Ability to set default UA for either fetching types

Author: dgtlmoon

changedetectionio/content_fetchers/puppeteer.py

@@ -9,8 +9,6 @@
 from changedetectionio.content_fetchers.base import Fetcher, manage_user_agent
 from changedetectionio.content_fetchers.exceptions import PageUnloadable, Non200ErrorCodeReceived, EmptyReply, BrowserFetchTimedOut, BrowserConnectError
 
-DEFAULT_USER_AGENT = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/121.0.0.0 Safari/537.36"
-
 class fetcher(Fetcher):
     fetcher_description = "Puppeteer/direct {}/Javascript".format(
         os.getenv("PLAYWRIGHT_BROWSER_TYPE", 'chromium').capitalize()
@@ -106,8 +104,9 @@ async def fetch_page(self,
         self.page = (pages := await browser.pages) and len(pages) or await browser.newPage()
 
         # This user agent is similar to what was used when tweaking the evasions in inject_evasions_into_page(..)
-        user_agent = next((value for key, value in request_headers.items() if key.lower().strip() == 'user-agent'), DEFAULT_USER_AGENT)
-        await self.page.setUserAgent(user_agent)
+        user_agent = next((value for key, value in request_headers.items() if key.lower().strip() == 'user-agent'))
+        if user_agent:
+            await self.page.setUserAgent(user_agent)
 
         try:
             from pyppeteerstealth import inject_evasions_into_page

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

@@ -22,6 +22,10 @@ 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': None,
+                        'html_webdriver': None,
+                    }
                 },
                 'application': {
                     # Custom notification content

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/store.py

@@ -554,7 +554,6 @@ def has_extra_headers_file(self):
         return os.path.isfile(filepath)
 
     def get_all_base_headers(self):
-        from .model.App import parse_headers_from_text_file
         headers = {}
         # Global app settings
         headers.update(self.data['settings'].get('headers', {}))

changedetectionio/templates/settings.html

@@ -108,8 +108,6 @@
                         <p>Use the <strong>Basic</strong> method (default) where your watched sites don't need Javascript to render.</p>
                         <p>The <strong>Chrome/Javascript</strong> method requires a network connection to a running WebDriver+Chrome server, set by the ENV var 'WEBDRIVER_URL'. </p>
                     </span>
-                    <br>
-                    Tip: <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support">Connect using Bright Data and Oxylabs Proxies, find out more here.</a>
                 </div>
                 <fieldset class="pure-group" id="webdriver-override-options" data-visible-for="application-fetch_backend=html_webdriver">
                     <div class="pure-form-message-inline">
@@ -121,6 +119,18 @@
                         {{ render_field(form.application.form.webdriver_delay) }}
                     </div>
                 </fieldset>
+                <div class="pure-control-group inline-radio">
+                    {{ render_field(form.requests.form.default_ua) }}
+                    <span class="pure-form-message-inline">
+                        Applied to all requests.<br><br>
+                        Note: Simply changing the User-Agent often does not defeat anti-robot technologies, it's important to consider <a href="">all of the ways that the browser is detected</a>.
+                    </span>
+                </div>
+                <div class="pure-control-group">
+                                        <br>
+                    Tip: <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support">Connect using Bright Data and Oxylabs Proxies, find out more here.</a>
+
+                </div>
             </div>
 
             <div class="tab-pane-inner" id="filters">
@@ -190,7 +200,7 @@ <h4>Chrome Extension</h4>
                         <a id="chrome-extension-link"
                            title="Try our new Chrome Extension!"
                            href="https://chromewebstore.google.com/detail/changedetectionio-website/kefcfmgmlhmankjmnbijimhofdjekbop">
-                            <img src="{{ url_for('static_content', group='images', filename='Google-Chrome-icon.png') }}">
+                            <img src="{{ url_for('static_content', group='images', filename='Google-Chrome-icon.png') }}" alt="Chrome">
                             Chrome Webstore
                         </a>
                     </p>