Add help text

.github/workflows/test-only.yml

@@ -29,7 +29,7 @@ jobs:
           docker network create changedet-network
 
           # Selenium+browserless
-          docker run --network changedet-network -d --hostname selenium  -p 4444:4444 --rm --shm-size="2g"  selenium/standalone-chrome:4
+          docker run --network changedet-network -d --hostname selenium  -p 4444:4444 --rm --shm-size="2g"  selenium/standalone-chrome:4.14.1
           docker run --network changedet-network -d --hostname browserless -e "FUNCTION_BUILT_INS=[\"fs\",\"crypto\"]" -e "DEFAULT_LAUNCH_ARGS=[\"--window-size=1920,1080\"]" --rm  -p 3000:3000  --shm-size="2g"  browserless/chrome:1.60-chrome-stable
 
       - name: Build changedetection.io container for testing

Dockerfile

@@ -1,5 +1,5 @@
 # pip dependencies install stage
-FROM python:3.11-slim-bookworm as builder
+FROM python:3.11-slim-bullseye as builder
 
 # See `cryptography` pin comment in requirements.txt
 ARG CRYPTOGRAPHY_DONT_BUILD_RUST=1
@@ -34,9 +34,10 @@ RUN pip install --target=/dependencies playwright~=1.27.1 \
     || echo "WARN: Failed to install Playwright. The application can still run, but the Playwright option will be disabled."
 
 # Final image stage
-FROM python:3.11-slim-bookworm
+FROM python:3.11-slim-bullseye
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
+    libssl1.1 \
     libxslt1.1 \
     # For pdftohtml
     poppler-utils \

changedetectionio/__init__.py

@@ -38,7 +38,7 @@ from flask_paginate import Pagination, get_page_parameter
 from changedetectionio import html_tools
 from changedetectionio.api import api_v1
 
-__version__ = '0.45.5'
+__version__ = '0.45.3'
 
 from changedetectionio.store import BASE_URL_NOT_SET_TEXT
 

changedetectionio/content_fetcher.py

@@ -159,16 +159,6 @@ class Fetcher():
         """
         return {k.lower(): v for k, v in self.headers.items()}
 
-    def browser_steps_get_valid_steps(self):
-        if self.browser_steps is not None and len(self.browser_steps):
-            valid_steps = filter(
-                lambda s: (s['operation'] and len(s['operation']) and s['operation'] != 'Choose one' and s['operation'] != 'Goto site'),
-                self.browser_steps)
-
-            return valid_steps
-
-        return None
-
     def iterate_browser_steps(self):
         from changedetectionio.blueprint.browser_steps.browser_steps import steppable_browser_interface
         from playwright._impl._api_types import TimeoutError
@@ -180,7 +170,10 @@ class Fetcher():
         if self.browser_steps is not None and len(self.browser_steps):
             interface = steppable_browser_interface()
             interface.page = self.page
-            valid_steps = self.browser_steps_get_valid_steps()
+
+            valid_steps = filter(
+                lambda s: (s['operation'] and len(s['operation']) and s['operation'] != 'Choose one' and s['operation'] != 'Goto site'),
+                self.browser_steps)
 
             for step in valid_steps:
                 step_n += 1
@@ -333,8 +326,9 @@ class base_html_playwright(Fetcher):
             # Remove username/password if it exists in the URL or you will receive "ERR_NO_SUPPORTED_PROXIES" error
             # Actual authentication handled by Puppeteer/node
             o = urlparse(self.proxy.get('server'))
-            proxy_url = urllib.parse.quote(o._replace(netloc="{}:{}".format(o.hostname, o.port)).geturl())
-            browserless_function_url = f"{browserless_function_url}&--proxy-server={proxy_url}"
+            # Remove scheme, socks5:// doesnt always work and it will autodetect anyway
+            proxy_url = urllib.parse.quote(o._replace(netloc="{}:{}".format(o.hostname, o.port)).geturl().replace(f"{o.scheme}://", '', 1))
+            browserless_function_url = f"{browserless_function_url}&--proxy-server={proxy_url}&dumpio=true"
 
         try:
             amp = '&' if '?' in browserless_function_url else '?'
@@ -478,18 +472,12 @@ class base_html_playwright(Fetcher):
             browsersteps_interface = steppable_browser_interface()
             browsersteps_interface.page = self.page
 
-            response = browsersteps_interface.action_goto_url(value=url)
-            self.headers = response.all_headers()
-
-            if response is None:
-                context.close()
-                browser.close()
-                print("Content Fetcher > Response object was none")
-                raise EmptyReply(url=url, status_code=None)
-
             try:
+                response = browsersteps_interface.action_goto_url(value=url)
+
                 if self.webdriver_js_execute_code is not None and len(self.webdriver_js_execute_code):
                     browsersteps_interface.action_execute_js(value=self.webdriver_js_execute_code, selector=None)
+
             except playwright._impl._api_types.TimeoutError as e:
                 context.close()
                 browser.close()
@@ -501,26 +489,31 @@ class base_html_playwright(Fetcher):
                 browser.close()
                 raise PageUnloadable(url=url, status_code=None, message=str(e))
 
+            if response is None:
+                context.close()
+                browser.close()
+                print("Content Fetcher > Response object was none")
+                raise EmptyReply(url=url, status_code=None)
+
             extra_wait = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay
             self.page.wait_for_timeout(extra_wait * 1000)
 
+            # Run Browser Steps here
+            self.iterate_browser_steps()
 
+            extra_wait = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay
+            self.page.wait_for_timeout(extra_wait * 1000)
+
+            self.content = self.page.content()
             self.status_code = response.status
-
-            if self.status_code != 200 and not ignore_status_codes:
-                raise Non200ErrorCodeReceived(url=url, status_code=self.status_code)
-
             if len(self.page.content().strip()) == 0:
                 context.close()
                 browser.close()
                 print("Content Fetcher > Content was empty")
                 raise EmptyReply(url=url, status_code=response.status)
 
-            # Run Browser Steps here
-            if self.browser_steps_get_valid_steps():
-                self.iterate_browser_steps()
-                
-            self.page.wait_for_timeout(extra_wait * 1000)
+            self.status_code = response.status
+            self.headers = response.all_headers()
 
             # So we can find an element on the page where its selector was entered manually (maybe not xPath etc)
             if current_include_filters is not None:
@@ -532,7 +525,6 @@ class base_html_playwright(Fetcher):
                 "async () => {" + self.xpath_element_js.replace('%ELEMENTS%', visualselector_xpath_selectors) + "}")
             self.instock_data = self.page.evaluate("async () => {" + self.instock_data_js + "}")
 
-            self.content = self.page.content()
             # Bug 3 in Playwright screenshot handling
             # Some bug where it gives the wrong screenshot size, but making a request with the clip set first seems to solve it
             # JPEG is better here because the screenshots can be very very large
@@ -547,7 +539,7 @@ class base_html_playwright(Fetcher):
             except Exception as e:
                 context.close()
                 browser.close()
-                raise ScreenshotUnavailable(url=url, status_code=response.status_code)
+                raise ScreenshotUnavailable(url=url, status_code=None)
 
             context.close()
             browser.close()

changedetectionio/processors/text_json_diff.py

@@ -338,7 +338,8 @@ class perform_site_check(difference_detection_processor):
                 # incase they specified something in '/.../x'
                 if re.search(PERL_STYLE_REGEX, s_re, re.IGNORECASE):
                     regex = html_tools.perl_style_slash_enclosed_regex_to_options(s_re)
-                    result = re.findall(regex.encode('utf-8'), stripped_text_from_html)
+                    # Both the regex (r) and (stripped_text_from_html) should be bytes by now
+                    result = re.findall(rf"{regex}".encode('utf-8'), stripped_text_from_html)
 
                     for l in result:
                         if type(l) is tuple:

changedetectionio/templates/edit.html

@@ -127,7 +127,7 @@
                     <div  class="pure-control-group inline-radio">
                         {{ render_checkbox_field(form.ignore_status_codes) }}
                     </div>
-                <fieldset id="webdriver-override-options">
+                <fieldset id="webdriver-override-options" class="hideable show-html_webdriver">
                     <div class="pure-control-group">
                         {{ render_field(form.webdriver_delay) }}
                         <div class="pure-form-message-inline">
@@ -139,6 +139,8 @@
                             {% endif %}
                         </div>
                     </div>
+                </fieldset>
+                <fieldset class="hideable show-html_webdriver">
                     <div class="pure-control-group">
                         {{ render_field(form.webdriver_js_execute_code) }}
                         <div class="pure-form-message-inline">
@@ -146,13 +148,8 @@
                         </div>
                     </div>
                 </fieldset>
-                <fieldset class="pure-group" id="requests-override-options">
-                    {% if not playwright_enabled %}
-                        <div class="pure-form-message-inline">
-                            <strong>Request override is currently only used by the <i>Basic fast Plaintext/HTTP Client</i> method.</strong>
-                        </div>
-                    {% endif %}
-                    <div class="pure-control-group" id="request-method">
+                <fieldset class="pure-group hideable show-html_requests" id="requests-override-options">
+                    <div class="pure-control-group " id="request-method">
                         {{ render_field(form.method) }}
                     </div>
                     <div class="pure-control-group" id="request-headers">
@@ -384,6 +381,7 @@ Unavailable") }}
                         <li>Extracts text in the final output (line by line) after other filters using regular expressions or string match;
                             <ul>
                                 <li>Regular expression &dash; example <code>/reports.+?2022/i</code></li>
+                                <li>Regular expression to match across lines &dash; example <code>/FromHere.+?ToHere/is</code></li>
                                 <li>Don't forget to consider the white-space at the start of a line <code>/.+?reports.+?2022/i</code></li>
                                 <li>Use <code>//(?aiLmsux))</code> type flags (more <a href="https://docs.python.org/3/library/re.html#index-15">information here</a>)<br></li>
                                 <li>Keyword example &dash; example <code>Out of stock</code></li>
@@ -455,15 +453,15 @@ Unavailable") }}
                         <tbody>
                         <tr>
                             <td>Check count</td>
-                            <td>{{ "{:,}".format( watch.check_count) }}</td>
+                            <td>{{ watch.check_count }}</td>
                         </tr>
                         <tr>
                             <td>Consecutive filter failures</td>
-                            <td>{{ "{:,}".format( watch.consecutive_filter_failures) }}</td>
+                            <td>{{ watch.consecutive_filter_failures }}</td>
                         </tr>
                         <tr>
                             <td>History length</td>
-                            <td>{{ "{:,}".format(watch.history|length) }}</td>
+                            <td>{{ watch.history|length }}</td>
                         </tr>
                         <tr>
                             <td>Last fetch time</td>

changedetectionio/tests/visualselector/test_fetch_data.py

@@ -1,19 +1,18 @@
 #!/usr/bin/python3
 
 import time
-import os
 from flask import url_for
 from ..util import live_server_setup, wait_for_all_checks, extract_UUID_from_client
 
-def test_setup(client, live_server):
-    live_server_setup(live_server)
-
 # Add a site in paused mode, add an invalid filter, we should still have visual selector data ready
 def test_visual_selector_content_ready(client, live_server):
     import os
     import json
 
     assert os.getenv('PLAYWRIGHT_DRIVER_URL'), "Needs PLAYWRIGHT_DRIVER_URL set for this test"
+    time.sleep(1)
+    live_server_setup(live_server)
+
 
     # Add our URL to the import page, because the docker container (playwright/selenium) wont be able to connect to our usual test url
     test_url = "https://changedetection.io/ci-test/test-runjs.html"
@@ -61,75 +60,4 @@ def test_visual_selector_content_ready(client, live_server):
         follow_redirects=True
     )
     assert b'notification_screenshot' in res.data
-    client.get(
-        url_for("form_delete", uuid="all"),
-        follow_redirects=True
-    )
 
-def test_basic_browserstep(client, live_server):
-
-    assert os.getenv('PLAYWRIGHT_DRIVER_URL'), "Needs PLAYWRIGHT_DRIVER_URL set for this test"
-    #live_server_setup(live_server)
-
-    # Add our URL to the import page, because the docker container (playwright/selenium) wont be able to connect to our usual test url
-    test_url = "https://changedetection.io/ci-test/test-runjs.html"
-
-    res = client.post(
-        url_for("form_quick_watch_add"),
-        data={"url": test_url, "tags": '', 'edit_and_watch_submit_button': 'Edit > Watch'},
-        follow_redirects=True
-    )
-    assert b"Watch added in Paused state, saving will unpause" in res.data
-
-    res = client.post(
-        url_for("edit_page", uuid="first", unpause_on_save=1),
-        data={
-              "url": test_url,
-              "tags": "",
-              "headers": "",
-              'fetch_backend': "html_webdriver",
-              'browser_steps-0-operation': 'Goto site',
-              'browser_steps-1-operation': 'Click element',
-              'browser_steps-1-selector': 'button[name=test-button]',
-              'browser_steps-1-optional_value': ''
-        },
-        follow_redirects=True
-    )
-    assert b"unpaused" in res.data
-    wait_for_all_checks(client)
-
-    uuid = extract_UUID_from_client(client)
-
-    # Check HTML conversion detected and workd
-    res = client.get(
-        url_for("preview_page", uuid=uuid),
-        follow_redirects=True
-    )
-    assert b"This text should be removed" not in res.data
-    assert b"I smell JavaScript because the button was pressed" in res.data
-
-    # now test for 404 errors
-    res = client.post(
-        url_for("edit_page", uuid=uuid, unpause_on_save=1),
-        data={
-              "url": "https://changedetection.io/404",
-              "tags": "",
-              "headers": "",
-              'fetch_backend': "html_webdriver",
-              'browser_steps-0-operation': 'Goto site',
-              'browser_steps-1-operation': 'Click element',
-              'browser_steps-1-selector': 'button[name=test-button]',
-              'browser_steps-1-optional_value': ''
-        },
-        follow_redirects=True
-    )
-    assert b"unpaused" in res.data
-    wait_for_all_checks(client)
-
-    res = client.get(url_for("index"))
-    assert b'Error - 404' in res.data
-
-    client.get(
-        url_for("form_delete", uuid="all"),
-        follow_redirects=True
-    )

docker-compose.yml

@@ -68,7 +68,7 @@ services:
 
 #    browser-chrome:
 #        hostname: browser-chrome
-#        image: selenium/standalone-chrome:4
+#        image: selenium/standalone-chrome-debug:3.141.59
 #        environment:
 #            - VNC_NO_PASSWORD=1
 #            - SCREEN_WIDTH=1920