changedetection.io/wiki
 
-__version__ = '0.46.01'
+__version__ = '0.46.04'
 
 from changedetectionio.strtobool import strtobool
 from json.decoder import JSONDecodeError

changedetectionio/blueprint/browser_steps/__init__.py

@@ -85,7 +85,8 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         browsersteps_start_session['browserstepper'] = browser_steps.browsersteps_live_ui(
             playwright_browser=browsersteps_start_session['browser'],
             proxy=proxy,
-            start_url=datastore.data['watching'][watch_uuid].get('url')
+            start_url=datastore.data['watching'][watch_uuid].get('url'),
+            headers=datastore.data['watching'][watch_uuid].get('headers')
         )
 
         # For test

changedetectionio/blueprint/tags/templates/edit-tag.html

@@ -58,9 +58,9 @@ xpath://body/div/span[contains(@class, 'example-class')]",
                         {% if '/text()' in  field %}
                           <span class="pure-form-message-inline"><strong>Note!: //text() function does not work where the &lt;element&gt; contains &lt;![CDATA[]]&gt;</strong></span><br>
                         {% endif %}
-                        <span class="pure-form-message-inline">One rule per line, <i>any</i> rules that matches will be used.<br>
-
-                    <ul>
+                        <span class="pure-form-message-inline">One CSS, xPath, JSON Path/JQ selector per line, <i>any</i> rules that matches will be used.<br>
+                    <div data-target="#advanced-help-selectors" class="toggle-show pure-button button-tag button-xsmall">Show advanced help and tips</div>
+                    <ul id="advanced-help-selectors">
                         <li>CSS - Limit text to this CSS rule, only text matching this CSS rule is included.</li>
                         <li>JSON - Limit text to this JSON rule, using either <a href="https://pypi.org/project/jsonpath-ng/" target="new">JSONPath</a> or <a href="https://stedolan.github.io/jq/" target="new">jq</a> (if installed).
                             <ul>

changedetectionio/content_fetchers/base.py

@@ -65,8 +65,8 @@ class Fetcher():
 
     def __init__(self):
         import importlib.resources
-        self.xpath_element_js = importlib.resources.files("changedetectionio.content_fetchers.res").joinpath('xpath_element_scraper.js').read_text()
-        self.instock_data_js = importlib.resources.files("changedetectionio.content_fetchers.res").joinpath('stock-not-in-stock.js').read_text()
+        self.xpath_element_js = importlib.resources.files("changedetectionio.content_fetchers.res").joinpath('xpath_element_scraper.js').read_text(encoding='utf-8')
+        self.instock_data_js = importlib.resources.files("changedetectionio.content_fetchers.res").joinpath('stock-not-in-stock.js').read_text(encoding='utf-8')
 
     @abstractmethod
     def get_error(self):
@@ -81,7 +81,8 @@ class Fetcher():
             request_method,
             ignore_status_codes=False,
             current_include_filters=None,
-            is_binary=False):
+            is_binary=False,
+            empty_pages_are_a_change=False):
         # Should set self.error, self.status_code and self.content
         pass
 

changedetectionio/content_fetchers/playwright.py

@@ -83,7 +83,8 @@ class fetcher(Fetcher):
             request_method,
             ignore_status_codes=False,
             current_include_filters=None,
-            is_binary=False):
+            is_binary=False,
+            empty_pages_are_a_change=False):
 
         from playwright.sync_api import sync_playwright
         import playwright._impl._errors
@@ -130,7 +131,7 @@ class fetcher(Fetcher):
             if response is None:
                 context.close()
                 browser.close()
-                logger.debug("Content Fetcher > Response object was none")
+                logger.debug("Content Fetcher > Response object from the browser communication was none")
                 raise EmptyReply(url=url, status_code=None)
 
             try:
@@ -166,10 +167,10 @@ class fetcher(Fetcher):
 
                 raise Non200ErrorCodeReceived(url=url, status_code=self.status_code, screenshot=screenshot)
 
-            if len(self.page.content().strip()) == 0:
+            if not empty_pages_are_a_change and len(self.page.content().strip()) == 0:
+                logger.debug("Content Fetcher > Content was empty, empty_pages_are_a_change = False")
                 context.close()
                 browser.close()
-                logger.debug("Content Fetcher > Content was empty")
                 raise EmptyReply(url=url, status_code=response.status)
 
             # Run Browser Steps here

changedetectionio/content_fetchers/puppeteer.py

@@ -75,7 +75,8 @@ class fetcher(Fetcher):
                          request_method,
                          ignore_status_codes,
                          current_include_filters,
-                         is_binary
+                         is_binary,
+                         empty_pages_are_a_change
                          ):
 
         from changedetectionio.content_fetchers import visualselector_xpath_selectors
@@ -153,7 +154,7 @@ class fetcher(Fetcher):
         if response is None:
             await self.page.close()
             await browser.close()
-            logger.warning("Content Fetcher > Response object was none")
+            logger.warning("Content Fetcher > Response object was none (as in, the response from the browser was empty, not just the content)")
             raise EmptyReply(url=url, status_code=None)
 
         self.headers = response.headers
@@ -186,10 +187,11 @@ class fetcher(Fetcher):
 
             raise Non200ErrorCodeReceived(url=url, status_code=self.status_code, screenshot=screenshot)
         content = await self.page.content
-        if len(content.strip()) == 0:
+
+        if not empty_pages_are_a_change and len(content.strip()) == 0:
+            logger.error("Content Fetcher > Content was empty (empty_pages_are_a_change is False), closing browsers")
             await self.page.close()
             await browser.close()
-            logger.error("Content Fetcher > Content was empty")
             raise EmptyReply(url=url, status_code=response.status)
 
         # Run Browser Steps here
@@ -247,7 +249,7 @@ class fetcher(Fetcher):
         await self.fetch_page(**kwargs)
 
     def run(self, url, timeout, request_headers, request_body, request_method, ignore_status_codes=False,
-            current_include_filters=None, is_binary=False):
+            current_include_filters=None, is_binary=False, empty_pages_are_a_change=False):
 
         #@todo make update_worker async which could run any of these content_fetchers within memory and time constraints
         max_time = os.getenv('PUPPETEER_MAX_PROCESSING_TIMEOUT_SECONDS', 180)
@@ -262,7 +264,8 @@ class fetcher(Fetcher):
                 request_method=request_method,
                 ignore_status_codes=ignore_status_codes,
                 current_include_filters=current_include_filters,
-                is_binary=is_binary
+                is_binary=is_binary,
+                empty_pages_are_a_change=empty_pages_are_a_change
             ), timeout=max_time))
         except asyncio.TimeoutError:
             raise(BrowserFetchTimedOut(msg=f"Browser connected but was unable to process the page in {max_time} seconds."))

changedetectionio/content_fetchers/requests.py

@@ -1,9 +1,8 @@
+from loguru import logger
+import chardet
 import hashlib
 import os
-
-import chardet
 import requests
-
 from changedetectionio import strtobool
 from changedetectionio.content_fetchers.exceptions import BrowserStepsInUnsupportedFetcher, EmptyReply, Non200ErrorCodeReceived
 from changedetectionio.content_fetchers.base import Fetcher
@@ -26,7 +25,8 @@ class fetcher(Fetcher):
             request_method,
             ignore_status_codes=False,
             current_include_filters=None,
-            is_binary=False):
+            is_binary=False,
+            empty_pages_are_a_change=False):
 
         if self.browser_steps_get_valid_steps():
             raise BrowserStepsInUnsupportedFetcher(url=url)
@@ -53,7 +53,7 @@ class fetcher(Fetcher):
             session.mount('file://', FileAdapter())
 
         r = session.request(method=request_method,
-                            data=request_body,
+                            data=request_body.encode('utf-8') if type(request_body) is str else request_body,
                             url=url,
                             headers=request_headers,
                             timeout=timeout,
@@ -74,7 +74,10 @@ class fetcher(Fetcher):
         self.headers = r.headers
 
         if not r.content or not len(r.content):
-            raise EmptyReply(url=url, status_code=r.status_code)
+            if not empty_pages_are_a_change:
+                raise EmptyReply(url=url, status_code=r.status_code)
+            else:
+                logger.debug(f"URL {url} gave zero byte content reply with Status Code {r.status_code}, but empty_pages_are_a_change = True")
 
         # @todo test this
         # @todo maybe you really want to test zero-byte return pages?

changedetectionio/content_fetchers/res/stock-not-in-stock.js

@@ -75,6 +75,7 @@ function isItemInStock() {
         'vergriffen',
         'vorbestellen',
         'vorbestellung ist bald möglich',
+        'we don\'t currently have any',
         'we couldn\'t find any products that match',
         'we do not currently have an estimate of when this product will be back in stock.',
         'we don\'t know when or if this item will be back in stock.',
@@ -173,7 +174,8 @@ function isItemInStock() {
         const element = elementsToScan[i];
         // outside the 'fold' or some weird text in the heading area
         // .getBoundingClientRect() was causing a crash in chrome 119, can only be run on contentVisibility != hidden
-        if (element.getBoundingClientRect().top + window.scrollY >= vh + 150 || element.getBoundingClientRect().top + window.scrollY <= 100) {
+        // Note: theres also an automated test that places the 'out of stock' text fairly low down
+        if (element.getBoundingClientRect().top + window.scrollY >= vh + 250 || element.getBoundingClientRect().top + window.scrollY <= 100) {
             continue
         }
         elementText = "";
@@ -187,7 +189,7 @@ function isItemInStock() {
             // and these mean its out of stock
             for (const outOfStockText of outOfStockTexts) {
                 if (elementText.includes(outOfStockText)) {
-                    console.log(`Selected 'Out of Stock' - found text "${outOfStockText}" - "${elementText}"`)
+                    console.log(`Selected 'Out of Stock' - found text "${outOfStockText}" - "${elementText}" - offset top ${element.getBoundingClientRect().top}, page height is ${vh}`)
                     return outOfStockText; // item is out of stock
                 }
             }

changedetectionio/content_fetchers/res/xpath_element_scraper.js

@@ -164,6 +164,15 @@ visibleElementsArray.forEach(function (element) {
         }
     }
 
+    let label = "not-interesting" // A placeholder, the actual labels for training are done by hand for now
+
+    let text = element.textContent.trim().slice(0, 30).trim();
+    while (/\n{2,}|\t{2,}/.test(text)) {
+        text = text.replace(/\n{2,}/g, '\n').replace(/\t{2,}/g, '\t')
+    }
+
+    // Try to identify any possible currency amounts "Sale: 4000" or "Sale now 3000 Kc", can help with the training.
+    const hasDigitCurrency = (/\d/.test(text.slice(0, 6)) || /\d/.test(text.slice(-6)) ) &&  /([€£$¥₩₹]|USD|AUD|EUR|Kč|kr|SEK|,–)/.test(text) ;
 
     size_pos.push({
         xpath: xpath_result,
@@ -171,9 +180,16 @@ visibleElementsArray.forEach(function (element) {
         height: Math.round(bbox['height']),
         left: Math.floor(bbox['left']),
         top: Math.floor(bbox['top']) + scroll_y,
+        // tagName used by Browser Steps
         tagName: (element.tagName) ? element.tagName.toLowerCase() : '',
+        // tagtype used by Browser Steps
         tagtype: (element.tagName.toLowerCase() === 'input' && element.type) ? element.type.toLowerCase() : '',
-        isClickable: window.getComputedStyle(element).cursor == "pointer"
+        isClickable: window.getComputedStyle(element).cursor === "pointer",
+        // Used by the keras trainer
+        fontSize: window.getComputedStyle(element).getPropertyValue('font-size'),
+        fontWeight: window.getComputedStyle(element).getPropertyValue('font-weight'),
+        hasDigitCurrency: hasDigitCurrency,
+        label: label,
     });
 
 });

changedetectionio/content_fetchers/webdriver_selenium.py

@@ -56,7 +56,8 @@ class fetcher(Fetcher):
             request_method,
             ignore_status_codes=False,
             current_include_filters=None,
-            is_binary=False):
+            is_binary=False,
+            empty_pages_are_a_change=False):
 
         from selenium import webdriver
         from selenium.webdriver.chrome.options import Options as ChromeOptions

changedetectionio/flask_app.py

@@ -1377,17 +1377,19 @@ def changedetection_app(config=None, datastore_o=None):
         import brotli
 
         watch = datastore.data['watching'].get(uuid)
-        if watch and os.path.isdir(watch.watch_data_dir):
-            latest_filename = list(watch.history.keys())[0]
+        if watch and watch.history.keys() and os.path.isdir(watch.watch_data_dir):
+            latest_filename = list(watch.history.keys())[-1]
             html_fname = os.path.join(watch.watch_data_dir, f"{latest_filename}.html.br")
-            if html_fname.endswith('.br'):
-                # Read and decompress the Brotli file
-                with open(html_fname, 'rb') as f:
+            with open(html_fname, 'rb') as f:
+                if html_fname.endswith('.br'):
+                    # Read and decompress the Brotli file
                     decompressed_data = brotli.decompress(f.read())
+                else:
+                    decompressed_data = f.read()
 
-                buffer = BytesIO(decompressed_data)
+            buffer = BytesIO(decompressed_data)
 
-                return send_file(buffer, as_attachment=True, download_name=f"{latest_filename}.html", mimetype='text/html')
+            return send_file(buffer, as_attachment=True, download_name=f"{latest_filename}.html", mimetype='text/html')
 
 
         # Return a 500 error

changedetectionio/notification.py

@@ -107,7 +107,7 @@ def apprise_custom_api_call_wrapper(body, title, notify_type, *args, **kwargs):
 
     r(results.get('url'),
       auth=auth,
-      data=body,
+      data=body.encode('utf-8') if type(body) is str else body,
       headers=headers,
       params=params
       )

changedetectionio/processors/__init__.py

@@ -26,6 +26,8 @@ class difference_detection_processor():
 
     def call_browser(self):
         from requests.structures import CaseInsensitiveDict
+        from changedetectionio.content_fetchers.exceptions import EmptyReply
+
         # Protect against file:// access
         if re.search(r'^file://', self.watch.get('url', '').strip(), re.IGNORECASE):
             if not strtobool(os.getenv('ALLOW_FILE_URI', 'false')):
@@ -133,8 +135,18 @@ class difference_detection_processor():
         is_binary = self.watch.is_pdf
 
         # And here we go! call the right browser with browser-specific settings
-        self.fetcher.run(url, timeout, request_headers, request_body, request_method, ignore_status_codes, self.watch.get('include_filters'),
-                    is_binary=is_binary)
+        empty_pages_are_a_change = self.datastore.data['settings']['application'].get('empty_pages_are_a_change', False)
+
+        self.fetcher.run(url=url,
+                         timeout=timeout,
+                         request_headers=request_headers,
+                         request_body=request_body,
+                         request_method=request_method,
+                         ignore_status_codes=ignore_status_codes,
+                         current_include_filters=self.watch.get('include_filters'),
+                         is_binary=is_binary,
+                         empty_pages_are_a_change=empty_pages_are_a_change
+                         )
 
         #@todo .quit here could go on close object, so we can run JS if change-detected
         self.fetcher.quit()

changedetectionio/processors/restock_diff/__init__.py

@@ -1,11 +1,12 @@
 
-from changedetectionio.model.Watch import model as BaseWatch
-import re
 from babel.numbers import parse_decimal
+from changedetectionio.model.Watch import model as BaseWatch
+from typing import Union
+import re
 
 class Restock(dict):
 
-    def parse_currency(self, raw_value: str) -> float:
+    def parse_currency(self, raw_value: str) -> Union[float, None]:
         # Clean and standardize the value (ie 1,400.00 should be 1400.00), even better would be store the whole thing as an integer.
         standardized_value = raw_value
 
@@ -21,8 +22,11 @@ class Restock(dict):
         # Remove any non-numeric characters except for the decimal point
         standardized_value = re.sub(r'[^\d.-]', '', standardized_value)
 
-        # Convert to float
-        return float(parse_decimal(standardized_value, locale='en'))
+        if standardized_value:
+            # Convert to float
+            return float(parse_decimal(standardized_value, locale='en'))
+
+        return None
 
     def __init__(self, *args, **kwargs):
         # Define default values

changedetectionio/processors/restock_diff/processor.py

@@ -40,13 +40,16 @@ def get_itemprop_availability(html_content) -> Restock:
     import extruct
     logger.trace(f"Imported extruct module in {time.time() - now:.3f}s")
 
-    value = {}
     now = time.time()
+
     # Extruct is very slow, I'm wondering if some ML is going to be faster (800ms on my i7), 'rdfa' seems to be the heaviest.
-
     syntaxes = ['dublincore', 'json-ld', 'microdata', 'microformat', 'opengraph']
+    try:
+        data = extruct.extract(html_content, syntaxes=syntaxes)
+    except Exception as e:
+        logger.warning(f"Unable to extract data, document parsing with extruct failed with {type(e).__name__} - {str(e)}")
+        return Restock()
 
-    data = extruct.extract(html_content, syntaxes=syntaxes)
     logger.trace(f"Extruct basic extract of all metadata done in {time.time() - now:.3f}s")
 
     # First phase, dead simple scanning of anything that looks useful

changedetectionio/static/js/global-settings.js

@@ -18,9 +18,11 @@ $(document).ready(function () {
 
     });
 
-    $("#notification-token-toggle").click(function (e) {
+    $(".toggle-show").click(function (e) {
         e.preventDefault();
-        $('#notification-tokens-info').toggle();
+        let target = $(this).data('target');
+        $(target).toggle();
     });
+
 });
 

changedetectionio/templates/_common_fields.html

@@ -11,8 +11,11 @@
     class="notification-urls" )
                             }}
                             <div class="pure-form-message-inline">
-                              <ul>
-                                <li>Use <a target=_new href="https://github.com/caronc/apprise">AppRise URLs</a> for notification to just about any service! <i><a target=_new href="https://github.com/dgtlmoon/changedetection.io/wiki/Notification-configuration-notes">Please read the notification services wiki here for important configuration notes</a></i>.</li>
+                                <p>
+                                <strong>Tip:</strong> Use <a target=_new href="https://github.com/caronc/apprise">AppRise Notification URLs</a> for notification to just about any service! <i><a target=_new href="https://github.com/dgtlmoon/changedetection.io/wiki/Notification-configuration-notes">Please read the notification services wiki here for important configuration notes</a></i>.<br>
+</p>
+                                <div data-target="#advanced-help-notifications" class="toggle-show pure-button button-tag button-xsmall">Show advanced help and tips</div>
+                              <ul style="display: none" id="advanced-help-notifications">
                                 <li><code><a target=_new href="https://github.com/caronc/apprise/wiki/Notify_discord">discord://</a></code> (or <code>https://discord.com/api/webhooks...</code>)) only supports a maximum <strong>2,000 characters</strong> of notification text, including the title.</li>
                                 <li><code><a target=_new href="https://github.com/caronc/apprise/wiki/Notify_telegram">tgram://</a></code> bots can't send messages to other bots, so you should specify chat ID of non-bot user.</li>
                                 <li><code><a target=_new href="https://github.com/caronc/apprise/wiki/Notify_telegram">tgram://</a></code> only supports very limited HTML and can fail when extra tags are sent, <a href="https://core.telegram.org/bots/api#html-style">read more here</a> (or use plaintext/markdown format)</li>
@@ -40,7 +43,7 @@
 
                             </div>
                             <div class="pure-controls">
-                                <div id="notification-token-toggle" class="pure-button button-tag button-xsmall">Show token/placeholders</div>
+                                <div data-target="#notification-tokens-info" class="toggle-show pure-button button-tag button-xsmall">Show token/placeholders</div>
                             </div>
                             <div class="pure-controls" style="display: none;" id="notification-tokens-info">
                                 <table class="pure-table" id="token-table">

changedetectionio/templates/edit.html

@@ -4,6 +4,7 @@
 {% from '_common_fields.html' import render_common_settings_form %}
 <script src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
 <script src="{{url_for('static_content', group='js', filename='vis.js')}}" defer></script>
+<script src="{{url_for('static_content', group='js', filename='global-settings.js')}}" defer></script>
 <script>
     const browser_steps_available_screenshots=JSON.parse('{{ watch.get_browsersteps_available_screenshots|tojson }}');
     const browser_steps_config=JSON.parse('{{ browser_steps_config|tojson }}');
@@ -275,9 +276,9 @@ xpath://body/div/span[contains(@class, 'example-class')]",
                         {% if '/text()' in  field %}
                           <span class="pure-form-message-inline"><strong>Note!: //text() function does not work where the &lt;element&gt; contains &lt;![CDATA[]]&gt;</strong></span><br>
                         {% endif %}
-                        <span class="pure-form-message-inline">One rule per line, <i>any</i> rules that matches will be used.<br>
-
-                    <ul>
+                        <span class="pure-form-message-inline">One CSS, xPath, JSON Path/JQ selector per line, <i>any</i> rules that matches will be used.<br>
+<p><div data-target="#advanced-help-selectors" class="toggle-show pure-button button-tag button-xsmall">Show advanced help and tips</div><br></p>
+                    <ul id="advanced-help-selectors" style="display: none;">
                         <li>CSS - Limit text to this CSS rule, only text matching this CSS rule is included.</li>
                         <li>JSON - Limit text to this JSON rule, using either <a href="https://pypi.org/project/jsonpath-ng/" target="new">JSONPath</a> or <a href="https://stedolan.github.io/jq/" target="new">jq</a> (if installed).
                             <ul>
@@ -297,9 +298,12 @@ xpath://body/div/span[contains(@class, 'example-class')]",
                                 <li>To use XPath1.0: Prefix with <code>xpath1:</code></li>
                             </ul>
                             </li>
-                    </ul>
-                    Please be sure that you thoroughly understand how to write CSS, JSONPath, XPath{% if jq_support %}, or jq selector{%endif%} rules before filing an issue on GitHub! <a
+                    <li>
+                        Please be sure that you thoroughly understand how to write CSS, JSONPath, XPath{% if jq_support %}, or jq selector{%endif%} rules before filing an issue on GitHub! <a
                                 href="https://github.com/dgtlmoon/changedetection.io/wiki/CSS-Selector-help">here for more CSS selector help</a>.<br>
+                    </li>
+                    </ul>
+
                 </span>
                     </div>
                 <fieldset class="pure-control-group">

changedetectionio/templates/settings.html

@@ -76,7 +76,7 @@
                     </div>
                     <div class="pure-control-group">
                         {{ render_checkbox_field(form.application.form.empty_pages_are_a_change) }}
-                        <span class="pure-form-message-inline">When a page contains HTML, but no renderable text appears (empty page), is this considered a change?</span>
+                        <span class="pure-form-message-inline">When a request returns no content, or the HTML does not contain any text, is this considered a change?</span>
                     </div>
                 {% if form.requests.proxy %}
                     <div class="pure-control-group inline-radio">

changedetectionio/tests/restock/test_restock.py

@@ -2,7 +2,7 @@
 import os
 import time
 from flask import url_for
-from ..util import live_server_setup, wait_for_all_checks, extract_UUID_from_client
+from ..util import live_server_setup, wait_for_all_checks, extract_UUID_from_client, wait_for_notification_endpoint_output
 from changedetectionio.notification import (
     default_notification_body,
     default_notification_format,
@@ -94,7 +94,7 @@ def test_restock_detection(client, live_server, measure_memory_usage):
     assert b'not-in-stock' not in res.data
 
     # We should have a notification
-    time.sleep(2)
+    wait_for_notification_endpoint_output()
     assert os.path.isfile("test-datastore/notification.txt"), "Notification received"
     os.unlink("test-datastore/notification.txt")
 
@@ -103,6 +103,7 @@ def test_restock_detection(client, live_server, measure_memory_usage):
     set_original_response()
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
     wait_for_all_checks(client)
+    time.sleep(5)
     assert not os.path.isfile("test-datastore/notification.txt"), "No notification should have fired when it went OUT OF STOCK by default"
 
     # BUT we should see that it correctly shows "not in stock"

changedetectionio/tests/test_add_replace_remove_filter.py

@@ -2,7 +2,7 @@
 import os.path
 import time
 from flask import url_for
-from .util import live_server_setup, wait_for_all_checks
+from .util import live_server_setup, wait_for_all_checks, wait_for_notification_endpoint_output
 from changedetectionio import html_tools
 
 
@@ -112,7 +112,7 @@ def test_check_add_line_contains_trigger(client, live_server, measure_memory_usa
     res = client.post(
         url_for("settings_page"),
         data={"application-notification_title": "New ChangeDetection.io Notification - {{ watch_url }}",
-              "application-notification_body": 'triggered text was -{{triggered_text}}-',
+              "application-notification_body": 'triggered text was -{{triggered_text}}- 网站监测 内容更新了',
               # https://github.com/caronc/apprise/wiki/Notify_Custom_JSON#get-parameter-manipulation
               "application-notification_urls": test_notification_url,
               "application-minutes_between_check": 180,
@@ -165,11 +165,12 @@ def test_check_add_line_contains_trigger(client, live_server, measure_memory_usa
     assert b'unviewed' in res.data
 
     # Takes a moment for apprise to fire
-    time.sleep(3)
+    wait_for_notification_endpoint_output()
     assert os.path.isfile("test-datastore/notification.txt"), "Notification fired because I can see the output file"
-    with open("test-datastore/notification.txt", 'r') as f:
-        response= f.read()
-        assert '-Oh yes please-' in response
+    with open("test-datastore/notification.txt", 'rb') as f:
+        response = f.read()
+        assert b'-Oh yes please-' in response
+        assert '网站监测 内容更新了'.encode('utf-8') in response
 
 
     res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)

changedetectionio/tests/test_backend.py

@@ -69,6 +69,12 @@ def test_check_basic_change_detection_functionality(client, live_server, measure
 
     wait_for_all_checks(client)
 
+    uuid = extract_UUID_from_client(client)
+
+    # Check the 'get latest snapshot works'
+    res = client.get(url_for("watch_get_latest_html", uuid=uuid))
+    assert b'which has this one new line' in res.data
+
     # Now something should be ready, indicated by having a 'unviewed' class
     res = client.get(url_for("index"))
     assert b'unviewed' in res.data
@@ -86,7 +92,7 @@ def test_check_basic_change_detection_functionality(client, live_server, measure
     assert expected_url.encode('utf-8') in res.data
 
     # Following the 'diff' link, it should no longer display as 'unviewed' even after we recheck it a few times
-    res = client.get(url_for("diff_history_page", uuid="first"))
+    res = client.get(url_for("diff_history_page", uuid=uuid))
     assert b'selected=""' in res.data, "Confirm diff history page loaded"
 
     # Check the [preview] pulls the right one
@@ -143,18 +149,12 @@ def test_check_basic_change_detection_functionality(client, live_server, measure
     assert b'unviewed' not in res.data
 
     # #2458 "clear history" should make the Watch object update its status correctly when the first snapshot lands again
-    uuid = extract_UUID_from_client(client)
     client.get(url_for("clear_watch_history", uuid=uuid))
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
     wait_for_all_checks(client)
     res = client.get(url_for("index"))
     assert b'preview/' in res.data
 
-
-    # Check the 'get latest snapshot works'
-    res = client.get(url_for("watch_get_latest_html", uuid=uuid))
-    assert b'<head><title>head title</title></head>' in res.data
-
     #
     # Cleanup everything
     res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)

changedetectionio/tests/test_filter_exist_changes.py

@@ -4,7 +4,7 @@
 import os
 import time
 from flask import url_for
-from .util import set_original_response, live_server_setup
+from .util import set_original_response, live_server_setup, wait_for_notification_endpoint_output
 from changedetectionio.model import App
 
 
@@ -102,14 +102,15 @@ def test_filter_doesnt_exist_then_exists_should_get_notification(client, live_se
         follow_redirects=True
     )
     assert b"Updated watch." in res.data
-    time.sleep(3)
+    wait_for_notification_endpoint_output()
 
     # Shouldn't exist, shouldn't have fired
     assert not os.path.isfile("test-datastore/notification.txt")
     # Now the filter should exist
     set_response_with_filter()
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
-    time.sleep(3)
+
+    wait_for_notification_endpoint_output()
 
     assert os.path.isfile("test-datastore/notification.txt")
 

changedetectionio/tests/test_filter_failure_notification.py

@@ -1,7 +1,8 @@
 import os
 import time
 from flask import url_for
-from .util import set_original_response, live_server_setup, extract_UUID_from_client, wait_for_all_checks
+from .util import set_original_response, live_server_setup, extract_UUID_from_client, wait_for_all_checks, \
+    wait_for_notification_endpoint_output
 from changedetectionio.model import App
 
 
@@ -107,7 +108,8 @@ def run_filter_test(client, live_server, content_filter):
     # One more check should trigger the _FILTER_FAILURE_THRESHOLD_ATTEMPTS_DEFAULT threshold
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
     wait_for_all_checks(client)
-    time.sleep(2)  # delay for apprise to fire
+
+    wait_for_notification_endpoint_output()
     # Now it should exist and contain our "filter not found" alert
     assert os.path.isfile("test-datastore/notification.txt")
 
@@ -127,6 +129,7 @@ def run_filter_test(client, live_server, content_filter):
         client.get(url_for("form_watch_checknow"), follow_redirects=True)
         wait_for_all_checks(client)
 
+    wait_for_notification_endpoint_output()
     # It should have sent a notification, but..
     assert os.path.isfile("test-datastore/notification.txt")
     # but it should not contain the info about a failed filter (because there was none in this case)

changedetectionio/tests/test_nonrenderable_pages.py

@@ -1,11 +1,8 @@
 #!/usr/bin/env 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
-
-sleep_time_for_fetch_thread = 3
+from .util import set_original_response, set_modified_response, live_server_setup, wait_for_all_checks
+import time
 
 
 def set_nonrenderable_response():
@@ -16,12 +13,18 @@ def set_nonrenderable_response():
      </body>
      </html>
     """
-
     with open("test-datastore/endpoint-content.txt", "w") as f:
         f.write(test_return_data)
+    time.sleep(1)
 
     return None
 
+def set_zero_byte_response():
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write("")
+    time.sleep(1)
+    return None
+
 def test_check_basic_change_detection_functionality(client, live_server, measure_memory_usage):
     set_original_response()
     live_server_setup(live_server)
@@ -35,18 +38,11 @@ def test_check_basic_change_detection_functionality(client, live_server, measure
 
     assert b"1 Imported" in res.data
 
-    time.sleep(sleep_time_for_fetch_thread)
+    wait_for_all_checks(client)
 
-    # 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
-        time.sleep(sleep_time_for_fetch_thread)
-
-        # It should report nothing found (no new 'unviewed' class)
-        res = client.get(url_for("index"))
-        assert b'unviewed' not in res.data
+    # It should report nothing found (no new 'unviewed' class)
+    res = client.get(url_for("index"))
+    assert b'unviewed' not in res.data
 
 
     #####################
@@ -64,7 +60,7 @@ def test_check_basic_change_detection_functionality(client, live_server, measure
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
     # Give the thread time to pick it up
-    time.sleep(sleep_time_for_fetch_thread)
+    wait_for_all_checks(client)
 
     # It should report nothing found (no new 'unviewed' class)
     res = client.get(url_for("index"))
@@ -86,14 +82,20 @@ def test_check_basic_change_detection_functionality(client, live_server, measure
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
     # Give the thread time to pick it up
-    time.sleep(sleep_time_for_fetch_thread)
+    wait_for_all_checks(client)
 
     # It should report nothing found (no new 'unviewed' class)
     res = client.get(url_for("index"))
     assert b'unviewed' in res.data
+    client.get(url_for("mark_all_viewed"), follow_redirects=True)
 
-
-
+    # A totally zero byte (#2528) response should also not trigger an error
+    set_zero_byte_response()
+    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 # A change should have registered because empty_pages_are_a_change is ON
+    assert b'fetch-error' not in res.data
 
     #
     # Cleanup everything

changedetectionio/tests/test_notification.py

@@ -291,11 +291,11 @@ def test_notification_custom_endpoint_and_jinja2(client, live_server, measure_me
         data={
               "application-fetch_backend": "html_requests",
               "application-minutes_between_check": 180,
-              "application-notification_body": '{ "url" : "{{ watch_url }}", "secret": 444 }',
+              "application-notification_body": '{ "url" : "{{ watch_url }}", "secret": 444, "somebug": "网站监测 内容更新了" }',
               "application-notification_format": default_notification_format,
               "application-notification_urls": test_notification_url,
               # https://github.com/caronc/apprise/wiki/Notify_Custom_JSON#get-parameter-manipulation
-              "application-notification_title": "New ChangeDetection.io Notification - {{ watch_url }}",
+              "application-notification_title": "New ChangeDetection.io Notification - {{ watch_url }} ",
               },
         follow_redirects=True
     )
@@ -324,6 +324,7 @@ def test_notification_custom_endpoint_and_jinja2(client, live_server, measure_me
         j = json.loads(x)
         assert j['url'].startswith('http://localhost')
         assert j['secret'] == 444
+        assert j['somebug'] == '网站监测 内容更新了'
 
     # URL check, this will always be converted to lowercase
     assert os.path.isfile("test-datastore/notification-url.txt")
@@ -354,9 +355,10 @@ def test_notification_custom_endpoint_and_jinja2(client, live_server, measure_me
 #2510
 def test_global_send_test_notification(client, live_server, measure_memory_usage):
 
-
     #live_server_setup(live_server)
     set_original_response()
+    if os.path.isfile("test-datastore/notification.txt"):
+        os.unlink("test-datastore/notification.txt")
 
     # otherwise other settings would have already existed from previous tests in this file
     res = client.post(
@@ -364,7 +366,8 @@ def test_global_send_test_notification(client, live_server, measure_memory_usage
         data={
             "application-fetch_backend": "html_requests",
             "application-minutes_between_check": 180,
-            "application-notification_body": 'change detection is cool',
+            #1995 UTF-8 content should be encoded
+            "application-notification_body": 'change detection is cool 网站监测 内容更新了',
             "application-notification_format": default_notification_format,
             "application-notification_urls": "",
             "application-notification_title": "New ChangeDetection.io Notification - {{ watch_url }}",
@@ -399,8 +402,7 @@ def test_global_send_test_notification(client, live_server, measure_memory_usage
 
     with open("test-datastore/notification.txt", 'r') as f:
         x = f.read()
-        assert 'change detection is coo' in x
-
+        assert 'change detection is cool 网站监测 内容更新了' in x
 
     os.unlink("test-datastore/notification.txt")
 
@@ -420,7 +422,7 @@ def test_global_send_test_notification(client, live_server, measure_memory_usage
     with open("test-datastore/notification.txt", 'r') as f:
         x = f.read()
         # Should come from notification.py default handler when there is no notification body to pull from
-        assert 'change detection is coo' in x
+        assert 'change detection is cool 网站监测 内容更新了' in x
 
     client.get(
         url_for("form_delete", uuid="all"),

changedetectionio/tests/test_restock_itemprop.py

@@ -3,7 +3,7 @@ import os
 import time
 
 from flask import url_for
-from .util import live_server_setup, wait_for_all_checks, extract_UUID_from_client
+from .util import live_server_setup, wait_for_all_checks, extract_UUID_from_client, wait_for_notification_endpoint_output
 from ..notification import default_notification_format
 
 instock_props = [
@@ -182,7 +182,8 @@ def _run_test_minmax_limit(client, extra_watch_edit_form):
     # price changed to something LESS than min (900), SHOULD be a change
     set_original_response(props_markup=instock_props[0], price='890.45')
     # let previous runs wait
-    time.sleep(1)
+    time.sleep(2)
+    
     res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
     assert b'1 watches queued for rechecking.' in res.data
     wait_for_all_checks(client)
@@ -197,7 +198,8 @@ def _run_test_minmax_limit(client, extra_watch_edit_form):
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
     wait_for_all_checks(client)
     res = client.get(url_for("index"))
-    assert b'1,890.45' or b'1890.45' in res.data
+    # Depending on the LOCALE it may be either of these (generally for US/default/etc)
+    assert b'1,890.45' in res.data or b'1890.45' in res.data
     assert b'unviewed' in res.data
 
     res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
@@ -362,7 +364,7 @@ def test_change_with_notification_values(client, live_server):
     set_original_response(props_markup=instock_props[0], price='1950.45')
     client.get(url_for("form_watch_checknow"))
     wait_for_all_checks(client)
-    time.sleep(3)
+    wait_for_notification_endpoint_output()
     assert os.path.isfile("test-datastore/notification.txt"), "Notification received"
     with open("test-datastore/notification.txt", 'r') as f:
         notification = f.read()

changedetectionio/tests/util.py

@@ -76,6 +76,17 @@ def set_more_modified_response():
     return None
 
 
+def wait_for_notification_endpoint_output():
+    '''Apprise can take a few seconds to fire'''
+    from os.path import isfile
+    for i in range(1, 20):
+        time.sleep(1)
+        if isfile("test-datastore/notification.txt"):
+            return True
+
+    return False
+
+
 # kinda funky, but works for now
 def extract_api_key_from_UI(client):
     import re

changedetectionio/update_worker.py

@@ -1,6 +1,5 @@
 from .processors.exceptions import ProcessorException
-from . import content_fetchers
-
+import changedetectionio.content_fetchers.exceptions as content_fetchers_exceptions
 from changedetectionio.processors.text_json_diff.processor import FilterNotFoundInResponse
 from changedetectionio import html_tools
 
@@ -301,7 +300,7 @@ class update_worker(threading.Thread):
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': e.message})
                         process_changedetection_results = False
 
-                    except content_fetchers.exceptions.ReplyWithContentButNoText as e:
+                    except content_fetchers_exceptions.ReplyWithContentButNoText as e:
                         # Totally fine, it's by choice - just continue on, nothing more to care about
                         # Page had elements/content but no renderable text
                         # Backend (not filters) gave zero output
@@ -327,7 +326,7 @@ class update_worker(threading.Thread):
                             
                         process_changedetection_results = False
 
-                    except content_fetchers.exceptions.Non200ErrorCodeReceived as e:
+                    except content_fetchers_exceptions.Non200ErrorCodeReceived as e:
                         if e.status_code == 403:
                             err_text = "Error - 403 (Access denied) received"
                         elif e.status_code == 404:
@@ -380,23 +379,23 @@ class update_worker(threading.Thread):
 
                         process_changedetection_results = False
 
-                    except content_fetchers.exceptions.checksumFromPreviousCheckWasTheSame as e:
+                    except content_fetchers_exceptions.checksumFromPreviousCheckWasTheSame as e:
                         # Yes fine, so nothing todo, don't continue to process.
                         process_changedetection_results = False
                         changed_detected = False
-                    except content_fetchers.exceptions.BrowserConnectError as e:
+                    except content_fetchers_exceptions.BrowserConnectError as e:
                         self.datastore.update_watch(uuid=uuid,
                                                     update_obj={'last_error': e.msg
                                                                 }
                                                     )
                         process_changedetection_results = False
-                    except content_fetchers.exceptions.BrowserFetchTimedOut as e:
+                    except content_fetchers_exceptions.BrowserFetchTimedOut as e:
                         self.datastore.update_watch(uuid=uuid,
                                                     update_obj={'last_error': e.msg
                                                                 }
                                                     )
                         process_changedetection_results = False
-                    except content_fetchers.exceptions.BrowserStepsStepException as e:
+                    except content_fetchers_exceptions.BrowserStepsStepException as e:
 
                         if not self.datastore.data['watching'].get(uuid):
                             continue
@@ -438,25 +437,25 @@ class update_worker(threading.Thread):
 
                         process_changedetection_results = False
 
-                    except content_fetchers.exceptions.EmptyReply as e:
+                    except content_fetchers_exceptions.EmptyReply as e:
                         # Some kind of custom to-str handler in the exception handler that does this?
                         err_text = "EmptyReply - try increasing 'Wait seconds before extracting text', Status Code {}".format(e.status_code)
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
                                                                            'last_check_status': e.status_code})
                         process_changedetection_results = False
-                    except content_fetchers.exceptions.ScreenshotUnavailable as e:
+                    except content_fetchers_exceptions.ScreenshotUnavailable as e:
                         err_text = "Screenshot unavailable, page did not render fully in the expected time or page was too long - try increasing 'Wait seconds before extracting text'"
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
                                                                            'last_check_status': e.status_code})
                         process_changedetection_results = False
-                    except content_fetchers.exceptions.JSActionExceptions as e:
+                    except content_fetchers_exceptions.JSActionExceptions as e:
                         err_text = "Error running JS Actions - Page request - "+e.message
                         if e.screenshot:
                             watch.save_screenshot(screenshot=e.screenshot, as_error=True)
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
                                                                            'last_check_status': e.status_code})
                         process_changedetection_results = False
-                    except content_fetchers.exceptions.PageUnloadable as e:
+                    except content_fetchers_exceptions.PageUnloadable as e:
                         err_text = "Page request from server didnt respond correctly"
                         if e.message:
                             err_text = "{} - {}".format(err_text, e.message)
@@ -468,7 +467,7 @@ class update_worker(threading.Thread):
                                                                            'last_check_status': e.status_code,
                                                                            'has_ldjson_price_data': None})
                         process_changedetection_results = False
-                    except content_fetchers.exceptions.BrowserStepsInUnsupportedFetcher as e:
+                    except content_fetchers_exceptions.BrowserStepsInUnsupportedFetcher as e:
                         err_text = "This watch has Browser Steps configured and so it cannot run with the 'Basic fast Plaintext/HTTP Client', either remove the Browser Steps or select a Chrome fetcher."
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text})
                         process_changedetection_results = False

docker-compose.yml

@@ -18,7 +18,7 @@ services:
   #
   #        Log levels are in descending order. (TRACE is the most detailed one)
   #        Log output levels: TRACE, DEBUG(default), INFO, SUCCESS, WARNING, ERROR, CRITICAL
-  #      - LOGGER_LEVEL=DEBUG
+  #      - LOGGER_LEVEL=TRACE
   #
   #       Alternative WebDriver/selenium URL, do not use "'s or 's!
   #      - WEBDRIVER_URL=http://browser-chrome:4444/wd/hub
@@ -29,8 +29,9 @@ services:
   #
   #             https://selenium-python.readthedocs.io/api.html#module-selenium.webdriver.common.proxy
   #
-  #       Alternative Playwright URL, do not use "'s or 's!
-  #      - PLAYWRIGHT_DRIVER_URL=ws://playwright-chrome:3000
+  #       Alternative target "Chrome" Playwright URL, do not use "'s or 's!
+  #       "Playwright" is a driver/librarythat allows changedetection to talk to a Chrome or similar browser.
+  #      - PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000
   #
   #       Playwright proxy settings playwright_proxy_server, playwright_proxy_bypass, playwright_proxy_username, playwright_proxy_password
   #
@@ -73,10 +74,10 @@ services:
 #              condition: service_started
 
 
-     # Used for fetching pages via Playwright+Chrome where you need Javascript support.
+     # Sockpuppetbrowser is basically chrome wrapped in an API for allowing fast fetching of web-pages.
      # RECOMMENDED FOR FETCHING PAGES WITH CHROME
-#    playwright-chrome:
-#        hostname: playwright-chrome
+#    sockpuppetbrowser:
+#        hostname: sockpuppetbrowser
 #        image: dgtlmoon/sockpuppetbrowser:latest
 #        cap_add:
 #            - SYS_ADMIN

requirements.txt

@@ -35,7 +35,7 @@ dnspython==2.6.1 # related to eventlet fixes
 # jq not available on Windows so must be installed manually
 
 # Notification library
-apprise~=1.8.0
+apprise~=1.8.1
 
 # apprise mqtt https://github.com/dgtlmoon/changedetection.io/issues/315
 # and 2.0.0 https://github.com/dgtlmoon/changedetection.io/issues/2241 not yet compatible
@@ -79,8 +79,9 @@ pyppeteerstealth>=0.0.4
 pytest ~=7.2
 pytest-flask ~=1.2
 
-# Pin jsonschema version to prevent build errors on armv6 while rpds-py wheels aren't available (1708)
-jsonschema==4.17.3
+# Anything 4.0 and up but not 5.0
+jsonschema ~= 4.0
+
 
 loguru