Merge branch 'master' into python312

changedetectionio/__init__.py

@@ -175,6 +175,7 @@ def hide_referrer(response):
     #         proxy_set_header Host "localhost";
     #         proxy_set_header X-Forwarded-Prefix /app;
 
+
     if os.getenv('USE_X_SETTINGS'):
         logger.info("USE_X_SETTINGS is ENABLED")
         from werkzeug.middleware.proxy_fix import ProxyFix

changedetectionio/content_fetchers/puppeteer.py

@@ -9,7 +9,6 @@
 from changedetectionio.content_fetchers.base import Fetcher, manage_user_agent
 from changedetectionio.content_fetchers.exceptions import PageUnloadable, Non200ErrorCodeReceived, EmptyReply, BrowserFetchTimedOut, BrowserConnectError
 
-
 class fetcher(Fetcher):
     fetcher_description = "Puppeteer/direct {}/Javascript".format(
         os.getenv("PLAYWRIGHT_BROWSER_TYPE", 'chromium').capitalize()
@@ -93,15 +92,39 @@ async def fetch_page(self,
                                                        ignoreHTTPSErrors=True
                                                        )
         except websockets.exceptions.InvalidStatusCode as e:
-            raise BrowserConnectError(msg=f"Error while trying to connect the browser, Code {e.status_code} (check your access)")
+            raise BrowserConnectError(msg=f"Error while trying to connect the browser, Code {e.status_code} (check your access, whitelist IP, password etc)")
         except websockets.exceptions.InvalidURI:
             raise BrowserConnectError(msg=f"Error connecting to the browser, check your browser connection address (should be ws:// or wss://")
         except Exception as e:
             raise BrowserConnectError(msg=f"Error connecting to the browser {str(e)}")
+
+        # Better is to launch chrome with the URL as arg
+        # non-headless - newPage() will launch an extra tab/window, .browser should already contain 1 page/tab
+        # headless - ask a new page
+        self.page = (pages := await browser.pages) and len(pages) or await browser.newPage()
+
+        try:
+            from pyppeteerstealth import inject_evasions_into_page
+        except ImportError:
+            logger.debug("pyppeteerstealth module not available, skipping")
+            pass
         else:
-            self.page = await browser.newPage()
+            # I tried hooking events via self.page.on(Events.Page.DOMContentLoaded, inject_evasions_requiring_obj_to_page)
+            # But I could never get it to fire reliably, so we just inject it straight after
+            await inject_evasions_into_page(self.page)
 
-        await self.page.setUserAgent(manage_user_agent(headers=request_headers, current_ua=await self.page.evaluate('navigator.userAgent')))
+        # This user agent is similar to what was used when tweaking the evasions in inject_evasions_into_page(..)
+        user_agent = None
+        if request_headers:
+            user_agent = next((value for key, value in request_headers.items() if key.lower().strip() == 'user-agent'), None)
+            if user_agent:
+                await self.page.setUserAgent(user_agent)
+                # Remove it so it's not sent again with headers after
+                [request_headers.pop(key) for key in list(request_headers) if key.lower().strip() == 'user-agent'.lower().strip()]
+
+        if not user_agent:
+            # Attempt to strip 'HeadlessChrome' etc
+            await self.page.setUserAgent(manage_user_agent(headers=request_headers, current_ua=await self.page.evaluate('navigator.userAgent')))
 
         await self.page.setBypassCSP(True)
         if request_headers:

changedetectionio/content_fetchers/requests.py

@@ -30,11 +30,6 @@ def run(self,
         if self.browser_steps_get_valid_steps():
             raise BrowserStepsInUnsupportedFetcher(url=url)
 
-        # Make requests use a more modern looking user-agent
-        if not {k.lower(): v for k, v in request_headers.items()}.get('user-agent', None):
-            request_headers['User-Agent'] = os.getenv("DEFAULT_SETTINGS_HEADERS_USERAGENT",
-                                                      'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.66 Safari/537.36')
-
         proxies = {}
 
         # Allows override the proxy on a per-request basis

changedetectionio/flask_app.py

@@ -338,8 +338,11 @@ def rss():
 
         # @todo needs a .itemsWithTag() or something - then we can use that in Jinaj2 and throw this away
         for uuid, watch in datastore.data['watching'].items():
+            # @todo tag notification_muted skip also (improve Watch model)
+            if watch.get('notification_muted'):
+                continue
             if limit_tag and not limit_tag in watch['tags']:
-                    continue
+                continue
             watch['uuid'] = uuid
             sorted_watches.append(watch)
 
@@ -768,7 +771,7 @@ def edit_page(uuid):
                                      jq_support=jq_support,
                                      playwright_enabled=os.getenv('PLAYWRIGHT_DRIVER_URL', False),
                                      settings_application=datastore.data['settings']['application'],
-                                     using_global_webdriver_wait=default['webdriver_delay'] is None,
+                                     using_global_webdriver_wait=not default['webdriver_delay'],
                                      uuid=uuid,
                                      visualselector_enabled=visualselector_enabled,
                                      watch=watch
@@ -1063,6 +1066,8 @@ def preview_page(uuid):
         content = []
         ignored_line_numbers = []
         trigger_line_numbers = []
+        versions = []
+        timestamp = None
 
         # More for testing, possible to return the first/only
         if uuid == 'first':
@@ -1082,57 +1087,53 @@ def preview_page(uuid):
         if (watch.get('fetch_backend') == 'system' and system_uses_webdriver) or watch.get('fetch_backend') == 'html_webdriver' or watch.get('fetch_backend', '').startswith('extra_browser_'):
             is_html_webdriver = True
 
-        # Never requested successfully, but we detected a fetch error
         if datastore.data['watching'][uuid].history_n == 0 and (watch.get_error_text() or watch.get_error_snapshot()):
             flash("Preview unavailable - No fetch/check completed or triggers not reached", "error")
-            output = render_template("preview.html",
-                                     content=content,
-                                     history_n=watch.history_n,
-                                     extra_stylesheets=extra_stylesheets,
-#                                     current_diff_url=watch['url'],
-                                     watch=watch,
-                                     uuid=uuid,
-                                     is_html_webdriver=is_html_webdriver,
-                                     last_error=watch['last_error'],
-                                     last_error_text=watch.get_error_text(),
-                                     last_error_screenshot=watch.get_error_snapshot())
-            return output
+        else:
+            # So prepare the latest preview or not
+            preferred_version = request.args.get('version')
+            versions = list(watch.history.keys())
+            timestamp = versions[-1]
+            if preferred_version and preferred_version in versions:
+                timestamp = preferred_version
 
-        timestamp = list(watch.history.keys())[-1]
-        try:
-            tmp = watch.get_history_snapshot(timestamp).splitlines()
-
-            # Get what needs to be highlighted
-            ignore_rules = watch.get('ignore_text', []) + datastore.data['settings']['application']['global_ignore_text']
-
-            # .readlines will keep the \n, but we will parse it here again, in the future tidy this up
-            ignored_line_numbers = html_tools.strip_ignore_text(content="\n".join(tmp),
-                                                                wordlist=ignore_rules,
-                                                                mode='line numbers'
-                                                                )
-
-            trigger_line_numbers = html_tools.strip_ignore_text(content="\n".join(tmp),
-                                                                wordlist=watch['trigger_text'],
-                                                                mode='line numbers'
-                                                                )
-            # Prepare the classes and lines used in the template
-            i=0
-            for l in tmp:
-                classes=[]
-                i+=1
-                if i in ignored_line_numbers:
-                    classes.append('ignored')
-                if i in trigger_line_numbers:
-                    classes.append('triggered')
-                content.append({'line': l, 'classes': ' '.join(classes)})
+            try:
+                versions = list(watch.history.keys())
+                tmp = watch.get_history_snapshot(timestamp).splitlines()
+
+                # Get what needs to be highlighted
+                ignore_rules = watch.get('ignore_text', []) + datastore.data['settings']['application']['global_ignore_text']
+
+                # .readlines will keep the \n, but we will parse it here again, in the future tidy this up
+                ignored_line_numbers = html_tools.strip_ignore_text(content="\n".join(tmp),
+                                                                    wordlist=ignore_rules,
+                                                                    mode='line numbers'
+                                                                    )
+
+                trigger_line_numbers = html_tools.strip_ignore_text(content="\n".join(tmp),
+                                                                    wordlist=watch['trigger_text'],
+                                                                    mode='line numbers'
+                                                                    )
+                # Prepare the classes and lines used in the template
+                i=0
+                for l in tmp:
+                    classes=[]
+                    i+=1
+                    if i in ignored_line_numbers:
+                        classes.append('ignored')
+                    if i in trigger_line_numbers:
+                        classes.append('triggered')
+                    content.append({'line': l, 'classes': ' '.join(classes)})
 
-        except Exception as e:
-            content.append({'line': f"File doesnt exist or unable to read timestamp {timestamp}", 'classes': ''})
+            except Exception as e:
+                content.append({'line': f"File doesnt exist or unable to read timestamp {timestamp}", 'classes': ''})
 
         output = render_template("preview.html",
                                  content=content,
+                                 current_version=timestamp,
                                  history_n=watch.history_n,
                                  extra_stylesheets=extra_stylesheets,
+                                 extra_title=f" - Diff - {watch.label} @ {timestamp}",
                                  ignored_line_numbers=ignored_line_numbers,
                                  triggered_line_numbers=trigger_line_numbers,
                                  current_diff_url=watch['url'],
@@ -1142,7 +1143,10 @@ def preview_page(uuid):
                                  is_html_webdriver=is_html_webdriver,
                                  last_error=watch['last_error'],
                                  last_error_text=watch.get_error_text(),
-                                 last_error_screenshot=watch.get_error_snapshot())
+                                 last_error_screenshot=watch.get_error_snapshot(),
+                                 versions=versions
+                                )
+
 
         return output
 

changedetectionio/forms.py

@@ -526,6 +526,10 @@ class SingleExtraBrowser(Form):
     browser_connection_url = StringField('Browser connection URL', [validators.Optional()], render_kw={"placeholder": "wss://brightdata... wss://oxylabs etc", "size":50})
     # @todo do the validation here instead
 
+class DefaultUAInputForm(Form):
+    html_requests = StringField('Plaintext requests', validators=[validators.Optional()], render_kw={"placeholder": "<default>"})
+    if os.getenv("PLAYWRIGHT_DRIVER_URL") or os.getenv("WEBDRIVER_URL"):
+        html_webdriver = StringField('Chrome requests', validators=[validators.Optional()], render_kw={"placeholder": "<default>"})
 
 # datastore.data['settings']['requests']..
 class globalSettingsRequestForm(Form):
@@ -537,6 +541,8 @@ class globalSettingsRequestForm(Form):
     extra_proxies = FieldList(FormField(SingleExtraProxy), min_entries=5)
     extra_browsers = FieldList(FormField(SingleExtraBrowser), min_entries=5)
 
+    default_ua = FormField(DefaultUAInputForm, label="Default User-Agent overrides")
+
     def validate_extra_proxies(self, extra_validators=None):
         for e in self.data['extra_proxies']:
             if e.get('proxy_name') or e.get('proxy_url'):

changedetectionio/model/App.py

@@ -6,6 +6,7 @@
 )
 
 _FILTER_FAILURE_THRESHOLD_ATTEMPTS_DEFAULT = 6
+DEFAULT_SETTINGS_HEADERS_USERAGENT='Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.66 Safari/537.36'
 
 class model(dict):
     base_config = {
@@ -22,6 +23,10 @@ class model(dict):
                     'time_between_check': {'weeks': None, 'days': None, 'hours': 3, 'minutes': None, 'seconds': None},
                     'timeout': int(getenv("DEFAULT_SETTINGS_REQUESTS_TIMEOUT", "45")),  # Default 45 seconds
                     'workers': int(getenv("DEFAULT_SETTINGS_REQUESTS_WORKERS", "10")),  # Number of threads, lower is better for slow connections
+                    'default_ua': {
+                        'html_requests': getenv("DEFAULT_SETTINGS_HEADERS_USERAGENT", DEFAULT_SETTINGS_HEADERS_USERAGENT),
+                        'html_webdriver': None,
+                    }
                 },
                 'application': {
                     # Custom notification content

changedetectionio/notification.py

@@ -122,10 +122,6 @@ def process_notification(n_object, datastore):
     # Insert variables into the notification content
     notification_parameters = create_notification_parameters(n_object, datastore)
 
-    # Get the notification body from datastore
-    n_body = jinja_render(template_str=n_object.get('notification_body', ''), **notification_parameters)
-    n_title = jinja_render(template_str=n_object.get('notification_title', ''), **notification_parameters)
-
     n_format = valid_notification_formats.get(
         n_object.get('notification_format', default_notification_format),
         valid_notification_formats[default_notification_format],
@@ -151,6 +147,11 @@ def process_notification(n_object, datastore):
 
     with apprise.LogCapture(level=apprise.logging.DEBUG) as logs:
         for url in n_object['notification_urls']:
+
+            # Get the notification body from datastore
+            n_body = jinja_render(template_str=n_object.get('notification_body', ''), **notification_parameters)
+            n_title = jinja_render(template_str=n_object.get('notification_title', ''), **notification_parameters)
+
             url = url.strip()
             if not url:
                 logger.warning(f"Process Notification: skipping empty notification URL.")

changedetectionio/processors/__init__.py

@@ -97,6 +97,10 @@ def call_browser(self):
         request_headers.update(self.datastore.get_all_base_headers())
         request_headers.update(self.datastore.get_all_headers_in_textfile_for_watch(uuid=self.watch.get('uuid')))
 
+        ua = self.datastore.data['settings']['requests'].get('default_ua')
+        if ua and ua.get(prefer_fetch_backend):
+            request_headers.update({'User-Agent': ua.get(prefer_fetch_backend)})
+
         # https://github.com/psf/requests/issues/4525
         # Requests doesnt yet support brotli encoding, so don't put 'br' here, be totally sure that the user cannot
         # do this by accident.

changedetectionio/static/js/diff-overview.js

@@ -8,6 +8,13 @@ $(document).ready(function () {
         }
     })
 
+    $('.needs-localtime').each(function () {
+        for (var option of this.options) {
+            var dateObject = new Date(option.value * 1000);
+            option.label = dateObject.toLocaleString(undefined, {dateStyle: "full", timeStyle: "medium"});
+        }
+    });
+
     // Load it when the #screenshot tab is in use, so we dont give a slow experience when waiting for the text diff to load
     window.addEventListener('hashchange', function (e) {
         toggle(location.hash);

changedetectionio/static/js/diff-render.js

@@ -79,12 +79,7 @@ $(document).ready(function () {
         $('#jump-next-diff').click();
     }
 
-    $('.needs-localtime').each(function () {
-        for (var option of this.options) {
-            var dateObject = new Date(option.value * 1000);
-            option.label = dateObject.toLocaleString(undefined, {dateStyle: "full", timeStyle: "medium"});
-        }
-    })
+
     onDiffTypeChange(
         document.querySelector('#settings [name="diff_type"]:checked'),
     );

changedetectionio/static/js/preview.js

@@ -0,0 +1,49 @@
+function redirect_to_version(version) {
+    var currentUrl = window.location.href;
+    var baseUrl = currentUrl.split('?')[0]; // Base URL without query parameters
+    var anchor = '';
+
+    // Check if there is an anchor
+    if (baseUrl.indexOf('#') !== -1) {
+        anchor = baseUrl.substring(baseUrl.indexOf('#'));
+        baseUrl = baseUrl.substring(0, baseUrl.indexOf('#'));
+    }
+    window.location.href = baseUrl + '?version=' + version + anchor;
+}
+
+document.addEventListener('keydown', function (event) {
+    var selectElement = document.getElementById('preview-version');
+    if (selectElement) {
+        var selectedOption = selectElement.querySelector('option:checked');
+        if (selectedOption) {
+            if (event.key === 'ArrowLeft') {
+                if (selectedOption.previousElementSibling) {
+                    redirect_to_version(selectedOption.previousElementSibling.value);
+                }
+            } else if (event.key === 'ArrowRight') {
+                if (selectedOption.nextElementSibling) {
+                    redirect_to_version(selectedOption.nextElementSibling.value);
+                }
+            }
+        }
+    }
+});
+
+
+document.getElementById('preview-version').addEventListener('change', function () {
+    redirect_to_version(this.value);
+});
+
+var selectElement = document.getElementById('preview-version');
+if (selectElement) {
+    var selectedOption = selectElement.querySelector('option:checked');
+    if (selectedOption) {
+        if (selectedOption.previousElementSibling) {
+            document.getElementById('btn-previous').href = "?version=" + selectedOption.previousElementSibling.value;
+        }
+        if (selectedOption.nextElementSibling) {
+            document.getElementById('btn-next').href = "?version=" + selectedOption.nextElementSibling.value;
+        }
+
+    }
+}

changedetectionio/static/styles/scss/styles.scss

@@ -243,7 +243,6 @@ body::after {
 body::before {
   // background-image set in base.html so it works with reverse proxies etc
   content: "";
-  background-size: cover
 }
 
 body:after,
@@ -1083,6 +1082,9 @@ ul {
     li {
       list-style: none;
       font-size: 0.8rem;
+      > * {
+        display: inline-block;
+      }
     }
   }
 

changedetectionio/static/styles/styles.css

@@ -574,8 +574,7 @@ body::after {
   opacity: 0.91; }
 
 body::before {
-  content: "";
-  background-size: cover; }
+  content: ""; }
 
 body:after,
 body:before {
@@ -1173,6 +1172,8 @@ ul {
     #quick-watch-processor-type ul li {
       list-style: none;
       font-size: 0.8rem; }
+      #quick-watch-processor-type ul li > * {
+        display: inline-block; }
 
 .restock-label {
   padding: 3px;