some small extra checks

.github/workflows/test-only.yml

@@ -29,8 +29,8 @@ 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-debug:3.141.59
-          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:1.53-chrome-stable
+          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 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
         run: |         

Dockerfile

@@ -1,5 +1,5 @@
 # pip dependencies install stage
-FROM python:3.11-slim-bullseye as builder
+FROM python:3.11-slim-bookworm as builder
 
 # See `cryptography` pin comment in requirements.txt
 ARG CRYPTOGRAPHY_DONT_BUILD_RUST=1
@@ -20,19 +20,23 @@ WORKDIR /install
 
 COPY requirements.txt /requirements.txt
 
+# Instructing pip to fetch wheels from piwheels.org" on ARMv6 and ARMv7 machines
+RUN if [ "$(dpkg --print-architecture)" = "armhf" ] || [ "$(dpkg --print-architecture)" = "armel" ]; then \
+      printf "[global]\nextra-index-url=https://www.piwheels.org/simple\n" > /etc/pip.conf; \
+    fi;
+
 RUN pip install --target=/dependencies -r /requirements.txt
 
 # Playwright is an alternative to Selenium
 # Excluded this package from requirements.txt to prevent arm/v6 and arm/v7 builds from failing
 # https://github.com/dgtlmoon/changedetection.io/pull/1067 also musl/alpine (not supported)
-RUN pip install --target=/dependencies playwright~=1.27.1 \
+RUN pip install --target=/dependencies playwright~=1.39 \
     || 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-bullseye
+FROM python:3.11-slim-bookworm
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
-    libssl1.1 \
     libxslt1.1 \
     # For pdftohtml
     poppler-utils \

README.md

@@ -232,6 +232,13 @@ See the wiki https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configura
 
 Raspberry Pi and linux/arm/v6 linux/arm/v7 arm64 devices are supported! See the wiki for [details](https://github.com/dgtlmoon/changedetection.io/wiki/Fetching-pages-with-WebDriver)
 
+## Import support
+
+Easily [import your list of websites to watch for changes in Excel .xslx file format](https://changedetection.io/tutorial/how-import-your-website-change-detection-lists-excel), or paste in lists of website URLs as plaintext. 
+
+Excel import is recommended - that way you can better organise tags/groups of websites and other features.
+
+
 ## API Support
 
 Supports managing the website watch list [via our API](https://changedetection.io/docs/api_v1/index.html)

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__ = '0.45.3'
+__version__ = '0.45.5'
 
 from changedetectionio.store import BASE_URL_NOT_SET_TEXT
 
@@ -416,11 +416,18 @@ def changedetection_app(config=None, datastore_o=None):
 
         # Sort by last_changed and add the uuid which is usually the key..
         sorted_watches = []
+        with_errors = request.args.get('with_errors') == "1"
+        errored_count = 0
         search_q = request.args.get('q').strip().lower() if request.args.get('q') else False
         for uuid, watch in datastore.data['watching'].items():
+            if with_errors and not watch.get('last_error'):
+                continue
+
             if limit_tag and not limit_tag in watch['tags']:
                     continue
-
+            if watch.get('last_error'):
+                errored_count += 1
+                
             if search_q:
                 if (watch.get('title') and search_q in watch.get('title').lower()) or search_q in watch.get('url', '').lower():
                     sorted_watches.append(watch)
@@ -442,6 +449,7 @@ def changedetection_app(config=None, datastore_o=None):
                                  active_tag=limit_tag,
                                  app_rss_token=datastore.data['settings']['application']['rss_access_token'],
                                  datastore=datastore,
+                                 errored_count=errored_count,
                                  form=form,
                                  guid=datastore.data['app_guid'],
                                  has_proxies=datastore.proxy_list,
@@ -622,7 +630,6 @@ def changedetection_app(config=None, datastore_o=None):
 
             if request.args.get('unpause_on_save'):
                 extra_update_obj['paused'] = False
-
             # Re #110, if they submit the same as the default value, set it to None, so we continue to follow the default
             # Assume we use the default value, unless something relevant is different, then use the form value
             # values could be None, 0 etc.
@@ -708,7 +715,6 @@ def changedetection_app(config=None, datastore_o=None):
 
             # Only works reliably with Playwright
             visualselector_enabled = os.getenv('PLAYWRIGHT_DRIVER_URL', False) and is_html_webdriver
-
             output = render_template("edit.html",
                                      available_processors=processors.available_processors(),
                                      browser_steps_config=browser_step_ui_config,
@@ -816,6 +822,7 @@ def changedetection_app(config=None, datastore_o=None):
         from . import forms
 
         if request.method == 'POST':
+
             from .importer import import_url_list, import_distill_io_json
 
             # URL List import
@@ -839,11 +846,32 @@ def changedetection_app(config=None, datastore_o=None):
                 for uuid in d_importer.new_uuids:
                     update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': True}))
 
+            # XLSX importer
+            if request.files and request.files.get('xlsx_file'):
+                file = request.files['xlsx_file']
+                from .importer import import_xlsx_wachete, import_xlsx_custom
+
+                if request.values.get('file_mapping') == 'wachete':
+                    w_importer = import_xlsx_wachete()
+                    w_importer.run(data=file, flash=flash, datastore=datastore)
+                else:
+                    w_importer = import_xlsx_custom()
+                    # Building mapping of col # to col # type
+                    map = {}
+                    for i in range(10):
+                        c = request.values.get(f"custom_xlsx[col_{i}]")
+                        v = request.values.get(f"custom_xlsx[col_type_{i}]")
+                        if c and v:
+                            map[int(c)] = v
+
+                    w_importer.import_profile = map
+                    w_importer.run(data=file, flash=flash, datastore=datastore)
+
+                for uuid in w_importer.new_uuids:
+                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': True}))
 
-        form = forms.importForm(formdata=request.form if request.method == 'POST' else None,
-#                               data=default,
-                               )
         # Could be some remaining, or we could be on GET
+        form = forms.importForm(formdata=request.form if request.method == 'POST' else None)
         output = render_template("import.html",
                                  form=form,
                                  import_url_list_remaining="\n".join(remaining_urls),
@@ -857,7 +885,10 @@ def changedetection_app(config=None, datastore_o=None):
     def mark_all_viewed():
 
         # Save the current newest history as the most recently viewed
+        with_errors = request.args.get('with_errors') == "1"
         for watch_uuid, watch in datastore.data['watching'].items():
+            if with_errors and not watch.get('last_error'):
+                continue
             datastore.set_last_viewed(watch_uuid, int(time.time()))
 
         return redirect(url_for('index'))
@@ -1177,8 +1208,7 @@ def changedetection_app(config=None, datastore_o=None):
             # These files should be in our subdirectory
             try:
                 # set nocache, set content-type
-                watch_dir = datastore_o.datastore_path + "/" + filename
-                response = make_response(send_from_directory(filename="elements.json", directory=watch_dir, path=watch_dir + "/elements.json"))
+                response = make_response(send_from_directory(os.path.join(datastore_o.datastore_path, filename), "elements.json"))
                 response.headers['Content-type'] = 'application/json'
                 response.headers['Cache-Control'] = 'no-cache, no-store, must-revalidate'
                 response.headers['Pragma'] = 'no-cache'
@@ -1266,6 +1296,8 @@ def changedetection_app(config=None, datastore_o=None):
         # Forced recheck will skip the 'skip if content is the same' rule (, 'reprocess_existing_data': True})))
         tag = request.args.get('tag')
         uuid = request.args.get('uuid')
+        with_errors = request.args.get('with_errors') == "1"
+
         i = 0
 
         running_uuids = []
@@ -1281,6 +1313,8 @@ def changedetection_app(config=None, datastore_o=None):
             # Items that have this current tag
             for watch_uuid, watch in datastore.data['watching'].items():
                 if tag in watch.get('tags', {}):
+                    if with_errors and not watch.get('last_error'):
+                        continue
                     if watch_uuid not in running_uuids and not datastore.data['watching'][watch_uuid]['paused']:
                         update_q.put(
                             queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid, 'skip_when_checksum_same': False})
@@ -1291,8 +1325,11 @@ def changedetection_app(config=None, datastore_o=None):
             # No tag, no uuid, add everything.
             for watch_uuid, watch in datastore.data['watching'].items():
                 if watch_uuid not in running_uuids and not datastore.data['watching'][watch_uuid]['paused']:
+                    if with_errors and not watch.get('last_error'):
+                        continue
                     update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid, 'skip_when_checksum_same': False}))
                     i += 1
+
         flash("{} watches queued for rechecking.".format(i))
         return redirect(url_for('index', tag=tag))
 

changedetectionio/blueprint/browser_steps/__init__.py

@@ -23,8 +23,10 @@
 
 from distutils.util import strtobool
 from flask import Blueprint, request, make_response
-import os
 import logging
+import os
+import re
+
 from changedetectionio.store import ChangeDetectionStore
 from changedetectionio import login_optionally_required
 
@@ -44,7 +46,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
 
 
         # We keep the playwright session open for many minutes
-        seconds_keepalive = int(os.getenv('BROWSERSTEPS_MINUTES_KEEPALIVE', 10)) * 60
+        keepalive_seconds = int(os.getenv('BROWSERSTEPS_MINUTES_KEEPALIVE', 10)) * 60
 
         browsersteps_start_session = {'start_time': time.time()}
 
@@ -56,16 +58,18 @@ def construct_blueprint(datastore: ChangeDetectionStore):
             # Start the Playwright context, which is actually a nodejs sub-process and communicates over STDIN/STDOUT pipes
             io_interface_context = io_interface_context.start()
 
+        keepalive_ms = ((keepalive_seconds + 3) * 1000)
+        base_url = os.getenv('PLAYWRIGHT_DRIVER_URL', '')
+        a = "?" if not '?' in base_url else '&'
+        base_url += a + f"timeout={keepalive_ms}"
 
-        # keep it alive for 10 seconds more than we advertise, sometimes it helps to keep it shutting down cleanly
-        keepalive = "&timeout={}".format(((seconds_keepalive + 3) * 1000))
         try:
-            browsersteps_start_session['browser'] = io_interface_context.chromium.connect_over_cdp(
-                os.getenv('PLAYWRIGHT_DRIVER_URL', '') + keepalive)
+            browsersteps_start_session['browser'] = io_interface_context.chromium.connect_over_cdp(base_url)
         except Exception as e:
             if 'ECONNREFUSED' in str(e):
                 return make_response('Unable to start the Playwright Browser session, is it running?', 401)
             else:
+                # Other errors, bad URL syntax, bad reply etc
                 return make_response(str(e), 401)
 
         proxy_id = datastore.get_preferred_proxy_for_watch(uuid=watch_uuid)
@@ -118,6 +122,31 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         print("Starting connection with playwright - done")
         return {'browsersteps_session_id': browsersteps_session_id}
 
+    @login_optionally_required
+    @browser_steps_blueprint.route("/browsersteps_image", methods=['GET'])
+    def browser_steps_fetch_screenshot_image():
+        from flask import (
+            make_response,
+            request,
+            send_from_directory,
+        )
+        uuid = request.args.get('uuid')
+        step_n = int(request.args.get('step_n'))
+
+        watch = datastore.data['watching'].get(uuid)
+        filename = f"step_before-{step_n}.jpeg" if request.args.get('type', '') == 'before' else f"step_{step_n}.jpeg"
+
+        if step_n and watch and os.path.isfile(os.path.join(watch.watch_data_dir, filename)):
+            response = make_response(send_from_directory(directory=watch.watch_data_dir, path=filename))
+            response.headers['Content-type'] = 'image/jpeg'
+            response.headers['Cache-Control'] = 'no-cache, no-store, must-revalidate'
+            response.headers['Pragma'] = 'no-cache'
+            response.headers['Expires'] = 0
+            return response
+
+        else:
+            return make_response('Unable to fetch image, is the URL correct? does the watch exist? does the step_type-n.jpeg exist?', 401)
+
     # A request for an action was received
     @login_optionally_required
     @browser_steps_blueprint.route("/browsersteps_update", methods=['POST'])

changedetectionio/blueprint/browser_steps/browser_steps.py

@@ -77,13 +77,13 @@ class steppable_browser_interface():
     def action_goto_url(self, selector=None, value=None):
         # self.page.set_viewport_size({"width": 1280, "height": 5000})
         now = time.time()
-        response = self.page.goto(value, timeout=0, wait_until='commit')
-
-        # Wait_until = commit
-        # - `'commit'` - consider operation to be finished when network response is received and the document started loading.
-        # Better to not use any smarts from Playwright and just wait an arbitrary number of seconds
-        # This seemed to solve nearly all 'TimeoutErrors'
+        response = self.page.goto(value, timeout=0, wait_until='load')
+        # Should be the same as the puppeteer_fetch.js methods, means, load with no timeout set (skip timeout)
+        #and also wait for seconds ?
+        #await page.waitForTimeout(1000);
+        #await page.waitForTimeout(extra_wait_ms);
         print("Time to goto URL ", time.time() - now)
+        return response
 
     def action_click_element_containing_text(self, selector=None, value=''):
         if not len(value.strip()):
@@ -99,7 +99,8 @@ class steppable_browser_interface():
         self.page.fill(selector, value, timeout=10 * 1000)
 
     def action_execute_js(self, selector, value):
-        self.page.evaluate(value)
+        response = self.page.evaluate(value)
+        return response
 
     def action_click_element(self, selector, value):
         print("Clicking element")
@@ -138,13 +139,13 @@ class steppable_browser_interface():
     def action_wait_for_text(self, selector, value):
         import json
         v = json.dumps(value)
-        self.page.wait_for_function(f'document.querySelector("body").innerText.includes({v});', timeout=90000)
+        self.page.wait_for_function(f'document.querySelector("body").innerText.includes({v});', timeout=30000)
 
     def action_wait_for_text_in_element(self, selector, value):
         import json
         s = json.dumps(selector)
         v = json.dumps(value)
-        self.page.wait_for_function(f'document.querySelector({s}).innerText.includes({v});', timeout=90000)
+        self.page.wait_for_function(f'document.querySelector({s}).innerText.includes({v});', timeout=30000)
 
     # @todo - in the future make some popout interface to capture what needs to be set
     # https://playwright.dev/python/docs/api/class-keyboard

changedetectionio/content_fetcher.py

@@ -159,6 +159,16 @@ 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
@@ -170,10 +180,7 @@ class Fetcher():
         if self.browser_steps is not None and len(self.browser_steps):
             interface = steppable_browser_interface()
             interface.page = self.page
-
-            valid_steps = filter(
-                lambda s: (s['operation'] and len(s['operation']) and s['operation'] != 'Choose one' and s['operation'] != 'Goto site'),
-                self.browser_steps)
+            valid_steps = self.browser_steps_get_valid_steps()
 
             for step in valid_steps:
                 step_n += 1
@@ -326,9 +333,8 @@ 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'))
-            # 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"
+            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}"
 
         try:
             amp = '&' if '?' in browserless_function_url else '?'
@@ -464,39 +470,26 @@ class base_html_playwright(Fetcher):
             if len(request_headers):
                 context.set_extra_http_headers(request_headers)
 
-                self.page.set_default_navigation_timeout(90000)
-                self.page.set_default_timeout(90000)
+            # Listen for all console events and handle errors
+            self.page.on("console", lambda msg: print(f"Playwright console: Watch URL: {url} {msg.type}: {msg.text} {msg.args}"))
 
-                # Listen for all console events and handle errors
-                self.page.on("console", lambda msg: print(f"Playwright console: Watch URL: {url} {msg.type}: {msg.text} {msg.args}"))
+            # Re-use as much code from browser steps as possible so its the same
+            from changedetectionio.blueprint.browser_steps.browser_steps import steppable_browser_interface
+            browsersteps_interface = steppable_browser_interface()
+            browsersteps_interface.page = self.page
 
-            # Goto page
-            try:
-                # Wait_until = commit
-                # - `'commit'` - consider operation to be finished when network response is received and the document started loading.
-                # Better to not use any smarts from Playwright and just wait an arbitrary number of seconds
-                # This seemed to solve nearly all 'TimeoutErrors'
-                response = self.page.goto(url, wait_until='commit')
-            except playwright._impl._api_types.Error as e:
-                # Retry once - https://github.com/browserless/chrome/issues/2485
-                # Sometimes errors related to invalid cert's and other can be random
-                print("Content Fetcher > retrying request got error - ", str(e))
-                time.sleep(1)
-                response = self.page.goto(url, wait_until='commit')
-            except Exception as e:
-                print("Content Fetcher > Other exception when page.goto", str(e))
+            response = browsersteps_interface.action_goto_url(value=url)
+            self.headers = response.all_headers()
+
+            if response is None:
                 context.close()
                 browser.close()
-                raise PageUnloadable(url=url, status_code=None, message=str(e))
+                print("Content Fetcher > Response object was none")
+                raise EmptyReply(url=url, status_code=None)
 
-            # Execute any browser steps
             try:
-                extra_wait = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay
-                self.page.wait_for_timeout(extra_wait * 1000)
-
                 if self.webdriver_js_execute_code is not None and len(self.webdriver_js_execute_code):
-                    self.page.evaluate(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()
@@ -508,28 +501,26 @@ 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)
-
-            # Run Browser Steps here
-            self.iterate_browser_steps()
-
             extra_wait = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay
-            time.sleep(extra_wait)
+            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)
 
-            self.status_code = response.status
-            self.headers = response.all_headers()
+            # Run Browser Steps here
+            if self.browser_steps_get_valid_steps():
+                self.iterate_browser_steps()
+                
+            self.page.wait_for_timeout(extra_wait * 1000)
 
             # 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:
@@ -541,6 +532,7 @@ 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
@@ -555,7 +547,7 @@ class base_html_playwright(Fetcher):
             except Exception as e:
                 context.close()
                 browser.close()
-                raise ScreenshotUnavailable(url=url, status_code=None)
+                raise ScreenshotUnavailable(url=url, status_code=response.status_code)
 
             context.close()
             browser.close()
@@ -614,14 +606,17 @@ class base_html_webdriver(Fetcher):
             is_binary=False):
 
         from selenium import webdriver
-        from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
+        from selenium.webdriver.chrome.options import Options as ChromeOptions
         from selenium.common.exceptions import WebDriverException
         # request_body, request_method unused for now, until some magic in the future happens.
 
+        options = ChromeOptions()
+        if self.proxy:
+            options.proxy = self.proxy
+
         self.driver = webdriver.Remote(
             command_executor=self.command_executor,
-            desired_capabilities=DesiredCapabilities.CHROME,
-            proxy=self.proxy)
+            options=options)
 
         try:
             self.driver.get(url)
@@ -653,11 +648,11 @@ class base_html_webdriver(Fetcher):
     # Does the connection to the webdriver work? run a test connection.
     def is_ready(self):
         from selenium import webdriver
-        from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
+        from selenium.webdriver.chrome.options import Options as ChromeOptions
 
         self.driver = webdriver.Remote(
             command_executor=self.command_executor,
-            desired_capabilities=DesiredCapabilities.CHROME)
+            options=ChromeOptions())
 
         # driver.quit() seems to cause better exceptions
         self.quit()

changedetectionio/forms.py

@@ -15,14 +15,20 @@ from wtforms import (
     validators,
     widgets
 )
+from flask_wtf.file import FileField, FileAllowed
 from wtforms.fields import FieldList
+
 from wtforms.validators import ValidationError
 
+from validators.url import url as url_validator
+
+
 # default
 # each select <option data-enabled="enabled-0-0"
 from changedetectionio.blueprint.browser_steps.browser_steps import browser_step_ui_config
 
-from changedetectionio import content_fetcher
+from changedetectionio import content_fetcher, html_tools
+
 from changedetectionio.notification import (
     valid_notification_formats,
 )
@@ -40,7 +46,7 @@ valid_method = {
 }
 
 default_method = 'GET'
-
+allow_simplehost = not strtobool(os.getenv('BLOCK_SIMPLEHOSTS', 'False'))
 
 class StringListField(StringField):
     widget = widgets.TextArea()
@@ -260,19 +266,23 @@ class validateURL(object):
         self.message = message
 
     def __call__(self, form, field):
-        import validators
-        # If hosts that only contain alphanumerics are allowed ("localhost" for example)
-        allow_simplehost = not strtobool(os.getenv('BLOCK_SIMPLEHOSTS', 'False'))
-        try:
-            validators.url(field.data.strip(), simple_host=allow_simplehost)
-        except validators.ValidationFailure:
-            message = field.gettext('\'%s\' is not a valid URL.' % (field.data.strip()))
-            raise ValidationError(message)
+        # This should raise a ValidationError() or not
+        validate_url(field.data)
 
-        from .model.Watch import is_safe_url
-        if not is_safe_url(field.data):
-            raise ValidationError('Watch protocol is not permitted by SAFE_PROTOCOL_REGEX')
+def validate_url(test_url):
+    # If hosts that only contain alphanumerics are allowed ("localhost" for example)
+    try:
+        url_validator(test_url, simple_host=allow_simplehost)
+    except validators.ValidationError:
+        #@todo check for xss
+        message = f"'{test_url}' is not a valid URL."
+        # This should be wtforms.validators.
+        raise ValidationError(message)
 
+    from .model.Watch import is_safe_url
+    if not is_safe_url(test_url):
+        # This should be wtforms.validators.
+        raise ValidationError('Watch protocol is not permitted by SAFE_PROTOCOL_REGEX or incorrect URL format')
 
 class ValidateListRegex(object):
     """
@@ -284,11 +294,10 @@ class ValidateListRegex(object):
     def __call__(self, form, field):
 
         for line in field.data:
-            if line[0] == '/' and line[-1] == '/':
-                # Because internally we dont wrap in /
-                line = line.strip('/')
+            if re.search(html_tools.PERL_STYLE_REGEX, line, re.IGNORECASE):
                 try:
-                    re.compile(line)
+                    regex = html_tools.perl_style_slash_enclosed_regex_to_options(line)
+                    re.compile(regex)
                 except re.error:
                     message = field.gettext('RegEx \'%s\' is not a valid regular expression.')
                     raise ValidationError(message % (line))
@@ -398,6 +407,9 @@ class importForm(Form):
     from . import processors
     processor = RadioField(u'Processor', choices=processors.available_processors(), default="text_json_diff")
     urls = TextAreaField('URLs')
+    xlsx_file = FileField('Upload .xlsx file', validators=[FileAllowed(['xlsx'], 'Must be .xlsx file!')])
+    file_mapping = SelectField('File mapping', [validators.DataRequired()], choices={('wachete', 'Wachete mapping'), ('custom','Custom mapping')})
+
 
 class SingleBrowserStep(Form):
 

changedetectionio/html_tools.py

@@ -98,10 +98,7 @@ def xpath_filter(xpath_filter, html_content, append_pretty_line_formatting=False
         elif type(element) == etree._ElementUnicodeResult:
             html_block += str(element)
         else:
-            if not is_rss:
-                html_block += etree.tostring(element, pretty_print=True).decode('utf-8')
-            else:
-                html_block += f"<div>{element.text}</div>\n"
+            html_block += etree.tostring(element, pretty_print=True).decode('utf-8')
 
     return html_block
 
@@ -274,7 +271,7 @@ def cdata_in_document_to_text(html_content: str, render_anchor_tag_content=False
     pattern = '<!\[CDATA\[(\s*(?:.(?<!\]\]>)\s*)*)\]\]>'
     def repl(m):
         text = m.group(1)
-        return xml_escape(html_to_text(html_content=text))
+        return xml_escape(html_to_text(html_content=text)).strip()
 
     return re.sub(pattern, repl, html_content)
 
@@ -295,7 +292,8 @@ def html_to_text(html_content: str, render_anchor_tag_content=False, is_rss=Fals
     #  extracting this content
     if render_anchor_tag_content:
         parser_config = ParserConfig(
-            annotation_rules={"a": ["hyperlink"]}, display_links=True
+            annotation_rules={"a": ["hyperlink"]},
+            display_links=True
         )
     # otherwise set config to None/default
     else:
@@ -303,13 +301,12 @@ def html_to_text(html_content: str, render_anchor_tag_content=False, is_rss=Fals
 
     # RSS Mode - Inscriptis will treat `title` as something else.
     # Make it as a regular block display element (//item/title)
+    # This is a bit of a hack - the real way it to use XSLT to convert it to HTML #1874
     if is_rss:
-        css = CSS_PROFILES['strict'].copy()
-        css['title'] = HtmlElement(display=Display.block)
-        text_content = get_text(html_content, ParserConfig(css=css))
-    else:
-        # get text and annotations via inscriptis
-        text_content = get_text(html_content, config=parser_config)
+        html_content = re.sub(r'<title([\s>])', r'<h1\1', html_content)
+        html_content = re.sub(r'</title>', r'</h1>', html_content)
+
+    text_content = get_text(html_content, config=parser_config)
 
     return text_content
 

changedetectionio/importer.py

@@ -1,6 +1,9 @@
 from abc import ABC, abstractmethod
 import time
 import validators
+from wtforms import ValidationError
+
+from changedetectionio.forms import validate_url
 
 
 class Importer():
@@ -12,6 +15,7 @@ class Importer():
         self.new_uuids = []
         self.good = 0
         self.remaining_data = []
+        self.import_profile = None
 
     @abstractmethod
     def run(self,
@@ -132,3 +136,167 @@ class import_distill_io_json(Importer):
                     good += 1
 
         flash("{} Imported from Distill.io in {:.2f}s, {} Skipped.".format(len(self.new_uuids), time.time() - now, len(self.remaining_data)))
+
+
+class import_xlsx_wachete(Importer):
+
+    def run(self,
+            data,
+            flash,
+            datastore,
+            ):
+
+        good = 0
+        now = time.time()
+        self.new_uuids = []
+
+        from openpyxl import load_workbook
+
+        try:
+            wb = load_workbook(data)
+        except Exception as e:
+            # @todo correct except
+            flash("Unable to read export XLSX file, something wrong with the file?", 'error')
+            return
+
+        row_id = 2
+        for row in wb.active.iter_rows(min_row=row_id):
+            try:
+                extras = {}
+                data = {}
+                for cell in row:
+                    if not cell.value:
+                        continue
+                    column_title = wb.active.cell(row=1, column=cell.column).value.strip().lower()
+                    data[column_title] = cell.value
+
+                # Forced switch to webdriver/playwright/etc
+                dynamic_wachet = str(data.get('dynamic wachet', '')).strip().lower()  # Convert bool to str to cover all cases
+                # libreoffice and others can have it as =FALSE() =TRUE(), or bool(true)
+                if 'true' in dynamic_wachet or dynamic_wachet == '1':
+                    extras['fetch_backend'] = 'html_webdriver'
+                elif 'false' in dynamic_wachet or dynamic_wachet == '0':
+                    extras['fetch_backend'] = 'html_requests'
+
+                if data.get('xpath'):
+                    # @todo split by || ?
+                    extras['include_filters'] = [data.get('xpath')]
+                if data.get('name'):
+                    extras['title'] = data.get('name').strip()
+                if data.get('interval (min)'):
+                    minutes = int(data.get('interval (min)'))
+                    hours, minutes = divmod(minutes, 60)
+                    days, hours = divmod(hours, 24)
+                    weeks, days = divmod(days, 7)
+                    extras['time_between_check'] = {'weeks': weeks, 'days': days, 'hours': hours, 'minutes': minutes, 'seconds': 0}
+
+                # At minimum a URL is required.
+                if data.get('url'):
+                    try:
+                        validate_url(data.get('url'))
+                    except ValidationError as e:
+                        print(">> import URL error", data.get('url'), str(e))
+                        flash(f"Error processing row number {row_id}, URL value was incorrect, row was skipped.", 'error')
+                        # Don't bother processing anything else on this row
+                        continue
+
+                    new_uuid = datastore.add_watch(url=data['url'].strip(),
+                                                   extras=extras,
+                                                   tag=data.get('folder'),
+                                                   write_to_disk_now=False)
+                    if new_uuid:
+                        # Straight into the queue.
+                        self.new_uuids.append(new_uuid)
+                        good += 1
+            except Exception as e:
+                print(e)
+                flash(f"Error processing row number {row_id}, check all cell data types are correct, row was skipped.", 'error')
+            else:
+                row_id += 1
+
+        flash(
+            "{} imported from Wachete .xlsx in {:.2f}s".format(len(self.new_uuids), time.time() - now))
+
+
+class import_xlsx_custom(Importer):
+
+    def run(self,
+            data,
+            flash,
+            datastore,
+            ):
+
+        good = 0
+        now = time.time()
+        self.new_uuids = []
+
+        from openpyxl import load_workbook
+
+        try:
+            wb = load_workbook(data)
+        except Exception as e:
+            # @todo correct except
+            flash("Unable to read export XLSX file, something wrong with the file?", 'error')
+            return
+
+        # @todo cehck atleast 2 rows, same in other method
+        from .forms import validate_url
+        row_i = 1
+
+        try:
+            for row in wb.active.iter_rows():
+                url = None
+                tags = None
+                extras = {}
+
+                for cell in row:
+                    if not self.import_profile.get(cell.col_idx):
+                        continue
+                    if not cell.value:
+                        continue
+
+                    cell_map = self.import_profile.get(cell.col_idx)
+
+                    cell_val = str(cell.value).strip()  # could be bool
+
+                    if cell_map == 'url':
+                        url = cell.value.strip()
+                        try:
+                            validate_url(url)
+                        except ValidationError as e:
+                            print(">> Import URL error", url, str(e))
+                            flash(f"Error processing row number {row_i}, URL value was incorrect, row was skipped.", 'error')
+                            # Don't bother processing anything else on this row
+                            url = None
+                            break
+                    elif cell_map == 'tag':
+                        tags = cell.value.strip()
+                    elif cell_map == 'include_filters':
+                        # @todo validate?
+                        extras['include_filters'] = [cell.value.strip()]
+                    elif cell_map == 'interval_minutes':
+                        hours, minutes = divmod(int(cell_val), 60)
+                        days, hours = divmod(hours, 24)
+                        weeks, days = divmod(days, 7)
+                        extras['time_between_check'] = {'weeks': weeks, 'days': days, 'hours': hours, 'minutes': minutes, 'seconds': 0}
+                    else:
+                        extras[cell_map] = cell_val
+
+                # At minimum a URL is required.
+                if url:
+                    new_uuid = datastore.add_watch(url=url,
+                                                   extras=extras,
+                                                   tag=tags,
+                                                   write_to_disk_now=False)
+                    if new_uuid:
+                        # Straight into the queue.
+                        self.new_uuids.append(new_uuid)
+                        good += 1
+        except Exception as e:
+            print(e)
+            flash(f"Error processing row number {row_i}, check all cell data types are correct, row was skipped.", 'error')
+        else:
+            row_i += 1
+
+        flash(
+            "{} imported from custom .xlsx in {:.2f}s".format(len(self.new_uuids), time.time() - now))

changedetectionio/model/Watch.py

@@ -4,6 +4,7 @@ import os
 import re
 import time
 import uuid
+from pathlib import Path
 
 # Allowable protocols, protects against javascript: etc
 # file:// is further checked by ALLOW_FILE_URI
@@ -18,6 +19,7 @@ from changedetectionio.notification import (
 
 base_config = {
     'body': None,
+    'browser_steps_last_error_step': None,
     'check_unique_lines': False,  # On change-detected, compare against all history if its something new
     'check_count': 0,
     'date_created': None,
@@ -25,6 +27,7 @@ base_config = {
     'extract_text': [],  # Extract text by regex after filters
     'extract_title_as_title': False,
     'fetch_backend': 'system', # plaintext, playwright etc
+    'fetch_time': 0.0,
     'processor': 'text_json_diff', # could be restock_diff or others from .processors
     'filter_failure_notification_send': strtobool(os.getenv('FILTER_FAILURE_NOTIFICATION_SEND_DEFAULT', 'True')),
     'filter_text_added': True,
@@ -489,3 +492,13 @@ class model(dict):
         filepath = os.path.join(self.watch_data_dir, 'last-fetched.br')
         with open(filepath, 'wb') as f:
             f.write(brotli.compress(contents, mode=brotli.MODE_TEXT))
+
+    @property
+    def get_browsersteps_available_screenshots(self):
+        "For knowing which screenshots are available to show the user in BrowserSteps UI"
+        available = []
+        for f in Path(self.watch_data_dir).glob('step_before-*.jpeg'):
+            step_n=re.search(r'step_before-(\d+)', f.name)
+            if step_n:
+                available.append(step_n.group(1))
+        return available

changedetectionio/processors/text_json_diff.py

@@ -274,7 +274,7 @@ class perform_site_check(difference_detection_processor):
                         html_tools.html_to_text(
                             html_content=html_content,
                             render_anchor_tag_content=do_anchor,
-                            is_rss=is_rss
+                            is_rss=is_rss # #1874 activate the <title workaround hack
                         )
 
         # Re #340 - return the content before the 'ignore text' was applied

changedetectionio/static/js/browser-steps.js

@@ -321,8 +321,14 @@ $(document).ready(function () {
             var s = '<div class="control">' + '<a data-step-index=' + i + ' class="pure-button button-secondary button-green button-xsmall apply" >Apply</a>&nbsp;';
             if (i > 0) {
                 // The first step never gets these (Goto-site)
-                s += '<a data-step-index=' + i + ' class="pure-button button-secondary button-xsmall clear" >Clear</a>&nbsp;' +
-                    '<a data-step-index=' + i + ' class="pure-button button-secondary button-red button-xsmall remove" >Remove</a>';
+                s += `<a data-step-index="${i}" class="pure-button button-secondary button-xsmall clear" >Clear</a>&nbsp;` +
+                    `<a data-step-index="${i}" class="pure-button button-secondary button-red button-xsmall remove" >Remove</a>`;
+
+                // if a screenshot is available
+                if (browser_steps_available_screenshots.includes(i.toString())) {
+                    var d = (browser_steps_last_error_step === i+1) ? 'before' : 'after';
+                    s += `&nbsp;<a data-step-index="${i}" class="pure-button button-secondary button-xsmall show-screenshot" title="Show screenshot from last run" data-type="${d}">Pic</a>&nbsp;`;
+                }
             }
             s += '</div>';
             $(this).append(s)
@@ -437,6 +443,24 @@ $(document).ready(function () {
 
     });
 
+    $('ul#browser_steps li .control .show-screenshot').click(function (element) {
+        var step_n = $(event.currentTarget).data('step-index');
+        w = window.open(this.href, "_blank", "width=640,height=480");
+        const t = $(event.currentTarget).data('type');
+
+        const url = browser_steps_fetch_screenshot_image_url + `&step_n=${step_n}&type=${t}`;
+        w.document.body.innerHTML = `<!DOCTYPE html>
+            <html lang="en">
+                <body>
+                    <img src="${url}" style="width: 100%" alt="Browser Step at step ${step_n} from last run." title="Browser Step at step ${step_n} from last run."/>
+                </body>
+        </html>`;
+        w.document.title = `Browser Step at step ${step_n} from last run.`;
+    });
+
+    if (browser_steps_last_error_step) {
+        $("ul#browser_steps>li:nth-child("+browser_steps_last_error_step+")").addClass("browser-step-with-error");
+    }
 
     $("ul#browser_steps select").change(function () {
         set_greyed_state();

changedetectionio/static/js/diff-render.js

@@ -2,8 +2,7 @@ $(document).ready(function () {
     var a = document.getElementById("a");
     var b = document.getElementById("b");
     var result = document.getElementById("result");
-    var inputs = document.getElementsByClassName("change");
-    inputs.current = 0;
+    var inputs;
 
     $('#jump-next-diff').click(function () {
 
@@ -59,9 +58,6 @@ $(document).ready(function () {
         result.textContent = "";
         result.appendChild(fragment);
 
-        // Jump at start
-        inputs.current = 0;
-
         // For nice mouse-over hover/title information
         const removed_current_option = $('#diff-version option:selected')
         if (removed_current_option) {
@@ -75,7 +71,11 @@ $(document).ready(function () {
                 $(this).prop('title', 'Inserted '+inserted_current_option[0].label);
             });
         }
-
+        // Set the list of possible differences to jump to
+        inputs = document.querySelectorAll('#diff-ui .change')
+        // Set the "current" diff pointer
+        inputs.current = 0;
+        // Goto diff
         $('#jump-next-diff').click();
     }
 

changedetectionio/static/styles/scss/parts/_browser-steps.scss

@@ -6,6 +6,10 @@
   }
 
   li {
+    &.browser-step-with-error {
+      background-color: #ffd6d6;
+      border-radius: 4px;
+    }
     &:not(:first-child) {
       &:hover {
         opacity: 1.0;

changedetectionio/static/styles/scss/parts/_visualselector.scss

@@ -0,0 +1,28 @@
+
+#selector-wrapper {
+  height: 100%;
+  max-height: 70vh;
+  overflow-y: scroll;
+  position: relative;
+
+  //width: 100%;
+  >img {
+    position: absolute;
+    z-index: 4;
+    max-width: 100%;
+  }
+
+  >canvas {
+    position: relative;
+    z-index: 5;
+    max-width: 100%;
+
+    &:hover {
+      cursor: pointer;
+    }
+  }
+}
+
+#selector-current-xpath {
+  font-size: 80%;
+}

changedetectionio/static/styles/scss/styles.scss

@@ -943,32 +943,7 @@ ul {
   }
 }
 
-#selector-wrapper {
-  height: 100%;
-  overflow-y: scroll;
-  position: relative;
-
-  //width: 100%;
-  >img {
-    position: absolute;
-    z-index: 4;
-    max-width: 100%;
-  }
-
-  >canvas {
-    position: relative;
-    z-index: 5;
-    max-width: 100%;
-
-    &:hover {
-      cursor: pointer;
-    }
-  }
-}
-
-#selector-current-xpath {
-  font-size: 80%;
-}
+@import "parts/_visualselector";
 
 #webdriver-override-options {
   input[type="number"] {

changedetectionio/static/styles/styles.css

@@ -26,6 +26,9 @@
   #browser_steps li {
     list-style: decimal;
     padding: 5px; }
+    #browser_steps li.browser-step-with-error {
+      background-color: #ffd6d6;
+      border-radius: 4px; }
     #browser_steps li:not(:first-child):hover {
       opacity: 1.0; }
     #browser_steps li .control {
@@ -980,6 +983,7 @@ ul {
 
 #selector-wrapper {
   height: 100%;
+  max-height: 70vh;
   overflow-y: scroll;
   position: relative; }
   #selector-wrapper > img {

changedetectionio/store.py

@@ -244,12 +244,16 @@ class ChangeDetectionStore:
         import pathlib
 
         self.__data['watching'][uuid].update({
-                'last_checked': 0,
+                'browser_steps_last_error_step' : None,
+                'check_count': 0,
+                'fetch_time' : 0.0,
                 'has_ldjson_price_data': None,
+                'last_checked': 0,
                 'last_error': False,
                 'last_notification_error': False,
                 'last_viewed': 0,
                 'previous_md5': False,
+                'previous_md5_before_filters': False,
                 'track_ldjson_price_data': None,
             })
 
@@ -356,6 +360,8 @@ class ChangeDetectionStore:
         if write_to_disk_now:
             self.sync_to_json()
 
+        print("added ", url)
+
         return new_uuid
 
     def visualselector_data_is_ready(self, watch_uuid):

changedetectionio/templates/base.html

@@ -85,6 +85,7 @@
               <a href="{{url_for('logout')}}" class="pure-menu-link">LOG OUT</a>
             </li>
           {% endif %}
+          {% if current_user.is_authenticated or not has_password %}
           <li class="pure-menu-item pure-form" id="search-menu-item">
             <!-- We use GET here so it offers people a chance to set bookmarks etc -->
             <form name="searchForm" action="" method="GET">
@@ -95,6 +96,7 @@
               </button>
             </form>
           </li>
+          {% endif %}
           <li class="pure-menu-item">
             <button class="toggle-button" id ="toggle-light-mode" type="button" title="Toggle Light/Dark Mode">
               <span class="visually-hidden">Toggle light/dark mode</span>

changedetectionio/templates/diff.html

@@ -60,7 +60,7 @@
 </div>
 
 <div id="diff-jump">
-    <a id="jump-next-diff">Jump</a>
+    <a id="jump-next-diff" title="Jump to next difference">Jump</a>
 </div>
 
 <script src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>

changedetectionio/templates/edit.html

@@ -4,8 +4,10 @@
 {% from '_common_fields.jinja' import render_common_settings_form %}
 <script src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
 <script>
-
+    const browser_steps_available_screenshots=JSON.parse('{{ watch.get_browsersteps_available_screenshots|tojson }}');
     const browser_steps_config=JSON.parse('{{ browser_steps_config|tojson }}');
+    const browser_steps_fetch_screenshot_image_url="{{url_for('browser_steps.browser_steps_fetch_screenshot_image', uuid=uuid)}}";
+    const browser_steps_last_error_step={{ watch.browser_steps_last_error_step|tojson }};
     const browser_steps_start_url="{{url_for('browser_steps.browsersteps_start_session', uuid=uuid)}}";
     const browser_steps_sync_url="{{url_for('browser_steps.browsersteps_ui_update', uuid=uuid)}}";
 {% if emailprefix %}
@@ -49,6 +51,7 @@
             <li class="tab"><a href="#restock">Restock Detection</a></li>
             {% endif %}
             <li class="tab"><a href="#notifications">Notifications</a></li>
+            <li class="tab"><a href="#stats">Stats</a></li>
         </ul>
     </div>
 
@@ -441,7 +444,35 @@ Unavailable") }}
                 </fieldset>
             </div>
             {% endif %}
-
+            <div class="tab-pane-inner" id="stats">
+                <div class="pure-control-group">
+                    <style>
+                    #stats-table tr > td:first-child {
+                        font-weight: bold;
+                    }
+                    </style>
+                    <table class="pure-table" id="stats-table">
+                        <tbody>
+                        <tr>
+                            <td>Check count</td>
+                            <td>{{ "{:,}".format( watch.check_count) }}</td>
+                        </tr>
+                        <tr>
+                            <td>Consecutive filter failures</td>
+                            <td>{{ "{:,}".format( watch.consecutive_filter_failures) }}</td>
+                        </tr>
+                        <tr>
+                            <td>History length</td>
+                            <td>{{ "{:,}".format(watch.history|length) }}</td>
+                        </tr>
+                        <tr>
+                            <td>Last fetch time</td>
+                            <td>{{ watch.fetch_time }}s</td>
+                        </tr>
+                        </tbody>
+                    </table>
+                </div>
+            </div>
             <div id="actions">
                 <div class="pure-control-group">
                     {{ render_button(form.save_button) }}

changedetectionio/templates/import.html

@@ -8,11 +8,12 @@
         <ul>
             <li class="tab" id=""><a href="#url-list">URL List</a></li>
             <li class="tab"><a href="#distill-io">Distill.io</a></li>
+            <li class="tab"><a href="#xlsx">.XLSX &amp; Wachete</a></li>
         </ul>
     </div>
 
     <div class="box-wrap inner">
-        <form class="pure-form pure-form-aligned" action="{{url_for('import_page')}}" method="POST">
+        <form class="pure-form" action="{{url_for('import_page')}}" method="POST" enctype="multipart/form-data">
             <input type="hidden" name="csrf_token" value="{{ csrf_token() }}">
             <div class="tab-pane-inner" id="url-list">
                     <legend>
@@ -79,6 +80,42 @@
 " rows="25">{{ original_distill_json }}</textarea>
 
             </div>
+            <div class="tab-pane-inner" id="xlsx">
+            <fieldset>
+                <div class="pure-control-group">
+                {{ render_field(form.xlsx_file, class="processor") }}
+                </div>
+                <div class="pure-control-group">
+                    {{ render_field(form.file_mapping, class="processor") }}
+                </div>
+            </fieldset>
+                <div class="pure-control-group">
+                <span class="pure-form-message-inline">
+                    Table of custom column and data types mapping for the <strong>Custom mapping</strong> File mapping type.
+                </span>
+                    <table style="border: 1px solid #aaa; padding: 0.5rem; border-radius: 4px;">
+                        <tr>
+                            <td><strong>Column #</strong></td>
+                            {% for n in range(4) %}
+                                <td><input type="number" name="custom_xlsx[col_{{n}}]" style="width: 4rem;" min="1"></td>
+                            {%  endfor %}
+                        </tr>
+                        <tr>
+                            <td><strong>Type</strong></td>
+                            {% for n in range(4) %}
+                                <td><select name="custom_xlsx[col_type_{{n}}]">
+                                    <option value="" style="color: #aaa"> -- none --</option>
+                                    <option value="url">URL</option>
+                                    <option value="title">Title</option>
+                                    <option value="include_filter">CSS/xPath filter</option>
+                                    <option value="tag">Group / Tag name(s)</option>
+                                    <option value="interval_minutes">Recheck time (minutes)</option>
+                                </select></td>
+                            {%  endfor %}
+                        </tr>
+                    </table>
+                </div>
+            </div>
             <button type="submit" class="pure-button pure-input-1-2 pure-button-primary">Import</button>
         </form>
 

changedetectionio/templates/watch-overview.html

@@ -178,13 +178,18 @@
             </tbody>
         </table>
         <ul id="post-list-buttons">
+            {% if errored_count %}
+            <li>
+                <a href="{{url_for('index', with_errors=1, tag=request.args.get('tag')) }}" class="pure-button button-tag button-error ">With errors ({{ errored_count }})</a>
+            </li>
+            {% endif %}
             {% if has_unviewed %}
             <li>
-                <a href="{{url_for('mark_all_viewed', tag=request.args.get('tag')) }}" class="pure-button button-tag ">Mark all viewed</a>
+                <a href="{{url_for('mark_all_viewed',with_errors=request.args.get('with_errors',0)) }}" class="pure-button button-tag ">Mark all viewed</a>
             </li>
             {% endif %}
             <li>
-               <a href="{{ url_for('form_watch_checknow', tag=active_tag) }}" class="pure-button button-tag ">Recheck
+               <a href="{{ url_for('form_watch_checknow', tag=active_tag, with_errors=request.args.get('with_errors',0)) }}" class="pure-button button-tag ">Recheck
                 all {% if active_tag%} in "{{tags[active_tag].title}}"{%endif%}</a>
             </li>
             <li>

changedetectionio/tests/test_access_control.py

@@ -1,4 +1,4 @@
-from . util import live_server_setup, extract_UUID_from_client
+from .util import live_server_setup, extract_UUID_from_client, wait_for_all_checks
 from flask import url_for
 import time
 
@@ -19,10 +19,16 @@ def test_check_access_control(app, client, live_server):
         )
 
         assert b"1 Imported" in res.data
-        time.sleep(2)
-        res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
+        time.sleep(3)
+        # causes a 'Popped wrong request context.' error when client. is accessed?
+        #wait_for_all_checks(client)
+
+        res = c.get(url_for("form_watch_checknow"), follow_redirects=True)
         assert b'1 watches queued for rechecking.' in res.data
-        time.sleep(2)
+        time.sleep(3)
+        # causes a 'Popped wrong request context.' error when client. is accessed?
+        #wait_for_all_checks(client)
+
 
         # Enable password check and diff page access bypass
         res = c.post(
@@ -42,7 +48,7 @@ def test_check_access_control(app, client, live_server):
         assert b"Login" in res.data
 
         # The diff page should return something valid when logged out
-        res = client.get(url_for("diff_history_page", uuid="first"))
+        res = c.get(url_for("diff_history_page", uuid="first"))
         assert b'Random content' in res.data
 
         # Check wrong password does not let us in
@@ -83,6 +89,8 @@ def test_check_access_control(app, client, live_server):
         res = c.get(url_for("logout"),
             follow_redirects=True)
 
+        assert b"Login" in res.data
+
         res = c.get(url_for("settings_page"),
             follow_redirects=True)
 
@@ -160,5 +168,5 @@ def test_check_access_control(app, client, live_server):
         assert b"Login" in res.data
 
         # The diff page should return something valid when logged out
-        res = client.get(url_for("diff_history_page", uuid="first"))
+        res = c.get(url_for("diff_history_page", uuid="first"))
         assert b'Random content' not in res.data

changedetectionio/tests/test_extract_regex.py

@@ -202,3 +202,35 @@ def test_check_filter_and_regex_extract(client, live_server):
 
     # Should not be here
     assert b'Some text that did change' not in res.data
+
+
+
+def test_regex_error_handling(client, live_server):
+
+    #live_server_setup(live_server)
+
+    # Add our URL to the import page
+    test_url = url_for('test_endpoint', _external=True)
+    res = client.post(
+        url_for("import_page"),
+        data={"urls": test_url},
+        follow_redirects=True
+    )
+    assert b"1 Imported" in res.data
+
+    ### test regex error handling
+    res = client.post(
+        url_for("edit_page", uuid="first"),
+        data={"extract_text": '/something bad\d{3/XYZ',
+              "url": test_url,
+              "fetch_backend": "html_requests"},
+        follow_redirects=True
+    )
+
+    with open('/tmp/fuck.html', 'wb') as f:
+        f.write(res.data)
+
+    assert b'is not a valid regular expression.' in res.data
+
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data

changedetectionio/tests/test_import.py

@@ -1,16 +1,19 @@
 #!/usr/bin/python3
-
+import io
+import os
 import time
 
 from flask import url_for
 
-from .util import live_server_setup
+from .util import live_server_setup, wait_for_all_checks
+
+
 def test_setup(client, live_server):
     live_server_setup(live_server)
 
 def test_import(client, live_server):
     # Give the endpoint time to spin up
-    time.sleep(1)
+    wait_for_all_checks(client)
 
     res = client.post(
         url_for("import_page"),
@@ -119,3 +122,97 @@ def test_import_distillio(client, live_server):
     res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
     # Clear flask alerts
     res = client.get(url_for("index"))
+
+def test_import_custom_xlsx(client, live_server):
+    """Test can upload a excel spreadsheet and the watches are created correctly"""
+
+    #live_server_setup(live_server)
+
+    dirname = os.path.dirname(__file__)
+    filename = os.path.join(dirname, 'import/spreadsheet.xlsx')
+    with open(filename, 'rb') as f:
+
+        data= {
+            'file_mapping': 'custom',
+            'custom_xlsx[col_0]': '1',
+            'custom_xlsx[col_1]': '3',
+            'custom_xlsx[col_2]': '5',
+            'custom_xlsx[col_3]': '4',
+            'custom_xlsx[col_type_0]': 'title',
+            'custom_xlsx[col_type_1]': 'url',
+            'custom_xlsx[col_type_2]': 'include_filters',
+            'custom_xlsx[col_type_3]': 'interval_minutes',
+            'xlsx_file': (io.BytesIO(f.read()), 'spreadsheet.xlsx')
+        }
+
+    res = client.post(
+        url_for("import_page"),
+        data=data,
+        follow_redirects=True,
+    )
+
+    assert b'4 imported from custom .xlsx' in res.data
+    # Because this row was actually just a header with no usable URL, we should get an error
+    assert b'Error processing row number 1' in res.data
+
+    res = client.get(
+        url_for("index")
+    )
+
+    assert b'Somesite results ABC' in res.data
+    assert b'City news results' in res.data
+
+    # Just find one to check over
+    for uuid, watch in live_server.app.config['DATASTORE'].data['watching'].items():
+        if watch.get('title') == 'Somesite results ABC':
+            filters = watch.get('include_filters')
+            assert filters[0] == '/html[1]/body[1]/div[4]/div[1]/div[1]/div[1]||//*[@id=\'content\']/div[3]/div[1]/div[1]||//*[@id=\'content\']/div[1]'
+            assert watch.get('time_between_check') == {'weeks': 0, 'days': 1, 'hours': 6, 'minutes': 24, 'seconds': 0}
+
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data
+
+def test_import_watchete_xlsx(client, live_server):
+    """Test can upload a excel spreadsheet and the watches are created correctly"""
+
+    #live_server_setup(live_server)
+    dirname = os.path.dirname(__file__)
+    filename = os.path.join(dirname, 'import/spreadsheet.xlsx')
+    with open(filename, 'rb') as f:
+
+        data= {
+            'file_mapping': 'wachete',
+            'xlsx_file': (io.BytesIO(f.read()), 'spreadsheet.xlsx')
+        }
+
+    res = client.post(
+        url_for("import_page"),
+        data=data,
+        follow_redirects=True,
+    )
+
+    assert b'4 imported from Wachete .xlsx' in res.data
+
+    res = client.get(
+        url_for("index")
+    )
+
+    assert b'Somesite results ABC' in res.data
+    assert b'City news results' in res.data
+
+    # Just find one to check over
+    for uuid, watch in live_server.app.config['DATASTORE'].data['watching'].items():
+        if watch.get('title') == 'Somesite results ABC':
+            filters = watch.get('include_filters')
+            assert filters[0] == '/html[1]/body[1]/div[4]/div[1]/div[1]/div[1]||//*[@id=\'content\']/div[3]/div[1]/div[1]||//*[@id=\'content\']/div[1]'
+            assert watch.get('time_between_check') == {'weeks': 0, 'days': 1, 'hours': 6, 'minutes': 24, 'seconds': 0}
+            assert watch.get('fetch_backend') == 'html_requests' # Has inactive 'dynamic wachet'
+
+        if watch.get('title') == 'JS website':
+            assert watch.get('fetch_backend') == 'html_webdriver' # Has active 'dynamic wachet'
+
+        if watch.get('title') == 'system default website':
+            assert watch.get('fetch_backend') == 'system' # uses default if blank
+
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data

changedetectionio/tests/test_rss.py

@@ -118,7 +118,7 @@ def test_basic_cdata_rss_markup(client, live_server):
     res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
 
 def test_rss_xpath_filtering(client, live_server):
-#    live_server_setup(live_server)
+    #live_server_setup(live_server)
 
     set_original_cdata_xml()
 
@@ -154,6 +154,9 @@ def test_rss_xpath_filtering(client, live_server):
     )
     assert b'CDATA' not in res.data
     assert b'<![' not in res.data
+    # #1874  All but the first <title was getting selected
+    # Convert any HTML with just a top level <title> to <h1> to be sure title renders
+
     assert b'Hackers can access your computer' in res.data # Should ONLY be selected by the xpath
     assert b'Some other title' in res.data  # Should ONLY be selected by the xpath
     assert b'The days of Terminator' not in res.data # Should NOT be selected by the xpath

changedetectionio/tests/visualselector/test_fetch_data.py

@@ -1,18 +1,19 @@
 #!/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"
@@ -53,6 +54,13 @@ def test_visual_selector_content_ready(client, live_server):
     with open(os.path.join('test-datastore', uuid, 'elements.json'), 'r') as f:
         json.load(f)
 
+    # Attempt to fetch it via the web hook that the browser would use
+    res = client.get(url_for('static_content', group='visual_selector_data', filename=uuid))
+    json.loads(res.data)
+    assert res.mimetype == 'application/json'
+    assert res.status_code == 200
+
+
     # Some options should be enabled
     # @todo - in the future, the visibility should be toggled by JS from the request type setting
     res = client.get(
@@ -60,4 +68,75 @@ 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
+    )

changedetectionio/update_worker.py

@@ -238,7 +238,9 @@ class update_worker(threading.Thread):
                             # Used as a default and also by some tests
                             update_handler = text_json_diff.perform_site_check(datastore=self.datastore)
 
+                        self.datastore.data['watching'][uuid]['browser_steps_last_error_step'] = None
                         changed_detected, update_obj, contents = update_handler.run(uuid, skip_when_checksum_same=queued_item_data.item.get('skip_when_checksum_same'))
+
                         # Re #342
                         # In Python 3, all strings are sequences of Unicode characters. There is a bytes type that holds raw bytes.
                         # We then convert/.decode('utf-8') for the notification etc
@@ -324,8 +326,13 @@ class update_worker(threading.Thread):
                         if not self.datastore.data['watching'].get(uuid):
                             continue
 
-                        err_text = "Warning, browser step at position {} could not run, target not found, check the watch, add a delay if necessary.".format(e.step_n+1)
-                        self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text})
+                        error_step = e.step_n + 1
+                        err_text = f"Warning, browser step at position {error_step} could not run, target not found, check the watch, add a delay if necessary, view Browser Steps to see screenshot at that step"
+                        self.datastore.update_watch(uuid=uuid,
+                                                    update_obj={'last_error': err_text,
+                                                                'browser_steps_last_error_step': error_step
+                                                                }
+                                                    )
 
 
                         if self.datastore.data['watching'][uuid].get('filter_failure_notification_send', False):

docker-compose.yml

@@ -66,25 +66,12 @@ services:
 #        browser-chrome:
 #            condition: service_started
 
-#    browser-chrome:
-#        hostname: browser-chrome
-#        image: selenium/standalone-chrome-debug:3.141.59
-#        environment:
-#            - VNC_NO_PASSWORD=1
-#            - SCREEN_WIDTH=1920
-#            - SCREEN_HEIGHT=1080
-#            - SCREEN_DEPTH=24
-#        volumes:
-#            # Workaround to avoid the browser crashing inside a docker container
-#            # See https://github.com/SeleniumHQ/docker-selenium#quick-start
-#            - /dev/shm:/dev/shm
-#        restart: unless-stopped
-
      # Used for fetching pages via Playwright+Chrome where you need Javascript support.
      # Note: Playwright/browserless not supported on ARM type devices (rPi etc)
+     # RECOMMENDED FOR FETCHING PAGES WITH CHROME
 #    playwright-chrome:
 #        hostname: playwright-chrome
-#        image: browserless/chrome
+#        image: browserless/chrome:1.60-chrome-stable
 #        restart: unless-stopped
 #        environment:
 #            - SCREEN_WIDTH=1920
@@ -101,6 +88,23 @@ services:
 #             Ignore HTTPS errors, like for self-signed certs
 #            - DEFAULT_IGNORE_HTTPS_ERRORS=true
 #
+
+     # Used for fetching pages via Playwright+Chrome where you need Javascript support.
+     # Note: works well but is deprecated, doesnt fetch full page screenshots and other issues
+#    browser-chrome:
+#        hostname: browser-chrome
+#        image: selenium/standalone-chrome:4
+#        environment:
+#            - VNC_NO_PASSWORD=1
+#            - SCREEN_WIDTH=1920
+#            - SCREEN_HEIGHT=1080
+#            - SCREEN_DEPTH=24
+#        volumes:
+#            # Workaround to avoid the browser crashing inside a docker container
+#            # See https://github.com/SeleniumHQ/docker-selenium#quick-start
+#            - /dev/shm:/dev/shm
+#        restart: unless-stopped
+
 volumes:
   changedetection-data:
 

requirements.txt

@@ -1,12 +1,12 @@
 eventlet>=0.31.0
 feedgen~=0.9
 flask-compress
-flask-login~=0.5
+flask-login~=0.6
 flask-paginate
 flask_expects_json~=1.7
 flask_restful
 flask_wtf
-flask~=2.0
+flask~=2.3
 inscriptis~=2.2
 pytz
 timeago~=1.0
@@ -49,21 +49,18 @@ beautifulsoup4
 # XPath filtering, lxml is required by bs4 anyway, but put it here to be safe.
 lxml
 
-# 3.141 was missing socksVersion, 3.150 was not in pypi, so we try 4.1.0
-selenium~=4.1.0
+selenium~=4.14.0
 
-# https://stackoverflow.com/questions/71652965/importerror-cannot-import-name-safe-str-cmp-from-werkzeug-security/71653849#71653849
-# ImportError: cannot import name 'safe_str_cmp' from 'werkzeug.security'
-# need to revisit flask login versions
-werkzeug~=2.0.0
+werkzeug
 
 # Templating, so far just in the URLs but in the future can be for the notifications also
 jinja2~=3.1
 jinja2-time
-
+openpyxl
 # https://peps.python.org/pep-0508/#environment-markers
 # https://github.com/dgtlmoon/changedetection.io/pull/1009
-jq~=1.3 ;python_version >= "3.8" and sys_platform == "linux"
+jq~=1.3; python_version >= "3.8" and sys_platform == "darwin"
+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