Adding handy "limit to watches with errors" button

.github/workflows/containers.yml

@@ -96,9 +96,8 @@ jobs:
           tags: |
             ${{ secrets.DOCKER_HUB_USERNAME }}/changedetection.io:dev,ghcr.io/${{ github.repository }}:dev
           platforms: linux/amd64,linux/arm64,linux/arm/v6,linux/arm/v7,linux/arm/v8
-          cache-from: type=gha
-          cache-to: type=gha,mode=max
-
+          cache-from: type=local,src=/tmp/.buildx-cache
+          cache-to: type=local,dest=/tmp/.buildx-cache
 # Looks like this was disabled
 #          provenance: false
 
@@ -117,11 +116,18 @@ jobs:
             ${{ secrets.DOCKER_HUB_USERNAME }}/changedetection.io:latest
             ghcr.io/dgtlmoon/changedetection.io:latest
           platforms: linux/amd64,linux/arm64,linux/arm/v6,linux/arm/v7,linux/arm/v8
-          cache-from: type=gha
-          cache-to: type=gha,mode=max
+          cache-from: type=local,src=/tmp/.buildx-cache
+          cache-to: type=local,dest=/tmp/.buildx-cache
 # Looks like this was disabled
 #          provenance: false
 
       - name: Image digest
         run: echo step SHA ${{ steps.vars.outputs.sha_short }} tag ${{steps.vars.outputs.tag}} branch ${{steps.vars.outputs.branch}} digest ${{ steps.docker_build.outputs.digest }}
 
+      - name: Cache Docker layers
+        uses: actions/cache@v3
+        with:
+          path: /tmp/.buildx-cache
+          key: ${{ runner.os }}-buildx-${{ github.sha }}
+          restore-keys: |
+            ${{ runner.os }}-buildx-

.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: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" ghcr.io/browserless/chrome:latest
+          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
 
       - name: Build changedetection.io container for testing
         run: |         

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
@@ -25,13 +25,14 @@ 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~=1.39 \
+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 \

MANIFEST.in

@@ -16,4 +16,3 @@ global-exclude venv
 
 global-exclude test-datastore
 global-exclude changedetection.io*dist-info
-global-exclude changedetectionio/tests/proxy_socks5/test-datastore

README.md

@@ -232,13 +232,6 @@ 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__ = '0.45.7.3'
+__version__ = '0.45.3'
 
 from changedetectionio.store import BASE_URL_NOT_SET_TEXT
 
@@ -105,10 +105,6 @@ def get_darkmode_state():
     css_dark_mode = request.cookies.get('css_dark_mode', 'false')
     return 'true' if css_dark_mode and strtobool(css_dark_mode) else 'false'
 
-@app.template_global()
-def get_css_version():
-    return __version__
-
 # We use the whole watch object from the store/JSON so we can see if there's some related status in terms of a thread
 # running or something similar.
 @app.template_filter('format_last_checked_time')
@@ -426,12 +422,11 @@ def changedetection_app(config=None, datastore_o=None):
         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 limit_tag and not limit_tag in watch['tags']:
+                    continue
+
             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)
@@ -826,7 +821,6 @@ 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
@@ -850,32 +844,11 @@ 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),
@@ -1212,7 +1185,8 @@ def changedetection_app(config=None, datastore_o=None):
             # These files should be in our subdirectory
             try:
                 # set nocache, set content-type
-                response = make_response(send_from_directory(os.path.join(datastore_o.datastore_path, filename), "elements.json"))
+                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.headers['Content-type'] = 'application/json'
                 response.headers['Cache-Control'] = 'no-cache, no-store, must-revalidate'
                 response.headers['Pragma'] = 'no-cache'

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='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);
+        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'
         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()):
@@ -99,8 +99,7 @@ class steppable_browser_interface():
         self.page.fill(selector, value, timeout=10 * 1000)
 
     def action_execute_js(self, selector, value):
-        response = self.page.evaluate(value)
-        return response
+        self.page.evaluate(value)
 
     def action_click_element(self, selector, value):
         print("Clicking element")

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 '?'
@@ -470,26 +464,39 @@ class base_html_playwright(Fetcher):
             if len(request_headers):
                 context.set_extra_http_headers(request_headers)
 
-            # 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}"))
+                self.page.set_default_navigation_timeout(90000)
+                self.page.set_default_timeout(90000)
 
-            # 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
+                # 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}"))
 
-            response = browsersteps_interface.action_goto_url(value=url)
-            self.headers = response.all_headers()
-
-            if response is None:
+            # 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))
                 context.close()
                 browser.close()
-                print("Content Fetcher > Response object was none")
-                raise EmptyReply(url=url, status_code=None)
+                raise PageUnloadable(url=url, status_code=None, message=str(e))
 
+            # 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):
-                    browsersteps_interface.action_execute_js(value=self.webdriver_js_execute_code, selector=None)
+                    self.page.evaluate(self.webdriver_js_execute_code)
+
             except playwright._impl._api_types.TimeoutError as e:
                 context.close()
                 browser.close()
@@ -501,26 +508,28 @@ 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
-            self.page.wait_for_timeout(extra_wait * 1000)
-
+            time.sleep(extra_wait)
 
+            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 +541,6 @@ 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 +555,7 @@ 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()
@@ -606,17 +614,14 @@ class base_html_webdriver(Fetcher):
             is_binary=False):
 
         from selenium import webdriver
-        from selenium.webdriver.chrome.options import Options as ChromeOptions
+        from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
         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,
-            options=options)
+            desired_capabilities=DesiredCapabilities.CHROME,
+            proxy=self.proxy)
 
         try:
             self.driver.get(url)
@@ -648,11 +653,11 @@ 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.chrome.options import Options as ChromeOptions
+        from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
 
         self.driver = webdriver.Remote(
             command_executor=self.command_executor,
-            options=ChromeOptions())
+            desired_capabilities=DesiredCapabilities.CHROME)
 
         # driver.quit() seems to cause better exceptions
         self.quit()

changedetectionio/forms.py

@@ -15,20 +15,14 @@ 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, html_tools
-
+from changedetectionio import content_fetcher
 from changedetectionio.notification import (
     valid_notification_formats,
 )
@@ -46,7 +40,7 @@ valid_method = {
 }
 
 default_method = 'GET'
-allow_simplehost = not strtobool(os.getenv('BLOCK_SIMPLEHOSTS', 'False'))
+
 
 class StringListField(StringField):
     widget = widgets.TextArea()
@@ -266,23 +260,19 @@ class validateURL(object):
         self.message = message
 
     def __call__(self, form, field):
-        # This should raise a ValidationError() or not
-        validate_url(field.data)
+        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)
 
-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(field.data):
+            raise ValidationError('Watch protocol is not permitted by SAFE_PROTOCOL_REGEX')
 
-    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):
     """
@@ -294,10 +284,11 @@ class ValidateListRegex(object):
     def __call__(self, form, field):
 
         for line in field.data:
-            if re.search(html_tools.PERL_STYLE_REGEX, line, re.IGNORECASE):
+            if line[0] == '/' and line[-1] == '/':
+                # Because internally we dont wrap in /
+                line = line.strip('/')
                 try:
-                    regex = html_tools.perl_style_slash_enclosed_regex_to_options(line)
-                    re.compile(regex)
+                    re.compile(line)
                 except re.error:
                     message = field.gettext('RegEx \'%s\' is not a valid regular expression.')
                     raise ValidationError(message % (line))
@@ -407,9 +398,6 @@ 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/importer.py

@@ -1,9 +1,6 @@
 from abc import ABC, abstractmethod
 import time
 import validators
-from wtforms import ValidationError
-
-from changedetectionio.forms import validate_url
 
 
 class Importer():
@@ -15,7 +12,6 @@ class Importer():
         self.new_uuids = []
         self.good = 0
         self.remaining_data = []
-        self.import_profile = None
 
     @abstractmethod
     def run(self,
@@ -136,167 +132,3 @@ 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/static/js/toggle-theme.js

@@ -3,50 +3,45 @@
  * Toggles theme between light and dark mode.
  */
 $(document).ready(function () {
-    const button = document.getElementById("toggle-light-mode");
+  const button = document.getElementById("toggle-light-mode");
 
-    button.onclick = () => {
-        const htmlElement = document.getElementsByTagName("html");
-        const isDarkMode = htmlElement[0].dataset.darkmode === "true";
-        htmlElement[0].dataset.darkmode = !isDarkMode;
-        setCookieValue(!isDarkMode);
-    };
+  button.onclick = () => {
+    const htmlElement = document.getElementsByTagName("html");
+    const isDarkMode = htmlElement[0].dataset.darkmode === "true";
+    htmlElement[0].dataset.darkmode = !isDarkMode;
+    setCookieValue(!isDarkMode);
+  };
 
-    const setCookieValue = (value) => {
-        document.cookie = `css_dark_mode=${value};max-age=31536000;path=/`
-    }
+  const setCookieValue = (value) => {
+    document.cookie = `css_dark_mode=${value};max-age=31536000;path=/`
+  }
 
-    // Search input box behaviour
+  // Search input box behaviour
     const toggle_search = document.getElementById("toggle-search");
-    const search_q = document.getElementById("search-q");
-    if(search_q) {
-      window.addEventListener('keydown', function (e) {
-        if (e.altKey == true && e.keyCode == 83) {
-          search_q.classList.toggle('expanded');
-          search_q.focus();
-        }
-      });
+  const search_q = document.getElementById("search-q");
+  window.addEventListener('keydown', function (e) {
 
-      search_q.onkeydown = (e) => {
-        var key = e.keyCode || e.which;
-        if (key === 13) {
-          document.searchForm.submit();
-        }
-      };
-      toggle_search.onclick = () => {
-        // Could be that they want to search something once text is in there
-        if (search_q.value.length) {
-          document.searchForm.submit();
-        } else {
-          // If not..
-          search_q.classList.toggle('expanded');
-          search_q.focus();
-        }
-      };
+    if (e.altKey == true && e.keyCode == 83)
+      search_q.classList.toggle('expanded');
+      search_q.focus();
+  });
+
+
+  search_q.onkeydown = (e) => {
+    var key = e.keyCode || e.which;
+    if (key === 13) {
+      document.searchForm.submit();
     }
+  };
+  toggle_search.onclick = () => {
+    // Could be that they want to search something once text is in there
+    if (search_q.value.length) {
+      document.searchForm.submit();
+    } else {
+      // If not..
+      search_q.classList.toggle('expanded');
+      search_q.focus();
+    }
+  };
 
-    $('#heart-us').click(function () {
-        $("#overlay").toggleClass('visible');
-        heartpath.style.fill = document.getElementById("overlay").classList.contains("visible") ? '#ff0000' : 'var(--color-background)';
-    });
 });

changedetectionio/static/styles/scss/parts/_darkmode.scss

@@ -1,6 +1,6 @@
 
 #toggle-light-mode {
-/*  width: 3rem;*/
+  width: 3rem;
   /* default */
   .icon-dark {
     display: none;

changedetectionio/static/styles/scss/parts/_love.scss

@@ -1,38 +0,0 @@
-#overlay {
-
-  opacity: 0.95;
-  position: fixed;
-
-  width: 350px;
-  max-width: 100%;
-  height: 100%;
-  top: 0;
-  right: -350px;
-  background-color: var(--color-table-stripe);
-  z-index: 2;
-
-  transform: translateX(0);
-  transition: transform .5s ease;
-
-
-  &.visible {
-    transform: translateX(-100%);
-
-  }
-
-  .content {
-    font-size: 0.875rem;
-    padding: 1rem;
-    margin-top: 5rem;
-    max-width: 400px;
-    color: var(--color-watch-table-row-text);
-  }
-}
-
-#heartpath {
-  &:hover {
-    fill: #ff0000 !important;
-    transition: all ease 0.3s !important;
-  }
-  transition: all ease 0.3s !important;
-}

changedetectionio/static/styles/scss/parts/_menu.scss

@@ -1,25 +0,0 @@
-.pure-menu-link {
-  padding: 0.5rem 1em;
-  line-height: 1.2rem;
-}
-
-.pure-menu-item {
-  svg {
-    height: 1.2rem;
-  }
-  * {
-    vertical-align: middle;
-  }
-  .github-link {
-    height: 1.8rem;
-    display: block;
-    svg {
-      height: 100%;
-    }
-  }
-  .bi-heart {
-    &:hover {
-      cursor: pointer;
-    }
-  }
-}

changedetectionio/static/styles/scss/styles.scss

@@ -9,13 +9,10 @@
 @import "parts/_spinners";
 @import "parts/_variables";
 @import "parts/_darkmode";
-@import "parts/_menu";
-@import "parts/_love";
 
 body {
   color: var(--color-text);
   background: var(--color-background-page);
-  font-family: Helvetica Neue, Helvetica, Lucida Grande, Arial, Ubuntu, Cantarell, Fira Sans, sans-serif;
 }
 
 .visually-hidden {
@@ -58,6 +55,11 @@ a.github-link {
   }
 }
 
+
+#toggle-search {
+  width: 2rem;
+}
+
 #search-q {
   opacity: 0;
   -webkit-transition: all .9s ease;
@@ -1080,4 +1082,3 @@ ul {
   border-radius: 3px;
   white-space: nowrap;
 }
-

changedetectionio/static/styles/styles.css

@@ -331,7 +331,7 @@ html[data-darkmode="true"] {
       color: var(--color-watch-table-error); }
 
 #toggle-light-mode {
-  /*  width: 3rem;*/
+  width: 3rem;
   /* default */ }
   #toggle-light-mode .icon-dark {
     display: none; }
@@ -342,56 +342,9 @@ html[data-darkmode="true"] #toggle-light-mode .icon-light {
 html[data-darkmode="true"] #toggle-light-mode .icon-dark {
   display: block; }
 
-.pure-menu-link {
-  padding: 0.5rem 1em;
-  line-height: 1.2rem; }
-
-.pure-menu-item svg {
-  height: 1.2rem; }
-
-.pure-menu-item * {
-  vertical-align: middle; }
-
-.pure-menu-item .github-link {
-  height: 1.8rem;
-  display: block; }
-  .pure-menu-item .github-link svg {
-    height: 100%; }
-
-.pure-menu-item .bi-heart:hover {
-  cursor: pointer; }
-
-#overlay {
-  opacity: 0.95;
-  position: fixed;
-  width: 350px;
-  max-width: 100%;
-  height: 100%;
-  top: 0;
-  right: -350px;
-  background-color: var(--color-table-stripe);
-  z-index: 2;
-  transform: translateX(0);
-  transition: transform .5s ease; }
-  #overlay.visible {
-    transform: translateX(-100%); }
-  #overlay .content {
-    font-size: 0.875rem;
-    padding: 1rem;
-    margin-top: 5rem;
-    max-width: 400px;
-    color: var(--color-watch-table-row-text); }
-
-#heartpath {
-  transition: all ease 0.3s !important; }
-  #heartpath:hover {
-    fill: #ff0000 !important;
-    transition: all ease 0.3s !important; }
-
 body {
   color: var(--color-text);
-  background: var(--color-background-page);
-  font-family: Helvetica Neue, Helvetica, Lucida Grande, Arial, Ubuntu, Cantarell, Fira Sans, sans-serif; }
+  background: var(--color-background-page); }
 
 .visually-hidden {
   clip: rect(0 0 0 0);
@@ -423,6 +376,9 @@ a.github-link {
   a.github-link:hover {
     color: var(--color-icon-github-hover); }
 
+#toggle-search {
+  width: 2rem; }
+
 #search-q {
   opacity: 0;
   -webkit-transition: all .9s ease;

changedetectionio/store.py

@@ -360,8 +360,6 @@ 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

@@ -8,10 +8,10 @@
     <title>Change Detection{{extra_title}}</title>
     <link rel="alternate" type="application/rss+xml" title="Changedetection.io » Feed{% if active_tag %}- {{active_tag}}{% endif %}" href="{{ url_for('rss', tag=active_tag , token=app_rss_token)}}" >
     <link rel="stylesheet" href="{{url_for('static_content', group='styles', filename='pure-min.css')}}" >
-    <link rel="stylesheet" href="{{url_for('static_content', group='styles', filename='styles.css')}}?v={{ get_css_version() }}" >
+    <link rel="stylesheet" href="{{url_for('static_content', group='styles', filename='styles.css')}}" >
     {% if extra_stylesheets %}
       {% for m in extra_stylesheets %}
-        <link rel="stylesheet" href="{{ m }}?ver={{ get_css_version() }}" >
+        <link rel="stylesheet" href="{{ m }}?ver=1000" >
       {% endfor %}
     {% endif %}
 
@@ -85,7 +85,6 @@
               <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">
@@ -96,7 +95,6 @@
               </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>
@@ -108,20 +106,6 @@
               </span>
             </button>
           </li>
-          <li class="pure-menu-item" id="heart-us">
-                <svg
-                   fill="#ff0000"
-                   class="bi bi-heart"
-                   preserveAspectRatio="xMidYMid meet"
-                   viewBox="0 0 16.9 16.1"
-                   id="svg-heart"
-                   xmlns="http://www.w3.org/2000/svg"
-                   xmlns:svg="http://www.w3.org/2000/svg">
-                  <path id="heartpath" d="M 5.338316,0.50302766 C 0.71136983,0.50647126 -3.9576371,7.2707777 8.5004254,15.503028 23.833425,5.3700277 13.220206,-2.5384409 8.6762066,1.6475589 c -0.060791,0.054322 -0.11943,0.1110064 -0.1757812,0.1699219 -0.057,-0.059 -0.1157813,-0.116875 -0.1757812,-0.171875 C 7.4724566,0.86129334 6.4060729,0.50223298 5.338316,0.50302766 Z"
-                     style="fill:var(--color-background);fill-opacity:1;stroke:#ff0000;stroke-opacity:1" />
-                </svg>
-
-          </li>
           <li class="pure-menu-item">
             <a class="github-link" href="https://github.com/dgtlmoon/changedetection.io">
               {% include "svgs/github.svg" %}
@@ -145,44 +129,7 @@
       <div class="sticky-tab" id="right-sticky">{{ right_sticky }}</div>
     {% endif %}
     <section class="content">
-        <div id="overlay">
-            <div class="content">
-                <strong>changedetection.io needs your support!</strong><br>
-                <p>
-                    You can help us by supporting changedetection.io on these platforms;
-                </p>
-                <p>
-                <ul>
-                    <li>
-                        <a href="https://alternativeto.net/software/changedetection-io/about/">Rate us at
-                        AlternativeTo.net</a>
-                    </li>
-                <li>
-                    <a href="https://github.com/dgtlmoon/changedetection.io">Star us on GitHub</a>
-                </li>
-                <li>
-                    <a href="https://twitter.com/change_det_io">Follow us at Twitter/X</a>
-                </li>
-                <li>
-                    <a href="https://www.linkedin.com/company/changedetection-io">Check us out on LinkedIn</a>
-                </li>
-                <li>
-                    And tell your friends and colleagues :)
-                </li>
-                </ul>
-                </p>
-                <p>
-                    The more popular changedetection.io is, the more time we can dedicate to adding amazing features!
-                </p>
-                <p>
-                    Many thanks :)<br>
-                </p>
-                <p>
-                    <i>changedetection.io team</i>
-                </p>
-            </div>
-        </div>
-        <header>
+      <header>
         {% block header %}{% endblock %}
       </header>
 

changedetectionio/templates/edit.html

@@ -455,15 +455,15 @@ 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/templates/import.html

@@ -8,12 +8,11 @@
         <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" action="{{url_for('import_page')}}" method="POST" enctype="multipart/form-data">
+        <form class="pure-form pure-form-aligned" action="{{url_for('import_page')}}" method="POST">
             <input type="hidden" name="csrf_token" value="{{ csrf_token() }}">
             <div class="tab-pane-inner" id="url-list">
                     <legend>
@@ -80,42 +79,6 @@
 " 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/svgs/github.svg

@@ -1,6 +1,3 @@
-<svg class="octicon octicon-mark-github v-align-middle"  viewbox="0 0 16 16" version="1.1" aria-hidden="true">
-    <path
-     fill-rule="evenodd"
-     d="M 8,0 C 3.58,0 0,3.58 0,8 c 0,3.54 2.29,6.53 5.47,7.59 0.4,0.07 0.55,-0.17 0.55,-0.38 0,-0.19 -0.01,-0.82 -0.01,-1.49 C 4,14.09 3.48,13.23 3.32,12.78 3.23,12.55 2.84,11.84 2.5,11.65 2.22,11.5 1.82,11.13 2.49,11.12 3.12,11.11 3.57,11.7 3.72,11.94 4.44,13.15 5.59,12.81 6.05,12.6 6.12,12.08 6.33,11.73 6.56,11.53 4.78,11.33 2.92,10.64 2.92,7.58 2.92,6.71 3.23,5.99 3.74,5.43 3.66,5.23 3.38,4.41 3.82,3.31 c 0,0 0.67,-0.21 2.2,0.82 0.64,-0.18 1.32,-0.27 2,-0.27 0.68,0 1.36,0.09 2,0.27 1.53,-1.04 2.2,-0.82 2.2,-0.82 0.44,1.1 0.16,1.92 0.08,2.12 0.51,0.56 0.82,1.27 0.82,2.15 0,3.07 -1.87,3.75 -3.65,3.95 0.29,0.25 0.54,0.73 0.54,1.48 0,1.07 -0.01,1.93 -0.01,2.2 0,0.21 0.15,0.46 0.55,0.38 A 8.013,8.013 0 0 0 16,8 C 16,3.58 12.42,0 8,0 Z"
-     id="path2" />
+<svg class="octicon octicon-mark-github v-align-middle" height="32" viewbox="0 0 16 16" version="1.1" width="32" aria-hidden="true">
+  <path fill-rule="evenodd" d="M8 0C3.58 0 0 3.58 0 8c0 3.54 2.29 6.53 5.47 7.59.4.07.55-.17.55-.38 0-.19-.01-.82-.01-1.49-2.01.37-2.53-.49-2.69-.94-.09-.23-.48-.94-.82-1.13-.28-.15-.68-.52-.01-.53.63-.01 1.08.58 1.23.82.72 1.21 1.87.87 2.33.66.07-.52.28-.87.51-1.07-1.78-.2-3.64-.89-3.64-3.95 0-.87.31-1.59.82-2.15-.08-.2-.36-1.02.08-2.12 0 0 .67-.21 2.2.82.64-.18 1.32-.27 2-.27.68 0 1.36.09 2 .27 1.53-1.04 2.2-.82 2.2-.82.44 1.1.16 1.92.08 2.12.51.56.82 1.27.82 2.15 0 3.07-1.87 3.75-3.65 3.95.29.25.54.73.54 1.48 0 1.07-.01 1.93-.01 2.2 0 .21.15.46.55.38A8.013 8.013 0 0016 8c0-4.42-3.58-8-8-8z"></path>
 </svg>

changedetectionio/tests/test_access_control.py

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

changedetectionio/tests/test_extract_regex.py

@@ -202,35 +202,3 @@ 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

@@ -1,19 +1,16 @@
 #!/usr/bin/python3
-import io
-import os
+
 import time
 
 from flask import url_for
 
-from .util import live_server_setup, wait_for_all_checks
-
-
+from .util import live_server_setup
 def test_setup(client, live_server):
     live_server_setup(live_server)
 
 def test_import(client, live_server):
     # Give the endpoint time to spin up
-    wait_for_all_checks(client)
+    time.sleep(1)
 
     res = client.post(
         url_for("import_page"),
@@ -122,97 +119,3 @@ 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/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"
@@ -54,13 +53,6 @@ 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(
@@ -68,75 +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

@@ -66,12 +66,25 @@ 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: ghcr.io/browserless/chrome:latest
+#        image: browserless/chrome
 #        restart: unless-stopped
 #        environment:
 #            - SCREEN_WIDTH=1920
@@ -88,23 +101,6 @@ 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

@@ -1,13 +1,12 @@
-eventlet>=0.33.3 # related to dnspython fixes
+eventlet>=0.31.0
 feedgen~=0.9
 flask-compress
-# 0.6.3 included compatibility fix for werkzeug 3.x (2.x had deprecation of url handlers)
-flask-login>=0.6.3
+flask-login~=0.5
 flask-paginate
 flask_expects_json~=1.7
 flask_restful
-flask_wtf~=1.2
-flask~=2.3
+flask_wtf
+flask~=2.0
 inscriptis~=2.2
 pytz
 timeago~=1.0
@@ -25,7 +24,11 @@ chardet>2.3.0
 wtforms~=3.0
 jsonpath-ng~=1.5.3
 
-dnspython~=2.4 # related to eventlet fixes
+
+# dnspython 2.3.0 is not compatible with eventlet
+# * https://github.com/eventlet/eventlet/issues/781
+# * https://datastax-oss.atlassian.net/browse/PYTHON-1320
+dnspython<2.3.0
 
 # jq not available on Windows so must be installed manually
 
@@ -46,14 +49,18 @@ beautifulsoup4
 # XPath filtering, lxml is required by bs4 anyway, but put it here to be safe.
 lxml
 
-selenium~=4.14.0
+# 3.141 was missing socksVersion, 3.150 was not in pypi, so we try 4.1.0
+selenium~=4.1.0
 
-werkzeug~=3.0
+# 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
 
 # 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 == "darwin"