0.39.22

Dockerfile

@@ -9,6 +9,7 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
     gcc \
     libc-dev \
     libffi-dev \
+    libjpeg-dev \
     libssl-dev \
     libxslt-dev \
     make \
@@ -36,13 +37,14 @@ ARG CRYPTOGRAPHY_DONT_BUILD_RUST=1
 
 # Re #93, #73, excluding rustc (adds another 430Mb~)
 RUN apt-get update && apt-get install -y --no-install-recommends \
-    libssl-dev \
-    libffi-dev \
+    g++ \
     gcc \
     libc-dev \
+    libffi-dev \
+    libjpeg-dev \
+    libssl-dev \
     libxslt-dev \
-    zlib1g-dev \
-    g++
+    zlib1g-dev
 
 # https://stackoverflow.com/questions/58701233/docker-logs-erroneously-appears-empty-until-container-stops
 ENV PYTHONUNBUFFERED=1

README.md

@@ -53,6 +53,7 @@ _Need an actual Chrome runner with Javascript support? We support fetching via W
 - Override Request Headers, Specify `POST` or `GET` and other methods
 - Use the "Visual Selector" to help target specific elements
 - Configurable [proxy per watch](https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration)
+- Send a screenshot with the notification when a change is detected in the web page
 
 We [recommend and use Bright Data](https://brightdata.grsm.io/n0r16zf7eivq) global proxy services, Bright Data will match any first deposit up to $100 using our signup link.
 

changedetectionio/__init__.py

@@ -33,7 +33,7 @@ from flask_wtf import CSRFProtect
 from changedetectionio import html_tools
 from changedetectionio.api import api_v1
 
-__version__ = '0.39.21.1'
+__version__ = '0.39.22'
 
 datastore = None
 
@@ -644,12 +644,18 @@ def changedetection_app(config=None, datastore_o=None):
             except ModuleNotFoundError:
                 jq_support = False
 
+            watch = datastore.data['watching'].get(uuid)
+            system_uses_webdriver = datastore.data['settings']['application']['fetch_backend'] == 'html_webdriver'
+            is_html_webdriver = True if watch.get('fetch_backend') == 'html_webdriver' or (
+                    watch.get('fetch_backend', None) is None and system_uses_webdriver) else False
+
             output = render_template("edit.html",
                                      current_base_url=datastore.data['settings']['application']['base_url'],
                                      emailprefix=os.getenv('NOTIFICATION_MAIL_BUTTON_PREFIX', False),
                                      form=form,
                                      has_default_notification_urls=True if len(datastore.data['settings']['application']['notification_urls']) else False,
                                      has_empty_checktime=using_default_check_time,
+                                     is_html_webdriver=is_html_webdriver,
                                      jq_support=jq_support,
                                      playwright_enabled=os.getenv('PLAYWRIGHT_DRIVER_URL', False),
                                      settings_application=datastore.data['settings']['application'],
@@ -657,7 +663,7 @@ def changedetection_app(config=None, datastore_o=None):
                                      uuid=uuid,
                                      visualselector_data_is_ready=visualselector_data_is_ready,
                                      visualselector_enabled=visualselector_enabled,
-                                     watch=datastore.data['watching'][uuid],
+                                     watch=watch
                                      )
 
         return output

changedetectionio/forms.py

@@ -375,6 +375,7 @@ class watchForm(commonSettingsForm):
         'Send a notification when the filter can no longer be found on the page', default=False)
 
     notification_muted = BooleanField('Notifications Muted / Off', default=False)
+    notification_screenshot = BooleanField('Attach screenshot to notification (where possible)', default=False)
 
     def validate(self, **kwargs):
         if not super().validate():

changedetectionio/model/Watch.py

@@ -38,6 +38,7 @@ class model(dict):
             'notification_format': default_notification_format_for_watch,
             'notification_muted': False,
             'notification_title': None,
+            'notification_screenshot': False, # Include the latest screenshot if available and supported by the apprise URL
             'notification_urls': [],  # List of URLs to add to the notification Queue (Usually AppRise)
             'paused': False,
             'previous_md5': False,
@@ -247,7 +248,28 @@ class model(dict):
         if os.path.isfile(fname):
             return fname
 
-        return False
+        # False is not an option for AppRise, must be type None
+        return None
+
+    def get_screenshot_as_jpeg(self):
+        """Best used in notifications due to its smaller size"""
+        png_fname = os.path.join(self.watch_data_dir, "last-screenshot.png")
+        jpg_fname = os.path.join(self.watch_data_dir, "last-screenshot.jpg")
+
+        if os.path.isfile(jpg_fname):
+            return jpg_fname
+
+        if os.path.isfile(png_fname) and not os.path.isfile(jpg_fname):
+            # Doesnt exist, so create the JPEG from the PNG
+            from PIL import Image
+            im1 = Image.open(png_fname)
+            im1.convert('RGB').save(jpg_fname, quality=int(os.getenv("NOTIFICATION_SCREENSHOT_JPG_QUALITY", 75)))
+            return jpg_fname
+
+
+        # False is not an option for AppRise, must be type None
+        return None
+
 
     def __get_file_ctime(self, filename):
         fname = os.path.join(self.watch_data_dir, filename)

changedetectionio/notification.py

@@ -101,7 +101,10 @@ def process_notification(n_object, datastore):
                 apobj.notify(
                     title=n_title,
                     body=n_body,
-                    body_format=n_format)
+                    body_format=n_format,
+                    # False is not an option for AppRise, must be type None
+                    attach=n_object.get('screenshot', None)
+                )
 
                 apobj.clear()
 

changedetectionio/static/js/diff-render.js

@@ -0,0 +1,112 @@
+var a = document.getElementById('a');
+var b = document.getElementById('b');
+var result = document.getElementById('result');
+
+function changed() {
+    // https://github.com/kpdecker/jsdiff/issues/389
+    // I would love to use `{ignoreWhitespace: true}` here but it breaks the formatting
+    options = {ignoreWhitespace: document.getElementById('ignoreWhitespace').checked};
+
+    var diff = Diff[window.diffType](a.textContent, b.textContent, options);
+    var fragment = document.createDocumentFragment();
+    for (var i = 0; i < diff.length; i++) {
+
+        if (diff[i].added && diff[i + 1] && diff[i + 1].removed) {
+            var swap = diff[i];
+            diff[i] = diff[i + 1];
+            diff[i + 1] = swap;
+        }
+
+        var node;
+        if (diff[i].removed) {
+            node = document.createElement('del');
+            node.classList.add("change");
+            node.appendChild(document.createTextNode(diff[i].value));
+
+        } else if (diff[i].added) {
+            node = document.createElement('ins');
+            node.classList.add("change");
+            node.appendChild(document.createTextNode(diff[i].value));
+        } else {
+            node = document.createTextNode(diff[i].value);
+        }
+        fragment.appendChild(node);
+    }
+
+    result.textContent = '';
+    result.appendChild(fragment);
+
+    // Jump at start
+    inputs.current = 0;
+    next_diff();
+}
+
+window.onload = function () {
+
+
+    /* Convert what is options from UTC time.time() to local browser time */
+    var diffList = document.getElementById("diff-version");
+    if (typeof (diffList) != 'undefined' && diffList != null) {
+        for (var option of diffList.options) {
+            var dateObject = new Date(option.value * 1000);
+            option.label = dateObject.toLocaleString();
+        }
+    }
+
+    /* Set current version date as local time in the browser also */
+    var current_v = document.getElementById("current-v-date");
+    var dateObject = new Date(newest_version_timestamp*1000);
+    current_v.innerHTML = dateObject.toLocaleString();
+    onDiffTypeChange(document.querySelector('#settings [name="diff_type"]:checked'));
+    changed();
+};
+
+a.onpaste = a.onchange =
+    b.onpaste = b.onchange = changed;
+
+if ('oninput' in a) {
+    a.oninput = b.oninput = changed;
+} else {
+    a.onkeyup = b.onkeyup = changed;
+}
+
+function onDiffTypeChange(radio) {
+    window.diffType = radio.value;
+// Not necessary
+//	document.title = "Diff " + radio.value.slice(4);
+}
+
+var radio = document.getElementsByName('diff_type');
+for (var i = 0; i < radio.length; i++) {
+    radio[i].onchange = function (e) {
+        onDiffTypeChange(e.target);
+        changed();
+    }
+}
+
+document.getElementById('ignoreWhitespace').onchange = function (e) {
+    changed();
+}
+
+
+var inputs = document.getElementsByClassName('change');
+inputs.current = 0;
+
+
+function next_diff() {
+
+    var element = inputs[inputs.current];
+    var headerOffset = 80;
+    var elementPosition = element.getBoundingClientRect().top;
+    var offsetPosition = elementPosition - headerOffset + window.scrollY;
+
+    window.scrollTo({
+        top: offsetPosition,
+        behavior: "smooth"
+    });
+
+    inputs.current++;
+    if (inputs.current >= inputs.length) {
+        inputs.current = 0;
+    }
+}

changedetectionio/static/js/visual-selector.js

@@ -13,7 +13,7 @@ $(document).ready(function() {
     // redline highlight context
     var ctx;
 
-    var current_default_xpath;
+    var current_default_xpath=[];
     var x_scale=1;
     var y_scale=1;
     var selector_image;
@@ -57,21 +57,24 @@ $(document).ready(function() {
     bootstrap_visualselector();
 
 
-
     function bootstrap_visualselector() {
-        if ( 1 ) {
+        if (1) {
             // bootstrap it, this will trigger everything else
             $("img#selector-background").bind('load', function () {
                 console.log("Loaded background...");
-               c = document.getElementById("selector-canvas");
+                c = document.getElementById("selector-canvas");
                 // greyed out fill context
-               xctx = c.getContext("2d");
+                xctx = c.getContext("2d");
                 // redline highlight context
-               ctx = c.getContext("2d");
-               current_default_xpath =$("#include_filters").val().split(/\r?\n/g);
-               fetch_data();
-               $('#selector-canvas').off("mousemove mousedown");
-               // screenshot_url defined in the edit.html template
+                ctx = c.getContext("2d");
+                if ($("#include_filters").val().trim().length) {
+                    current_default_xpath = $("#include_filters").val().split(/\r?\n/g);
+                } else {
+                    current_default_xpath = [];
+                }
+                fetch_data();
+                $('#selector-canvas').off("mousemove mousedown");
+                // screenshot_url defined in the edit.html template
             }).attr("src", screenshot_url);
         }
     }

changedetectionio/templates/diff.html

@@ -21,6 +21,9 @@
 
             <label for="diffChars" class="pure-checkbox">
                 <input type="radio" name="diff_type" id="diffChars" value="diffChars"/> Chars</label>
+            <!-- @todo - when mimetype is JSON, select this by default? -->
+            <label for="diffJson" class="pure-checkbox">
+                <input type="radio" name="diff_type" id="diffJson" value="diffJson" /> JSON</label>
 
             {% if versions|length >= 1 %}
             <label for="diff-version">Compare newest (<span id="current-v-date"></span>) with</label>
@@ -37,6 +40,11 @@
     </form>
     <del>Removed text</del>
     <ins>Inserted Text</ins>
+    <span>
+        <!-- https://github.com/kpdecker/jsdiff/issues/389 ? -->
+        <label for="ignoreWhitespace" class="pure-checkbox" id="label-diff-ignorewhitespace">
+            <input type="checkbox" id="ignoreWhitespace" name="ignoreWhitespace"/> Ignore Whitespace</label>
+    </span>
 </div>
 
 <div id="diff-jump">
@@ -102,122 +110,12 @@
      </div>
 </div>
 
-
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='diff.js')}}"></script>
-
-<script defer="">
-
-var a = document.getElementById('a');
-var b = document.getElementById('b');
-var result = document.getElementById('result');
-
-function changed() {
-	var diff = JsDiff[window.diffType](a.textContent, b.textContent);
-	var fragment = document.createDocumentFragment();
-	for (var i=0; i < diff.length; i++) {
-
-		if (diff[i].added && diff[i + 1] && diff[i + 1].removed) {
-			var swap = diff[i];
-			diff[i] = diff[i + 1];
-			diff[i + 1] = swap;
-		}
-
-		var node;
-		if (diff[i].removed) {
-			node = document.createElement('del');
-			node.classList.add("change");
-			node.appendChild(document.createTextNode(diff[i].value));
-
-		} else if (diff[i].added) {
-			node = document.createElement('ins');
-			node.classList.add("change");
-			node.appendChild(document.createTextNode(diff[i].value));
-		} else {
-			node = document.createTextNode(diff[i].value);
-		}
-		fragment.appendChild(node);
-	}
-
-	result.textContent = '';
-	result.appendChild(fragment);
-
-	// Jump at start
-	inputs.current=0;
-    next_diff();
-}
-
-window.onload = function() {
-
-
-    /* Convert what is options from UTC time.time() to local browser time */
-    var diffList=document.getElementById("diff-version");
-    if (typeof(diffList) != 'undefined' && diffList != null) {
-        for (var option of diffList.options) {
-          var dateObject = new Date(option.value*1000);
-          option.label=dateObject.toLocaleString();
-        }
-    }
-
-    /* Set current version date as local time in the browser also */
-    var current_v = document.getElementById("current-v-date");
-    var dateObject = new Date({{ newest_version_timestamp }}*1000);
-    current_v.innerHTML=dateObject.toLocaleString();
-
-
-	onDiffTypeChange(document.querySelector('#settings [name="diff_type"]:checked'));
-	changed();
-
-};
-
-a.onpaste = a.onchange =
-b.onpaste = b.onchange = changed;
-
-if ('oninput' in a) {
-	a.oninput = b.oninput = changed;
-} else {
-	a.onkeyup = b.onkeyup = changed;
-}
-
-function onDiffTypeChange(radio) {
-	window.diffType = radio.value;
-// Not necessary 
-//	document.title = "Diff " + radio.value.slice(4);
-}
-
-var radio = document.getElementsByName('diff_type');
-for (var i = 0; i < radio.length; i++) {
-	radio[i].onchange = function(e) {
-		onDiffTypeChange(e.target);
-		changed();
-	}
-}
-
-
-var inputs = document.getElementsByClassName('change');
-inputs.current=0;
-
-
-function next_diff() {
-
-    var element = inputs[inputs.current];
-    var headerOffset = 80;
-    var elementPosition = element.getBoundingClientRect().top;
-    var offsetPosition = elementPosition - headerOffset +  window.scrollY;
-
-    window.scrollTo({
-         top: offsetPosition,
-         behavior: "smooth"
-    });
-
-    inputs.current++;
-    if(inputs.current >= inputs.length) {
-      inputs.current=0;
-    }
-}
-
-
-
+<script>
+    const newest_version_timestamp = {{newest_version_timestamp}};
 </script>
+<script type="text/javascript" src="{{url_for('static_content', group='js', filename='diff.min.js')}}"></script>
+
+<script type="text/javascript" src="{{url_for('static_content', group='js', filename='diff-render.js')}}"></script>
 
 
 {% endblock %}

changedetectionio/templates/edit.html

@@ -141,6 +141,14 @@ User-Agent: wonderbra 1.0") }}
                     <div  class="pure-control-group inline-radio">
                       {{ render_checkbox_field(form.notification_muted) }}
                     </div>
+                    {% if is_html_webdriver %}
+                    <div class="pure-control-group inline-radio">
+                      {{ render_checkbox_field(form.notification_screenshot) }}
+                        <span class="pure-form-message-inline">
+                            <strong>Use with caution!</strong> This will easily fill up your email storage quota or flood other storages.
+                        </span>
+                    </div>
+                    {% endif %}
                     <div class="field-group" id="notification-field-group">
                         {% if has_default_notification_urls %}
                         <div class="inline-warning">

changedetectionio/tests/test_auth.py

@@ -19,6 +19,7 @@ def test_basic_auth(client, live_server):
         follow_redirects=True
     )
     assert b"1 Imported" in res.data
+    time.sleep(1)
 
     # Check form validation
     res = client.post(
@@ -28,8 +29,6 @@ def test_basic_auth(client, live_server):
     )
     assert b"Updated watch." in res.data
 
-    # Trigger a check
-    client.get(url_for("form_watch_checknow"), follow_redirects=True)
     time.sleep(1)
     res = client.get(
         url_for("preview_page", uuid="first"),

changedetectionio/tests/test_css_selector.py

@@ -89,9 +89,6 @@ def test_check_markup_include_filters_restriction(client, live_server):
     )
     assert b"1 Imported" in res.data
 
-    # Trigger a check
-    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)
 
@@ -103,16 +100,13 @@ def test_check_markup_include_filters_restriction(client, live_server):
         follow_redirects=True
     )
     assert b"Updated watch." in res.data
-
+    time.sleep(1)
     # Check it saved
     res = client.get(
         url_for("edit_page", uuid="first"),
     )
     assert bytes(include_filters.encode('utf-8')) in res.data
 
-    # Trigger a check
-    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)
     #  Make a change

changedetectionio/tests/test_encoding.py

@@ -70,9 +70,6 @@ def test_check_encoding_detection_missing_content_type_header(client, live_serve
         follow_redirects=True
     )
 
-    # Trigger a check
-    client.get(url_for("form_watch_checknow"), follow_redirects=True)
-
     # Give the thread time to pick it up
     time.sleep(2)
 

changedetectionio/tests/test_notification.py

@@ -1,9 +1,12 @@
+import json
 import os
 import time
 import re
 from flask import url_for
 from . util import set_original_response, set_modified_response, set_more_modified_response, live_server_setup
+from . util import  extract_UUID_from_client
 import logging
+import base64
 
 from changedetectionio.notification import (
     default_notification_body,
@@ -18,7 +21,6 @@ def test_setup(live_server):
 # Hard to just add more live server URLs when one test is already running (I think)
 # So we add our test here (was in a different file)
 def test_check_notification(client, live_server):
-
     set_original_response()
 
     # Give the endpoint time to spin up
@@ -68,6 +70,15 @@ def test_check_notification(client, live_server):
     # Give the thread time to pick up the first version
     time.sleep(3)
 
+    # We write the PNG to disk, but a JPEG should appear in the notification
+    testimage_png = 'iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAQAAAC1HAwCAAAAC0lEQVR42mNkYAAAAAYAAjCB0C8AAAAASUVORK5CYII='
+    # Write the last screenshot png
+
+    uuid = extract_UUID_from_client(client)
+    datastore = 'test-datastore'
+    with open(os.path.join(datastore, str(uuid), 'last-screenshot.png'), 'wb') as f:
+        f.write(base64.b64decode(testimage_png))
+
     # Goto the edit page, add our ignore text
     # Add our URL to the import page
 
@@ -86,6 +97,7 @@ def test_check_notification(client, live_server):
                                                    "Diff: {diff}\n"
                                                    "Diff Full: {diff_full}\n"
                                                    ":-)",
+                              "notification_screenshot": True,
                               "notification_format": "Text"}
 
     notification_form_data.update({
@@ -143,6 +155,19 @@ def test_check_notification(client, live_server):
     assert ":-)" in notification_submission
     assert "New ChangeDetection.io Notification - {}".format(test_url) in notification_submission
 
+    # Check the attachment was added, and that it is a JPEG from the original PNG
+    notification_submission_object = json.loads(notification_submission)
+    assert notification_submission_object['attachments'][0]['filename'] == 'last-screenshot.jpg'
+    assert len(notification_submission_object['attachments'][0]['base64'])
+    assert notification_submission_object['attachments'][0]['mimetype'] == 'image/jpeg'
+    jpeg_in_attachment = base64.b64decode(notification_submission_object['attachments'][0]['base64'])
+    assert b'JFIF' in jpeg_in_attachment
+    assert testimage_png not in notification_submission
+    # Assert that the JPEG is readable (didn't get chewed up somewhere)
+    from PIL import Image
+    import io
+    assert Image.open(io.BytesIO(jpeg_in_attachment))
+
     if env_base_url:
         # Re #65 - did we see our BASE_URl ?
         logging.debug (">>> BASE_URL checking in notification: %s", env_base_url)

changedetectionio/update_worker.py

@@ -74,6 +74,7 @@ class update_worker(threading.Thread):
             n_object.update({
                 'watch_url': watch['url'],
                 'uuid': watch_uuid,
+                'screenshot': watch.get_screenshot_as_jpeg() if watch.get('notification_screenshot') else None,
                 'current_snapshot': snapshot_contents.decode('utf-8'),
                 'diff': diff.render_diff(watch_history[dates[-2]], watch_history[dates[-1]], line_feed_sep=line_feed_sep),
                 'diff_full': diff.render_diff(watch_history[dates[-2]], watch_history[dates[-1]], True, line_feed_sep=line_feed_sep)
@@ -106,7 +107,8 @@ class update_worker(threading.Thread):
         if 'notification_urls' in n_object:
             n_object.update({
                 'watch_url': watch['url'],
-                'uuid': watch_uuid
+                'uuid': watch_uuid,
+                'screenshot': None
             })
             self.notification_q.put(n_object)
             print("Sent filter not found notification for {}".format(watch_uuid))

requirements.txt

@@ -54,5 +54,7 @@ jinja2-time
 # https://github.com/dgtlmoon/changedetection.io/pull/1009
 jq~=1.3 ;python_version >= "3.8" and sys_platform == "linux"
 
+# Any current modern version, required so far for screenshot PNG->JPEG conversion but will be used more in the future
+pillow
 # playwright is installed at Dockerfile build time because it's not available on all platforms