Ability to specify JS before running change-detection (#744)

changedetectionio/content_fetcher.py

@@ -46,6 +46,7 @@ class Fetcher():
     headers = None
 
     fetcher_description = "No description"
+    webdriver_js_execute_code = None
     xpath_element_js = """               
                 // Include the getXpath script directly, easier than fetching
                 !function(e,n){"object"==typeof exports&&"undefined"!=typeof module?module.exports=n():"function"==typeof define&&define.amd?define(n):(e=e||self).getXPath=n()}(this,function(){return function(e){var n=e;if(n&&n.id)return'//*[@id="'+n.id+'"]';for(var o=[];n&&Node.ELEMENT_NODE===n.nodeType;){for(var i=0,r=!1,d=n.previousSibling;d;)d.nodeType!==Node.DOCUMENT_TYPE_NODE&&d.nodeName===n.nodeName&&i++,d=d.previousSibling;for(d=n.nextSibling;d;){if(d.nodeName===n.nodeName){r=!0;break}d=d.nextSibling}o.push((n.prefix?n.prefix+":":"")+n.localName+(i||r?"["+(i+1)+"]":"")),n=n.parentNode}return o.length?"/"+o.reverse().join("/"):""}});
@@ -175,7 +176,6 @@ class Fetcher():
 
     # Will be needed in the future by the VisualSelector, always get this where possible.
     screenshot = False
-    fetcher_description = "No description"
     system_http_proxy = os.getenv('HTTP_PROXY')
     system_https_proxy = os.getenv('HTTPS_PROXY')
 
@@ -319,6 +319,9 @@ class base_html_playwright(Fetcher):
                 with page.expect_navigation():
                     response = page.goto(url, wait_until='load')
 
+                if self.webdriver_js_execute_code is not None:
+                    page.evaluate(self.webdriver_js_execute_code)
+
             except playwright._impl._api_types.TimeoutError as e:
                 context.close()
                 browser.close()
@@ -450,6 +453,12 @@ class base_html_webdriver(Fetcher):
 
         self.driver.set_window_size(1280, 1024)
         self.driver.implicitly_wait(int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)))
+
+        if self.webdriver_js_execute_code is not None:
+            self.driver.execute_script(self.webdriver_js_execute_code)
+            # Selenium doesn't automatically wait for actions as good as Playwright, so wait again
+            self.driver.implicitly_wait(int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)))
+
         self.screenshot = self.driver.get_screenshot_as_png()
 
         # @todo - how to check this? is it possible?

changedetectionio/fetch_site_status.py

@@ -106,6 +106,9 @@ class perform_site_check():
         elif system_webdriver_delay is not None:
             fetcher.render_extract_delay = system_webdriver_delay
 
+        if watch['webdriver_js_execute_code'] is not None and watch['webdriver_js_execute_code'].strip():
+            fetcher.webdriver_js_execute_code = watch['webdriver_js_execute_code']
+
         fetcher.run(url, timeout, request_headers, request_body, request_method, ignore_status_code, watch['css_filter'])
         fetcher.quit()
 

changedetectionio/forms.py

@@ -344,6 +344,8 @@ class watchForm(commonSettingsForm):
     trigger_text = StringListField('Trigger/wait for text', [validators.Optional(), ValidateListRegex()])
     text_should_not_be_present = StringListField('Block change-detection if text matches', [validators.Optional(), ValidateListRegex()])
 
+    webdriver_js_execute_code = TextAreaField('Execute JavaScript before change detection', render_kw={"rows": "5"}, validators=[validators.Optional()])
+
     save_button = SubmitField('Save', render_kw={"class": "pure-button pure-button-primary"})
     save_and_preview_button = SubmitField('Save & Preview', render_kw={"class": "pure-button pure-button-primary"})
     proxy = RadioField('Proxy')

changedetectionio/model/Watch.py

@@ -47,7 +47,8 @@ class model(dict):
             # Requires setting to None on submit if it's the same as the default
             # Should be all None by default, so we use the system default in this case.
             'time_between_check': {'weeks': None, 'days': None, 'hours': None, 'minutes': None, 'seconds': None},
-            'webdriver_delay': None
+            'webdriver_delay': None,
+            'webdriver_js_execute_code': None, # Run before change-detection
         }
     jitter_seconds = 0
     mtable = {'seconds': 1, 'minutes': 60, 'hours': 3600, 'days': 86400, 'weeks': 86400 * 7}

changedetectionio/store.py

@@ -298,7 +298,8 @@ class ChangeDetectionStore:
                           'ignore_text', 'css_filter',
                           'subtractive_selectors', 'trigger_text',
                           'extract_title_as_title', 'extract_text',
-                          'text_should_not_be_present']:
+                          'text_should_not_be_present',
+                          'webdriver_js_execute_code']:
                     if res.get(k):
                         apply_extras[k] = res[k]
 

changedetectionio/templates/edit.html

@@ -88,14 +88,17 @@
                             <strong>If you're having trouble waiting for the page to be fully rendered (text missing etc), try increasing the 'wait' time here.</strong>
                             <br/>
                             This will wait <i>n</i> seconds before extracting the text.
+                            {% if using_global_webdriver_wait %}
+                            <br/><strong>Using the current global default settings</strong>
+                            {% endif %}
                         </div>
-
                     </div>
-                    {% if using_global_webdriver_wait %}
+                    <div class="pure-control-group">
+                        {{ render_field(form.webdriver_js_execute_code) }}
                         <div class="pure-form-message-inline">
-                        <strong>Using the current global default settings</strong>
+                            Run this code before performing change detection, handy for filling in fields and other actions <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Run-JavaScript-before-change-detection">More help and examples here</a>
+                        </div>
                     </div>
-                    {% endif %}
                 </fieldset>
                 <fieldset class="pure-group" id="requests-override-options">
                     {% if not playwright_enabled %}