Disable version check when pytest is running

.github/test/Dockerfile-alpine

@@ -1,31 +0,0 @@
-# Taken from https://github.com/linuxserver/docker-changedetection.io/blob/main/Dockerfile
-# Test that we can still build on Alpine (musl modified libc https://musl.libc.org/)
-# Some packages wont install via pypi because they dont have a wheel available under this architecture.
-
-FROM ghcr.io/linuxserver/baseimage-alpine:3.16
-ENV PYTHONUNBUFFERED=1
-
-COPY requirements.txt /requirements.txt
-
-RUN \
-  apk add --update --no-cache --virtual=build-dependencies \
-    cargo \
-    g++ \
-    gcc \
-    libc-dev \
-    libffi-dev \
-    libxslt-dev \
-    make \
-    openssl-dev \
-    py3-wheel \
-    python3-dev \
-    zlib-dev && \
-  apk add --update --no-cache \
-    libxslt \
-    python3 \
-    py3-pip && \
-  echo "**** pip3 install test of changedetection.io ****" && \
-  pip3 install -U pip wheel setuptools && \
-  pip3 install -U --no-cache-dir --find-links https://wheel-index.linuxserver.io/alpine-3.16/ -r /requirements.txt && \
-  apk del --purge \
-    build-dependencies

.github/workflows/test-container-build.yml

@@ -43,16 +43,6 @@ jobs:
             version: latest
             driver-opts: image=moby/buildkit:master
 
-        # https://github.com/dgtlmoon/changedetection.io/pull/1067
-        # Check we can still build under alpine/musl
-        - name: Test that the docker containers can build (musl via alpine check)
-          id: docker_build_musl
-          uses: docker/build-push-action@v2
-          with:
-            context: ./
-            file: ./.github/test/Dockerfile-alpine
-            platforms: linux/amd64,linux/arm64
-
         - name: Test that the docker containers can build
           id: docker_build
           uses: docker/build-push-action@v2
@@ -63,4 +53,3 @@ jobs:
             platforms: linux/arm/v7,linux/arm/v6,linux/amd64,linux/arm64,
             cache-from: type=local,src=/tmp/.buildx-cache
             cache-to: type=local,dest=/tmp/.buildx-cache
-

Dockerfile

@@ -9,7 +9,6 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
     gcc \
     libc-dev \
     libffi-dev \
-    libjpeg-dev \
     libssl-dev \
     libxslt-dev \
     make \
@@ -22,11 +21,6 @@ COPY requirements.txt /requirements.txt
 
 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~=1.26 \
-    || echo "WARN: Failed to install Playwright. The application can still run, but the Playwright option will be disabled."
 
 # Final image stage
 FROM python:3.8-slim
@@ -37,14 +31,13 @@ ARG CRYPTOGRAPHY_DONT_BUILD_RUST=1
 
 # Re #93, #73, excluding rustc (adds another 430Mb~)
 RUN apt-get update && apt-get install -y --no-install-recommends \
-    g++ \
+    libssl-dev \
+    libffi-dev \
     gcc \
     libc-dev \
-    libffi-dev \
-    libjpeg-dev \
-    libssl-dev \
     libxslt-dev \
-    zlib1g-dev
+    zlib1g-dev \
+    g++
 
 # https://stackoverflow.com/questions/58701233/docker-logs-erroneously-appears-empty-until-container-stops
 ENV PYTHONUNBUFFERED=1

MANIFEST.in

@@ -3,7 +3,6 @@ recursive-include changedetectionio/templates *
 recursive-include changedetectionio/static *
 recursive-include changedetectionio/model *
 recursive-include changedetectionio/tests *
-recursive-include changedetectionio/res *
 include changedetection.py
 global-exclude *.pyc
 global-exclude node_modules

README.md

@@ -1,7 +1,6 @@
 ## Web Site Change Detection, Monitoring and Notification.
 
-_Live your data-life pro-actively, Detect website changes and perform meaningful actions, trigger notifications via Discord, Email, Slack, Telegram, API calls and many more._
-
+Live your data-life pro-actively, track website content changes and receive notifications via Discord, Email, Slack, Telegram and 70+ more
 
 [<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot.png" style="max-width:100%;" alt="Self-hosted web page change monitoring"  title="Self-hosted web page change monitoring"  />](https://lemonade.changedetection.io/start?src=github)
 
@@ -9,6 +8,8 @@ _Live your data-life pro-actively, Detect website changes and perform meaningful
 
 ![changedetection.io](https://github.com/dgtlmoon/changedetection.io/actions/workflows/test-only.yml/badge.svg?branch=master)
 
+Know when important content changes, we support notifications via Discord, Telegram, Home-Assistant, Slack, Email and 70+ more
+
 [**Don't have time? Let us host it for you! try our $6.99/month subscription - use our proxies and support!**](https://lemonade.changedetection.io/start) , _half the price of other website change monitoring services and comes with unlimited watches & checks!_
 
 - Chrome browser included.
@@ -53,7 +54,6 @@ _Need an actual Chrome runner with Javascript support? We support fetching via W
 - Override Request Headers, Specify `POST` or `GET` and other methods
 - Use the "Visual Selector" to help target specific elements
 - Configurable [proxy per watch](https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration)
-- Send a screenshot with the notification when a change is detected in the web page
 
 We [recommend and use Bright Data](https://brightdata.grsm.io/n0r16zf7eivq) global proxy services, Bright Data will match any first deposit up to $100 using our signup link.
 

changedetectionio/__init__.py

@@ -33,7 +33,7 @@ from flask_wtf import CSRFProtect
 from changedetectionio import html_tools
 from changedetectionio.api import api_v1
 
-__version__ = '0.39.21.1'
+__version__ = '0.39.20.4'
 
 datastore = None
 
@@ -599,7 +599,7 @@ def changedetection_app(config=None, datastore_o=None):
                     extra_update_obj['previous_md5'] = get_current_checksum_include_ignore_text(uuid=uuid)
 
             # Reset the previous_md5 so we process a new snapshot including stripping ignore text.
-            if form.include_filters.data != datastore.data['watching'][uuid].get('include_filters', []):
+            if form.css_filter.data.strip() != datastore.data['watching'][uuid]['css_filter']:
                 if len(datastore.data['watching'][uuid].history):
                     extra_update_obj['previous_md5'] = get_current_checksum_include_ignore_text(uuid=uuid)
 
@@ -644,18 +644,12 @@ def changedetection_app(config=None, datastore_o=None):
             except ModuleNotFoundError:
                 jq_support = False
 
-            watch = datastore.data['watching'].get(uuid)
-            system_uses_webdriver = datastore.data['settings']['application']['fetch_backend'] == 'html_webdriver'
-            is_html_webdriver = True if watch.get('fetch_backend') == 'html_webdriver' or (
-                    watch.get('fetch_backend', None) is None and system_uses_webdriver) else False
-
             output = render_template("edit.html",
                                      current_base_url=datastore.data['settings']['application']['base_url'],
                                      emailprefix=os.getenv('NOTIFICATION_MAIL_BUTTON_PREFIX', False),
                                      form=form,
                                      has_default_notification_urls=True if len(datastore.data['settings']['application']['notification_urls']) else False,
                                      has_empty_checktime=using_default_check_time,
-                                     is_html_webdriver=is_html_webdriver,
                                      jq_support=jq_support,
                                      playwright_enabled=os.getenv('PLAYWRIGHT_DRIVER_URL', False),
                                      settings_application=datastore.data['settings']['application'],
@@ -663,7 +657,7 @@ def changedetection_app(config=None, datastore_o=None):
                                      uuid=uuid,
                                      visualselector_data_is_ready=visualselector_data_is_ready,
                                      visualselector_enabled=visualselector_enabled,
-                                     watch=watch
+                                     watch=datastore.data['watching'][uuid],
                                      )
 
         return output
@@ -1374,7 +1368,7 @@ def notification_runner():
                 # UUID wont be present when we submit a 'test' from the global settings
                 if 'uuid' in n_object:
                     datastore.update_watch(uuid=n_object['uuid'],
-                                           update_obj={'last_notification_error': "Notification error detected, goto notification log."})
+                                           update_obj={'last_notification_error': "Notification error detected, please see logs."})
 
                 log_lines = str(e).splitlines()
                 notification_debug_log += log_lines

changedetectionio/changedetection.py

@@ -2,20 +2,19 @@
 
 # Launch as a eventlet.wsgi server instance.
 
-from distutils.util import strtobool
-import eventlet
-import eventlet.wsgi
 import getopt
 import os
 import signal
 import sys
 
+import eventlet
+import eventlet.wsgi
 from . import store, changedetection_app, content_fetcher
 from . import __version__
 
 # Only global so we can access it in the signal handler
-app = None
 datastore = None
+app = None
 
 def sigterm_handler(_signo, _stack_frame):
     global app
@@ -103,13 +102,12 @@ def main():
                     has_password=datastore.data['settings']['application']['password'] != False
                     )
 
-    # Monitored websites will not receive a Referer header when a user clicks on an outgoing link.
-    # @Note: Incompatible with password login (and maybe other features) for now, submit a PR!
+    # Monitored websites will not receive a Referer header
+    # when a user clicks on an outgoing link.
     @app.after_request
     def hide_referrer(response):
-        if strtobool(os.getenv("HIDE_REFERER", 'false')):
+        if os.getenv("HIDE_REFERER", False):
             response.headers["Referrer-Policy"] = "no-referrer"
-
         return response
 
     # Proxy sub-directory support

changedetectionio/content_fetcher.py

@@ -1,11 +1,11 @@
-from abc import abstractmethod
-from pkg_resources import resource_string
+from abc import ABC, abstractmethod
 import chardet
 import json
 import os
 import requests
-import sys
 import time
+import sys
+
 
 class Non200ErrorCodeReceived(Exception):
     def __init__(self, status_code, url, screenshot=None, xpath_data=None, page_html=None):
@@ -73,8 +73,131 @@ class Fetcher():
 
     fetcher_description = "No description"
     webdriver_js_execute_code = None
-    xpath_element_js = ""
+    xpath_element_js = """               
+                // Include the getXpath script directly, easier than fetching
+                !function(e,n){"object"==typeof exports&&"undefined"!=typeof module?module.exports=n():"function"==typeof define&&define.amd?define(n):(e=e||self).getXPath=n()}(this,function(){return function(e){var n=e;if(n&&n.id)return'//*[@id="'+n.id+'"]';for(var o=[];n&&Node.ELEMENT_NODE===n.nodeType;){for(var i=0,r=!1,d=n.previousSibling;d;)d.nodeType!==Node.DOCUMENT_TYPE_NODE&&d.nodeName===n.nodeName&&i++,d=d.previousSibling;for(d=n.nextSibling;d;){if(d.nodeName===n.nodeName){r=!0;break}d=d.nextSibling}o.push((n.prefix?n.prefix+":":"")+n.localName+(i||r?"["+(i+1)+"]":"")),n=n.parentNode}return o.length?"/"+o.reverse().join("/"):""}});
 
+
+                const findUpTag = (el) => {
+                  let r = el
+                  chained_css = [];
+                  depth=0;
+            
+                // Strategy 1: Keep going up until we hit an ID tag, imagine it's like  #list-widget div h4
+                  while (r.parentNode) {
+                    if(depth==5) {
+                      break;
+                    }
+                    if('' !==r.id) {
+                      chained_css.unshift("#"+CSS.escape(r.id));
+                      final_selector= chained_css.join(' > ');
+                      // Be sure theres only one, some sites have multiples of the same ID tag :-(
+                      if (window.document.querySelectorAll(final_selector).length ==1 ) {
+                        return final_selector;
+                        }
+                      return null;
+                    } else {
+                      chained_css.unshift(r.tagName.toLowerCase());
+                    }
+                    r=r.parentNode;
+                    depth+=1;
+                  }
+                  return null;
+                }
+
+
+                // @todo - if it's SVG or IMG, go into image diff mode
+                var elements = window.document.querySelectorAll("div,span,form,table,tbody,tr,td,a,p,ul,li,h1,h2,h3,h4, header, footer, section, article, aside, details, main, nav, section, summary");
+                var size_pos=[];
+                // after page fetch, inject this JS
+                // build a map of all elements and their positions (maybe that only include text?)
+                var bbox;
+                for (var i = 0; i < elements.length; i++) {   
+                 bbox = elements[i].getBoundingClientRect();
+
+                 // forget really small ones
+                 if (bbox['width'] <20 && bbox['height'] < 20 ) {
+                   continue;
+                 }
+
+                 // @todo the getXpath kind of sucks, it doesnt know when there is for example just one ID sometimes
+                 // it should not traverse when we know we can anchor off just an ID one level up etc..
+                 // maybe, get current class or id, keep traversing up looking for only class or id until there is just one match 
+
+                 // 1st primitive - if it has class, try joining it all and select, if theres only one.. well thats us.
+                 xpath_result=false;
+                 
+                 try {
+                   var d= findUpTag(elements[i]);
+                   if (d) {
+                     xpath_result =d;
+                   }                
+                 } catch (e) {
+                   console.log(e);
+                 }
+                 
+                 // You could swap it and default to getXpath and then try the smarter one
+                 // default back to the less intelligent one
+                 if (!xpath_result) {
+                    try {
+                       // I've seen on FB and eBay that this doesnt work
+                       // ReferenceError: getXPath is not defined at eval (eval at evaluate (:152:29), <anonymous>:67:20) at UtilityScript.evaluate (<anonymous>:159:18) at UtilityScript.<anonymous> (<anonymous>:1:44)
+                       xpath_result = getXPath(elements[i]);
+                     } catch (e) {
+                       console.log(e);
+                       continue;
+                     }            
+                 }
+                 
+                 if(window.getComputedStyle(elements[i]).visibility === "hidden") {
+                   continue;
+                 }
+
+                 size_pos.push({
+                   xpath: xpath_result,
+                   width: Math.round(bbox['width']), 
+                   height: Math.round(bbox['height']), 
+                   left: Math.floor(bbox['left']), 
+                   top: Math.floor(bbox['top']), 
+                   childCount: elements[i].childElementCount
+                 });                 
+                }
+
+
+                // inject the current one set in the css_filter, which may be a CSS rule
+                // used for displaying the current one in VisualSelector, where its not one we generated.
+                if (css_filter.length) {
+                   q=false;                   
+                   try {
+                       // is it xpath?
+                       if (css_filter.startsWith('/') || css_filter.startsWith('xpath:')) {
+                         q=document.evaluate(css_filter.replace('xpath:',''), document, null, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue;
+                       } else {
+                         q=document.querySelector(css_filter);
+                       }                       
+                   } catch (e) {
+                    // Maybe catch DOMException and alert? 
+                     console.log(e);                       
+                   }
+                   bbox=false;
+                   if(q) {
+                     bbox = q.getBoundingClientRect();
+                   }
+                                   
+                   if (bbox && bbox['width'] >0 && bbox['height']>0) {                       
+                       size_pos.push({
+                           xpath: css_filter,
+                           width: bbox['width'], 
+                           height: bbox['height'],
+                           left: bbox['left'],
+                           top: bbox['top'],
+                           childCount: q.childElementCount
+                         });
+                     }
+                }
+                // Window.width required for proper scaling in the frontend
+                return {'size_pos':size_pos, 'browser_width': window.innerWidth};
+    """
     xpath_data = None
 
     # Will be needed in the future by the VisualSelector, always get this where possible.
@@ -85,10 +208,6 @@ class Fetcher():
     # Time ONTOP of the system defined env minimum time
     render_extract_delay = 0
 
-    def __init__(self):
-        # The code that scrapes elements and makes a list of elements/size/position to click on in the VisualSelector
-        self.xpath_element_js = resource_string(__name__, "res/xpath_element_scraper.js").decode('utf-8')
-
     @abstractmethod
     def get_error(self):
         return self.error
@@ -101,7 +220,7 @@ class Fetcher():
             request_body,
             request_method,
             ignore_status_codes=False,
-            current_include_filters=None):
+            current_css_filter=None):
         # Should set self.error, self.status_code and self.content
         pass
 
@@ -154,7 +273,7 @@ class base_html_playwright(Fetcher):
     proxy = None
 
     def __init__(self, proxy_override=None):
-        super().__init__()
+
         # .strip('"') is going to save someone a lot of time when they accidently wrap the env value
         self.browser_type = os.getenv("PLAYWRIGHT_BROWSER_TYPE", 'chromium').strip('"')
         self.command_executor = os.getenv(
@@ -191,7 +310,7 @@ class base_html_playwright(Fetcher):
             request_body,
             request_method,
             ignore_status_codes=False,
-            current_include_filters=None):
+            current_css_filter=None):
 
         from playwright.sync_api import sync_playwright
         import playwright._impl._api_types
@@ -294,10 +413,10 @@ class base_html_playwright(Fetcher):
             self.status_code = response.status
             self.headers = response.all_headers()
 
-            if current_include_filters is not None:
-                page.evaluate("var include_filters={}".format(json.dumps(current_include_filters)))
+            if current_css_filter is not None:
+                page.evaluate("var css_filter={}".format(json.dumps(current_css_filter)))
             else:
-                page.evaluate("var include_filters=''")
+                page.evaluate("var css_filter=''")
 
             self.xpath_data = page.evaluate("async () => {" + self.xpath_element_js + "}")
 
@@ -346,7 +465,6 @@ class base_html_webdriver(Fetcher):
     proxy = None
 
     def __init__(self, proxy_override=None):
-        super().__init__()
         from selenium.webdriver.common.proxy import Proxy as SeleniumProxy
 
         # .strip('"') is going to save someone a lot of time when they accidently wrap the env value
@@ -379,7 +497,7 @@ class base_html_webdriver(Fetcher):
             request_body,
             request_method,
             ignore_status_codes=False,
-            current_include_filters=None):
+            current_css_filter=None):
 
         from selenium import webdriver
         from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
@@ -455,7 +573,7 @@ class html_requests(Fetcher):
             request_body,
             request_method,
             ignore_status_codes=False,
-            current_include_filters=None):
+            current_css_filter=None):
 
         # Make requests use a more modern looking user-agent
         if not 'User-Agent' in request_headers:

changedetectionio/fetch_site_status.py

@@ -10,11 +10,6 @@ from changedetectionio import content_fetcher, html_tools
 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 
 
-class FilterNotFoundInResponse(ValueError):
-    def __init__(self, msg):
-        ValueError.__init__(self, msg)
-
-
 # Some common stuff here that can be moved to a base class
 # (set_proxy_from_list)
 class perform_site_check():
@@ -38,20 +33,18 @@ class perform_site_check():
 
         return regex
 
+
     def run(self, uuid):
-        from copy import deepcopy
         changed_detected = False
         screenshot = False  # as bytes
         stripped_text_from_html = ""
 
-        # DeepCopy so we can be sure we don't accidently change anything by reference
-        watch = deepcopy(self.datastore.data['watching'].get(uuid))
-
+        watch = self.datastore.data['watching'].get(uuid)
         if not watch:
             return
 
         # Protect against file:// access
-        if re.search(r'^file', watch.get('url', ''), re.IGNORECASE) and not os.getenv('ALLOW_FILE_URI', False):
+        if re.search(r'^file', watch['url'], re.IGNORECASE) and not os.getenv('ALLOW_FILE_URI', False):
             raise Exception(
                 "file:// type access is denied for security reasons."
             )
@@ -59,10 +52,10 @@ class perform_site_check():
         # Unset any existing notification error
         update_obj = {'last_notification_error': False, 'last_error': False}
 
-        extra_headers = watch.get('headers', [])
+        extra_headers =self.datastore.data['watching'][uuid].get('headers')
 
         # Tweak the base config with the per-watch ones
-        request_headers = deepcopy(self.datastore.data['settings']['headers'])
+        request_headers = self.datastore.data['settings']['headers'].copy()
         request_headers.update(extra_headers)
 
         # https://github.com/psf/requests/issues/4525
@@ -86,7 +79,7 @@ class perform_site_check():
             is_source = True
 
         # Pluggable content fetcher
-        prefer_backend = watch.get('fetch_backend')
+        prefer_backend = watch['fetch_backend']
         if hasattr(content_fetcher, prefer_backend):
             klass = getattr(content_fetcher, prefer_backend)
         else:
@@ -97,21 +90,21 @@ class perform_site_check():
         proxy_url = None
         if proxy_id:
             proxy_url = self.datastore.proxy_list.get(proxy_id).get('url')
-            print("UUID {} Using proxy {}".format(uuid, proxy_url))
+            print ("UUID {} Using proxy {}".format(uuid, proxy_url))
 
         fetcher = klass(proxy_override=proxy_url)
 
         # Configurable per-watch or global extra delay before extracting text (for webDriver types)
         system_webdriver_delay = self.datastore.data['settings']['application'].get('webdriver_delay', None)
         if watch['webdriver_delay'] is not None:
-            fetcher.render_extract_delay = watch.get('webdriver_delay')
+            fetcher.render_extract_delay = watch['webdriver_delay']
         elif system_webdriver_delay is not None:
             fetcher.render_extract_delay = system_webdriver_delay
 
-        if watch.get('webdriver_js_execute_code') is not None and watch.get('webdriver_js_execute_code').strip():
-            fetcher.webdriver_js_execute_code = watch.get('webdriver_js_execute_code')
+        if watch['webdriver_js_execute_code'] is not None and watch['webdriver_js_execute_code'].strip():
+            fetcher.webdriver_js_execute_code = watch['webdriver_js_execute_code']
 
-        fetcher.run(url, timeout, request_headers, request_body, request_method, ignore_status_codes, watch.get('include_filters'))
+        fetcher.run(url, timeout, request_headers, request_body, request_method, ignore_status_codes, watch['css_filter'])
         fetcher.quit()
 
         self.screenshot = fetcher.screenshot
@@ -135,30 +128,28 @@ class perform_site_check():
             is_html = False
             is_json = False
 
-        include_filters_rule = watch.get('include_filters', [])
-        # include_filters_rule = watch['include_filters']
+        css_filter_rule = watch['css_filter']
         subtractive_selectors = watch.get(
             "subtractive_selectors", []
         ) + self.datastore.data["settings"]["application"].get(
             "global_subtractive_selectors", []
         )
 
-        has_filter_rule = include_filters_rule and len("".join(include_filters_rule).strip())
+        has_filter_rule = css_filter_rule and len(css_filter_rule.strip())
         has_subtractive_selectors = subtractive_selectors and len(subtractive_selectors[0].strip())
 
         if is_json and not has_filter_rule:
-            include_filters_rule.append("json:$")
+            css_filter_rule = "json:$"
             has_filter_rule = True
 
         if has_filter_rule:
             json_filter_prefixes = ['json:', 'jq:']
-            for filter in include_filters_rule:
-                if any(prefix in filter for prefix in json_filter_prefixes):
-                    stripped_text_from_html += html_tools.extract_json_as_string(content=fetcher.content, json_filter=filter)
-                    is_html = False
+            if any(prefix in css_filter_rule for prefix in json_filter_prefixes):
+                stripped_text_from_html = html_tools.extract_json_as_string(content=fetcher.content, json_filter=css_filter_rule)
+                is_html = False
 
         if is_html or is_source:
-
+            
             # CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text
             fetcher.content = html_tools.workarounds_for_obfuscations(fetcher.content)
             html_content = fetcher.content
@@ -170,36 +161,30 @@ class perform_site_check():
             else:
                 # Then we assume HTML
                 if has_filter_rule:
-                    html_content = ""
-                    for filter_rule in include_filters_rule:
-                        # For HTML/XML we offer xpath as an option, just start a regular xPath "/.."
-                        if filter_rule[0] == '/' or filter_rule.startswith('xpath:'):
-                            html_content += html_tools.xpath_filter(xpath_filter=filter_rule.replace('xpath:', ''),
-                                                                    html_content=fetcher.content,
-                                                                    append_pretty_line_formatting=not is_source)
-                        else:
-                            # CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text
-                            html_content += html_tools.include_filters(include_filters=filter_rule,
-                                                                       html_content=fetcher.content,
-                                                                       append_pretty_line_formatting=not is_source)
-
-                    if not html_content.strip():
-                        raise FilterNotFoundInResponse(include_filters_rule)
+                    # For HTML/XML we offer xpath as an option, just start a regular xPath "/.."
+                    if css_filter_rule[0] == '/' or css_filter_rule.startswith('xpath:'):
+                        html_content = html_tools.xpath_filter(xpath_filter=css_filter_rule.replace('xpath:', ''),
+                                                               html_content=fetcher.content)
+                    else:
+                        # CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text
+                        html_content = html_tools.css_filter(css_filter=css_filter_rule, html_content=fetcher.content)
 
                 if has_subtractive_selectors:
                     html_content = html_tools.element_removal(subtractive_selectors, html_content)
 
-                if is_source:
-                    stripped_text_from_html = html_content
-                else:
+                if not is_source:
                     # extract text
-                    do_anchor = self.datastore.data["settings"]["application"].get("render_anchor_tag_content", False)
                     stripped_text_from_html = \
                         html_tools.html_to_text(
                             html_content,
-                            render_anchor_tag_content=do_anchor
+                            render_anchor_tag_content=self.datastore.data["settings"][
+                                "application"].get(
+                                "render_anchor_tag_content", False)
                         )
 
+                elif is_source:
+                    stripped_text_from_html = html_content
+
         # Re #340 - return the content before the 'ignore text' was applied
         text_content_before_ignored_filter = stripped_text_from_html.encode('utf-8')
 
@@ -232,7 +217,7 @@ class perform_site_check():
 
                 for l in result:
                     if type(l) is tuple:
-                        # @todo - some formatter option default (between groups)
+                        #@todo - some formatter option default (between groups)
                         regex_matched_output += list(l) + [b'\n']
                     else:
                         # @todo - some formatter option default (between each ungrouped result)
@@ -246,6 +231,7 @@ class perform_site_check():
                 stripped_text_from_html = b''.join(regex_matched_output)
                 text_content_before_ignored_filter = stripped_text_from_html
 
+
         # Re #133 - if we should strip whitespaces from triggering the change detected comparison
         if self.datastore.data['settings']['application'].get('ignore_whitespace', False):
             fetched_md5 = hashlib.md5(stripped_text_from_html.translate(None, b'\r\n\t ')).hexdigest()
@@ -255,30 +241,29 @@ class perform_site_check():
         ############ Blocking rules, after checksum #################
         blocked = False
 
-        trigger_text = watch.get('trigger_text', [])
-        if len(trigger_text):
+        if len(watch['trigger_text']):
             # Assume blocked
             blocked = True
             # Filter and trigger works the same, so reuse it
             # It should return the line numbers that match
             result = html_tools.strip_ignore_text(content=str(stripped_text_from_html),
-                                                  wordlist=trigger_text,
+                                                  wordlist=watch['trigger_text'],
                                                   mode="line numbers")
             # Unblock if the trigger was found
             if result:
                 blocked = False
 
-        text_should_not_be_present = watch.get('text_should_not_be_present', [])
-        if len(text_should_not_be_present):
+
+        if len(watch['text_should_not_be_present']):
             # If anything matched, then we should block a change from happening
             result = html_tools.strip_ignore_text(content=str(stripped_text_from_html),
-                                                  wordlist=text_should_not_be_present,
+                                                  wordlist=watch['text_should_not_be_present'],
                                                   mode="line numbers")
             if result:
                 blocked = True
 
         # The main thing that all this at the moment comes down to :)
-        if watch.get('previous_md5') != fetched_md5:
+        if watch['previous_md5'] != fetched_md5:
             changed_detected = True
 
         # Looks like something changed, but did it match all the rules?
@@ -287,7 +272,7 @@ class perform_site_check():
 
         # Extract title as title
         if is_html:
-            if self.datastore.data['settings']['application'].get('extract_title_as_title') or watch['extract_title_as_title']:
+            if self.datastore.data['settings']['application']['extract_title_as_title'] or watch['extract_title_as_title']:
                 if not watch['title'] or not len(watch['title']):
                     update_obj['title'] = html_tools.extract_element(find='title', html_content=fetcher.content)
 

changedetectionio/forms.py

@@ -349,7 +349,7 @@ class watchForm(commonSettingsForm):
 
     time_between_check = FormField(TimeBetweenCheckForm)
 
-    include_filters = StringListField('CSS/JSONPath/JQ/XPath Filters', [ValidateCSSJSONXPATHInput()], default='')
+    css_filter = StringField('CSS/JSON/XPATH Filter', [ValidateCSSJSONXPATHInput()], default='')
 
     subtractive_selectors = StringListField('Remove elements', [ValidateCSSJSONXPATHInput(allow_xpath=False, allow_json=False)])
 
@@ -375,7 +375,6 @@ class watchForm(commonSettingsForm):
         'Send a notification when the filter can no longer be found on the page', default=False)
 
     notification_muted = BooleanField('Notifications Muted / Off', default=False)
-    notification_screenshot = BooleanField('Attach screenshot to notification (where possible)', default=False)
 
     def validate(self, **kwargs):
         if not super().validate():

changedetectionio/html_tools.py

@@ -7,30 +7,26 @@ from typing import List
 import json
 import re
 
-# HTML added to be sure each result matching a filter (.example) gets converted to a new line by Inscriptis
-TEXT_FILTER_LIST_LINE_SUFFIX = "<br/>"
+class FilterNotFoundInResponse(ValueError):
+    def __init__(self, msg):
+        ValueError.__init__(self, msg)
 
 class JSONNotFound(ValueError):
     def __init__(self, msg):
         ValueError.__init__(self, msg)
-        
+
+
 # Given a CSS Rule, and a blob of HTML, return the blob of HTML that matches
-def include_filters(include_filters, html_content, append_pretty_line_formatting=False):
+def css_filter(css_filter, html_content):
     soup = BeautifulSoup(html_content, "html.parser")
     html_block = ""
-    r = soup.select(include_filters, separator="")
+    r = soup.select(css_filter, separator="")
+    if len(html_content) > 0 and len(r) == 0:
+        raise FilterNotFoundInResponse(css_filter)
+    for item in r:
+        html_block += str(item)
 
-    for element in r:
-        # When there's more than 1 match, then add the suffix to separate each line
-        # And where the matched result doesn't include something that will cause Inscriptis to add a newline
-        # (This way each 'match' reliably has a new-line in the diff)
-        # Divs are converted to 4 whitespaces by inscriptis
-        if append_pretty_line_formatting and len(html_block) and not element.name in (['br', 'hr', 'div', 'p']):
-            html_block += TEXT_FILTER_LIST_LINE_SUFFIX
-
-        html_block += str(element)
-
-    return html_block
+    return html_block + "\n"
 
 def subtractive_css_selector(css_selector, html_content):
     soup = BeautifulSoup(html_content, "html.parser")
@@ -46,29 +42,25 @@ def element_removal(selectors: List[str], html_content):
 
 
 # Return str Utf-8 of matched rules
-def xpath_filter(xpath_filter, html_content, append_pretty_line_formatting=False):
+def xpath_filter(xpath_filter, html_content):
     from lxml import etree, html
 
     tree = html.fromstring(bytes(html_content, encoding='utf-8'))
     html_block = ""
 
     r = tree.xpath(xpath_filter.strip(), namespaces={'re': 'http://exslt.org/regular-expressions'})
+    if len(html_content) > 0 and len(r) == 0:
+        raise FilterNotFoundInResponse(xpath_filter)
+
     #@note: //title/text() wont work where <title>CDATA..
 
     for element in r:
-        # When there's more than 1 match, then add the suffix to separate each line
-        # And where the matched result doesn't include something that will cause Inscriptis to add a newline
-        # (This way each 'match' reliably has a new-line in the diff)
-        # Divs are converted to 4 whitespaces by inscriptis
-        if append_pretty_line_formatting and len(html_block) and (not hasattr( element, 'tag' ) or not element.tag in (['br', 'hr', 'div', 'p'])):
-            html_block += TEXT_FILTER_LIST_LINE_SUFFIX
-
         if type(element) == etree._ElementStringResult:
-            html_block += str(element)
+            html_block += str(element) + "<br/>"
         elif type(element) == etree._ElementUnicodeResult:
-            html_block += str(element)
+            html_block += str(element) + "<br/>"
         else:
-            html_block += etree.tostring(element, pretty_print=True).decode('utf-8')
+            html_block += etree.tostring(element, pretty_print=True).decode('utf-8') + "<br/>"
 
     return html_block
 

changedetectionio/importer.py

@@ -103,12 +103,12 @@ class import_distill_io_json(Importer):
                     pass
                 except IndexError:
                     pass
-                extras['include_filters'] = []
+
                 try:
+                    extras['css_filter'] = d_config['selections'][0]['frames'][0]['includes'][0]['expr']
                     if d_config['selections'][0]['frames'][0]['includes'][0]['type'] == 'xpath':
-                        extras['include_filters'].append('xpath:' + d_config['selections'][0]['frames'][0]['includes'][0]['expr'])
-                    else:
-                        extras['include_filters'].append(d_config['selections'][0]['frames'][0]['includes'][0]['expr'])
+                        extras['css_filter'] = 'xpath:' + extras['css_filter']
+
                 except KeyError:
                     pass
                 except IndexError:

changedetectionio/model/Watch.py

@@ -16,44 +16,42 @@ class model(dict):
     __newest_history_key = None
     __history_n=0
     __base_config = {
-            #'history': {},  # Dict of timestamp and output stripped filename (removed)
-            #'newest_history_key': 0, (removed, taken from history.txt index)
-            'body': None,
-            'check_unique_lines': False, # On change-detected, compare against all history if its something new
-            'check_count': 0,
-            'consecutive_filter_failures': 0, # Every time the CSS/xPath filter cannot be located, reset when all is fine.
-            'extract_text': [],  # Extract text by regex after filters
-            'extract_title_as_title': False,
-            'fetch_backend': None,
-            'filter_failure_notification_send': strtobool(os.getenv('FILTER_FAILURE_NOTIFICATION_SEND_DEFAULT', 'True')),
-            'headers': {},  # Extra headers to send
-            'ignore_text': [],  # List of text to ignore when calculating the comparison checksum
-            'include_filters': [],
+            'url': None,
+            'tag': None,
             'last_checked': 0,
-            'last_error': False,
+            'paused': False,
             'last_viewed': 0,  # history key value of the last viewed via the [diff] link
+            #'newest_history_key': 0,
+            'title': None,
+            'previous_md5': False,
+            'uuid': str(uuid.uuid4()),
+            'headers': {},  # Extra headers to send
+            'body': None,
             'method': 'GET',
-             # Custom notification content
+            #'history': {},  # Dict of timestamp and output stripped filename
+            'ignore_text': [],  # List of text to ignore when calculating the comparison checksum
+            # Custom notification content
+            'notification_urls': [],  # List of URLs to add to the notification Queue (Usually AppRise)
+            'notification_title': None,
             'notification_body': None,
             'notification_format': default_notification_format_for_watch,
             'notification_muted': False,
-            'notification_title': None,
-            'notification_screenshot': False, # Include the latest screenshot if available and supported by the apprise URL
-            'notification_urls': [],  # List of URLs to add to the notification Queue (Usually AppRise)
-            'paused': False,
-            'previous_md5': False,
-            'proxy': None, # Preferred proxy connection
+            'css_filter': '',
+            'last_error': False,
+            'extract_text': [],  # Extract text by regex after filters
             'subtractive_selectors': [],
-            'tag': None,
+            'trigger_text': [],  # List of text or regex to wait for until a change is detected
             'text_should_not_be_present': [], # Text that should not present
+            'fetch_backend': None,
+            'filter_failure_notification_send': strtobool(os.getenv('FILTER_FAILURE_NOTIFICATION_SEND_DEFAULT', 'True')),
+            'consecutive_filter_failures': 0, # Every time the CSS/xPath filter cannot be located, reset when all is fine.
+            'extract_title_as_title': False,
+            'check_unique_lines': False, # On change-detected, compare against all history if its something new
+            'proxy': None, # Preferred proxy connection
             # Re #110, so then if this is set to None, we know to use the default value instead
             # Requires setting to None on submit if it's the same as the default
             # Should be all None by default, so we use the system default in this case.
             'time_between_check': {'weeks': None, 'days': None, 'hours': None, 'minutes': None, 'seconds': None},
-            'title': None,
-            'trigger_text': [],  # List of text or regex to wait for until a change is detected
-            'url': None,
-            'uuid': str(uuid.uuid4()),
             'webdriver_delay': None,
             'webdriver_js_execute_code': None, # Run before change-detection
         }
@@ -248,28 +246,7 @@ class model(dict):
         if os.path.isfile(fname):
             return fname
 
-        # False is not an option for AppRise, must be type None
-        return None
-
-    def get_screenshot_as_jpeg(self):
-        """Best used in notifications due to its smaller size"""
-        png_fname = os.path.join(self.watch_data_dir, "last-screenshot.png")
-        jpg_fname = os.path.join(self.watch_data_dir, "last-screenshot.jpg")
-
-        if os.path.isfile(jpg_fname):
-            return jpg_fname
-
-        if os.path.isfile(png_fname) and not os.path.isfile(jpg_fname):
-            # Doesnt exist, so create the JPEG from the PNG
-            from PIL import Image
-            im1 = Image.open(png_fname)
-            im1.convert('RGB').save(jpg_fname, quality=int(os.getenv("NOTIFICATION_SCREENSHOT_JPG_QUALITY", 75)))
-            return jpg_fname
-
-
-        # False is not an option for AppRise, must be type None
-        return None
-
+        return False
 
     def __get_file_ctime(self, filename):
         fname = os.path.join(self.watch_data_dir, filename)

changedetectionio/notification.py

@@ -101,10 +101,7 @@ def process_notification(n_object, datastore):
                 apobj.notify(
                     title=n_title,
                     body=n_body,
-                    body_format=n_format,
-                    # False is not an option for AppRise, must be type None
-                    attach=n_object.get('screenshot', None)
-                )
+                    body_format=n_format)
 
                 apobj.clear()
 

changedetectionio/res/xpath_element_scraper.js

@@ -1,154 +0,0 @@
-// Include the getXpath script directly, easier than fetching
-!function (e, n) {
-    "object" == typeof exports && "undefined" != typeof module ? module.exports = n() : "function" == typeof define && define.amd ? define(n) : (e = e || self).getXPath = n()
-}(this, function () {
-    return function (e) {
-        var n = e;
-        if (n && n.id) return '//*[@id="' + n.id + '"]';
-        for (var o = []; n && Node.ELEMENT_NODE === n.nodeType;) {
-            for (var i = 0, r = !1, d = n.previousSibling; d;) d.nodeType !== Node.DOCUMENT_TYPE_NODE && d.nodeName === n.nodeName && i++, d = d.previousSibling;
-            for (d = n.nextSibling; d;) {
-                if (d.nodeName === n.nodeName) {
-                    r = !0;
-                    break
-                }
-                d = d.nextSibling
-            }
-            o.push((n.prefix ? n.prefix + ":" : "") + n.localName + (i || r ? "[" + (i + 1) + "]" : "")), n = n.parentNode
-        }
-        return o.length ? "/" + o.reverse().join("/") : ""
-    }
-});
-
-
-const findUpTag = (el) => {
-    let r = el
-    chained_css = [];
-    depth = 0;
-
-// Strategy 1: Keep going up until we hit an ID tag, imagine it's like  #list-widget div h4
-    while (r.parentNode) {
-        if (depth == 5) {
-            break;
-        }
-        if ('' !== r.id) {
-            chained_css.unshift("#" + CSS.escape(r.id));
-            final_selector = chained_css.join(' > ');
-            // Be sure theres only one, some sites have multiples of the same ID tag :-(
-            if (window.document.querySelectorAll(final_selector).length == 1) {
-                return final_selector;
-            }
-            return null;
-        } else {
-            chained_css.unshift(r.tagName.toLowerCase());
-        }
-        r = r.parentNode;
-        depth += 1;
-    }
-    return null;
-}
-
-
-// @todo - if it's SVG or IMG, go into image diff mode
-var elements = window.document.querySelectorAll("div,span,form,table,tbody,tr,td,a,p,ul,li,h1,h2,h3,h4, header, footer, section, article, aside, details, main, nav, section, summary");
-var size_pos = [];
-// after page fetch, inject this JS
-// build a map of all elements and their positions (maybe that only include text?)
-var bbox;
-for (var i = 0; i < elements.length; i++) {
-    bbox = elements[i].getBoundingClientRect();
-
-    // forget really small ones
-    if (bbox['width'] < 15 && bbox['height'] < 15) {
-        continue;
-    }
-
-    // @todo the getXpath kind of sucks, it doesnt know when there is for example just one ID sometimes
-    // it should not traverse when we know we can anchor off just an ID one level up etc..
-    // maybe, get current class or id, keep traversing up looking for only class or id until there is just one match
-
-    // 1st primitive - if it has class, try joining it all and select, if theres only one.. well thats us.
-    xpath_result = false;
-
-    try {
-        var d = findUpTag(elements[i]);
-        if (d) {
-            xpath_result = d;
-        }
-    } catch (e) {
-        console.log(e);
-    }
-
-    // You could swap it and default to getXpath and then try the smarter one
-    // default back to the less intelligent one
-    if (!xpath_result) {
-        try {
-            // I've seen on FB and eBay that this doesnt work
-            // ReferenceError: getXPath is not defined at eval (eval at evaluate (:152:29), <anonymous>:67:20) at UtilityScript.evaluate (<anonymous>:159:18) at UtilityScript.<anonymous> (<anonymous>:1:44)
-            xpath_result = getXPath(elements[i]);
-        } catch (e) {
-            console.log(e);
-            continue;
-        }
-    }
-
-    if (window.getComputedStyle(elements[i]).visibility === "hidden") {
-        continue;
-    }
-
-    size_pos.push({
-        xpath: xpath_result,
-        width: Math.round(bbox['width']),
-        height: Math.round(bbox['height']),
-        left: Math.floor(bbox['left']),
-        top: Math.floor(bbox['top'])
-    });
-}
-
-
-// Inject the current one set in the include_filters, which may be a CSS rule
-// used for displaying the current one in VisualSelector, where its not one we generated.
-if (include_filters.length) {
-    // Foreach filter, go and find it on the page and add it to the results so we can visualise it again
-    for (const f of include_filters) {
-        bbox = false;
-        q = false;
-
-        if (!f.length) {
-            console.log("xpath_element_scraper: Empty filter, skipping");
-            continue;
-        }
-
-        try {
-            // is it xpath?
-            if (f.startsWith('/') || f.startsWith('xpath:')) {
-                q = document.evaluate(f.replace('xpath:', ''), document, null, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue;
-            } else {
-                q = document.querySelector(f);
-            }
-        } catch (e) {
-            // Maybe catch DOMException and alert?
-            console.log("xpath_element_scraper: Exception selecting element from filter "+f);
-            console.log(e);
-        }
-
-        if (q) {
-            bbox = q.getBoundingClientRect();
-        } else {
-            console.log("xpath_element_scraper: filter element "+f+" was not found");
-        }
-
-        if (bbox && bbox['width'] > 0 && bbox['height'] > 0) {
-            size_pos.push({
-                xpath: f,
-                width: Math.round(bbox['width']),
-                height: Math.round(bbox['height']),
-                left: Math.floor(bbox['left']),
-                top: Math.floor(bbox['top'])
-            });
-        }
-    }
-}
-
-// Window.width required for proper scaling in the frontend
-return {'size_pos': size_pos, 'browser_width': window.innerWidth};

changedetectionio/run_all_tests.sh

@@ -24,12 +24,6 @@ echo "RUNNING WITH BASE_URL SET"
 export BASE_URL="https://really-unique-domain.io"
 pytest tests/test_notification.py
 
-
-# Re-run with HIDE_REFERER set - could affect login
-export HIDE_REFERER=True
-pytest tests/test_access_control.py
-
-
 # Now for the selenium and playwright/browserless fetchers
 # Note - this is not UI functional tests - just checking that each one can fetch the content
 
@@ -44,10 +38,6 @@ unset WEBDRIVER_URL
 docker kill $$-test_selenium
 
 echo "TESTING WEBDRIVER FETCH > PLAYWRIGHT/BROWSERLESS..."
-# Not all platforms support playwright (not ARM/rPI), so it's not packaged in requirements.txt
-PLAYWRIGHT_VERSION=$(grep -i -E "RUN pip install.+" "$SCRIPT_DIR/../Dockerfile" | grep --only-matching -i -E "playwright[=><~+]+[0-9\.]+")
-echo "using $PLAYWRIGHT_VERSION"
-pip3 install "$PLAYWRIGHT_VERSION"
 docker run -d --name $$-test_browserless -e "DEFAULT_LAUNCH_ARGS=[\"--window-size=1920,1080\"]" --rm  -p 3000:3000  --shm-size="2g"  browserless/chrome:1.53-chrome-stable
 # takes a while to spin up
 sleep 5

changedetectionio/static/js/diff-render.js

@@ -1,112 +0,0 @@
-var a = document.getElementById('a');
-var b = document.getElementById('b');
-var result = document.getElementById('result');
-
-function changed() {
-    // https://github.com/kpdecker/jsdiff/issues/389
-    // I would love to use `{ignoreWhitespace: true}` here but it breaks the formatting
-    options = {ignoreWhitespace: document.getElementById('ignoreWhitespace').checked};
-
-    var diff = Diff[window.diffType](a.textContent, b.textContent, options);
-    var fragment = document.createDocumentFragment();
-    for (var i = 0; i < diff.length; i++) {
-
-        if (diff[i].added && diff[i + 1] && diff[i + 1].removed) {
-            var swap = diff[i];
-            diff[i] = diff[i + 1];
-            diff[i + 1] = swap;
-        }
-
-        var node;
-        if (diff[i].removed) {
-            node = document.createElement('del');
-            node.classList.add("change");
-            node.appendChild(document.createTextNode(diff[i].value));
-
-        } else if (diff[i].added) {
-            node = document.createElement('ins');
-            node.classList.add("change");
-            node.appendChild(document.createTextNode(diff[i].value));
-        } else {
-            node = document.createTextNode(diff[i].value);
-        }
-        fragment.appendChild(node);
-    }
-
-    result.textContent = '';
-    result.appendChild(fragment);
-
-    // Jump at start
-    inputs.current = 0;
-    next_diff();
-}
-
-window.onload = function () {
-
-
-    /* Convert what is options from UTC time.time() to local browser time */
-    var diffList = document.getElementById("diff-version");
-    if (typeof (diffList) != 'undefined' && diffList != null) {
-        for (var option of diffList.options) {
-            var dateObject = new Date(option.value * 1000);
-            option.label = dateObject.toLocaleString();
-        }
-    }
-
-    /* Set current version date as local time in the browser also */
-    var current_v = document.getElementById("current-v-date");
-    var dateObject = new Date(newest_version_timestamp*1000);
-    current_v.innerHTML = dateObject.toLocaleString();
-    onDiffTypeChange(document.querySelector('#settings [name="diff_type"]:checked'));
-    changed();
-};
-
-a.onpaste = a.onchange =
-    b.onpaste = b.onchange = changed;
-
-if ('oninput' in a) {
-    a.oninput = b.oninput = changed;
-} else {
-    a.onkeyup = b.onkeyup = changed;
-}
-
-function onDiffTypeChange(radio) {
-    window.diffType = radio.value;
-// Not necessary
-//	document.title = "Diff " + radio.value.slice(4);
-}
-
-var radio = document.getElementsByName('diff_type');
-for (var i = 0; i < radio.length; i++) {
-    radio[i].onchange = function (e) {
-        onDiffTypeChange(e.target);
-        changed();
-    }
-}
-
-document.getElementById('ignoreWhitespace').onchange = function (e) {
-    changed();
-}
-
-
-var inputs = document.getElementsByClassName('change');
-inputs.current = 0;
-
-
-function next_diff() {
-
-    var element = inputs[inputs.current];
-    var headerOffset = 80;
-    var elementPosition = element.getBoundingClientRect().top;
-    var offsetPosition = elementPosition - headerOffset + window.scrollY;
-
-    window.scrollTo({
-        top: offsetPosition,
-        behavior: "smooth"
-    });
-
-    inputs.current++;
-    if (inputs.current >= inputs.length) {
-        inputs.current = 0;
-    }
-}

changedetectionio/static/js/visual-selector.js

@@ -13,7 +13,7 @@ $(document).ready(function() {
     // redline highlight context
     var ctx;
 
-    var current_default_xpath=[];
+    var current_default_xpath;
     var x_scale=1;
     var y_scale=1;
     var selector_image;
@@ -50,31 +50,28 @@ $(document).ready(function() {
         state_clicked=false;
         ctx.clearRect(0, 0, c.width, c.height);
         xctx.clearRect(0, 0, c.width, c.height);
-        $("#include_filters").val('');
+        $("#css_filter").val('');
     });
 
 
     bootstrap_visualselector();
 
 
+
     function bootstrap_visualselector() {
-        if (1) {
+        if ( 1 ) {
             // bootstrap it, this will trigger everything else
             $("img#selector-background").bind('load', function () {
                 console.log("Loaded background...");
-                c = document.getElementById("selector-canvas");
+               c = document.getElementById("selector-canvas");
                 // greyed out fill context
-                xctx = c.getContext("2d");
+               xctx = c.getContext("2d");
                 // redline highlight context
-                ctx = c.getContext("2d");
-                if ($("#include_filters").val().trim().length) {
-                    current_default_xpath = $("#include_filters").val().split(/\r?\n/g);
-                } else {
-                    current_default_xpath = [];
-                }
-                fetch_data();
-                $('#selector-canvas').off("mousemove mousedown");
-                // screenshot_url defined in the edit.html template
+               ctx = c.getContext("2d");
+               current_default_xpath =$("#css_filter").val();
+               fetch_data();
+               $('#selector-canvas').off("mousemove mousedown");
+               // screenshot_url defined in the edit.html template
             }).attr("src", screenshot_url);
         }
     }
@@ -130,30 +127,24 @@ $(document).ready(function() {
 
       console.log(selector_data['size_pos'].length + " selectors found");
 
-        // highlight the default one if we can find it in the xPath list
-        // or the xpath matches the default one
-        found = false;
-        if (current_default_xpath.length) {
-            // Find the first one that matches
-            // @todo In the future paint all that match
-            for (const c of current_default_xpath) {
-                for (var i = selector_data['size_pos'].length; i !== 0; i--) {
-                    if (selector_data['size_pos'][i - 1].xpath === c) {
-                        console.log("highlighting " + c);
-                        current_selected_i = i - 1;
-                        highlight_current_selected_i();
-                        found = true;
-                        break;
-                    }
-                }
-                if (found) {
-                    break;
-                }
-            }
-            if (!found) {
-                alert("Unfortunately your existing CSS/xPath Filter was no longer found!");
+      // highlight the default one if we can find it in the xPath list
+      // or the xpath matches the default one
+      found = false;
+      if(current_default_xpath.length) {
+          for (var i = selector_data['size_pos'].length; i!==0; i--) {
+            var sel = selector_data['size_pos'][i-1];
+            if(selector_data['size_pos'][i - 1].xpath == current_default_xpath) {
+            console.log("highlighting "+current_default_xpath);
+              current_selected_i = i-1;
+              highlight_current_selected_i();
+              found = true;
+              break;
             }
+          }
+        if(!found) {
+          alert("Unfortunately your existing CSS/xPath Filter was no longer found!");
         }
+      }
 
 
       $('#selector-canvas').bind('mousemove', function (e) {
@@ -214,9 +205,9 @@ $(document).ready(function() {
         var sel = selector_data['size_pos'][current_selected_i];
         if (sel[0] == '/') {
         // @todo - not sure just checking / is right
-            $("#include_filters").val('xpath:'+sel.xpath);
+            $("#css_filter").val('xpath:'+sel.xpath);
         } else {
-            $("#include_filters").val(sel.xpath);
+            $("#css_filter").val(sel.xpath);
         }
         xctx.fillStyle = 'rgba(205,205,205,0.95)';
         xctx.strokeStyle = 'rgba(225,0,0,0.9)';

changedetectionio/store.py

@@ -82,13 +82,8 @@ class ChangeDetectionStore:
         except (FileNotFoundError, json.decoder.JSONDecodeError):
             if include_default_watches:
                 print("Creating JSON store at", self.datastore_path)
-                self.add_watch(url='https://news.ycombinator.com/',
-                               tag='Tech news',
-                               extras={'fetch_backend': 'html_requests'})
-
-                self.add_watch(url='https://changedetection.io/CHANGELOG.txt',
-                               tag='changedetection.io',
-                               extras={'fetch_backend': 'html_requests'})
+                self.add_watch(url='https://news.ycombinator.com/', tag='Tech news')
+                self.add_watch(url='https://changedetection.io/CHANGELOG.txt', tag='changedetection.io')
 
         self.__data['version_tag'] = version_tag
 
@@ -272,7 +267,7 @@ class ChangeDetectionStore:
             extras = {}
         # should always be str
         if tag is None or not tag:
-            tag = ''
+            tag=''
 
         # Incase these are copied across, assume it's a reference and deepcopy()
         apply_extras = deepcopy(extras)
@@ -287,31 +282,17 @@ class ChangeDetectionStore:
                 res = r.json()
 
                 # List of permissible attributes we accept from the wild internet
-                for k in [
-                    'body',
-                    'css_filter',
-                    'extract_text',
-                    'extract_title_as_title',
-                    'headers',
-                    'ignore_text',
-                    'include_filters',
-                    'method',
-                    'paused',
-                    'previous_md5',
-                    'subtractive_selectors',
-                    'tag',
-                    'text_should_not_be_present',
-                    'title',
-                    'trigger_text',
-                    'webdriver_js_execute_code',
-                    'url',
-                ]:
+                for k in ['url', 'tag',
+                          'paused', 'title',
+                          'previous_md5', 'headers',
+                          'body', 'method',
+                          'ignore_text', 'css_filter',
+                          'subtractive_selectors', 'trigger_text',
+                          'extract_title_as_title', 'extract_text',
+                          'text_should_not_be_present',
+                          'webdriver_js_execute_code']:
                     if res.get(k):
-                        if k != 'css_filter':
-                            apply_extras[k] = res[k]
-                        else:
-                            # We renamed the field and made it a list
-                            apply_extras['include_filters'] = [res['css_filter']]
+                        apply_extras[k] = res[k]
 
             except Exception as e:
                 logging.error("Error fetching metadata for shared watch link", url, str(e))
@@ -334,13 +315,12 @@ class ChangeDetectionStore:
                     del apply_extras[k]
 
             new_watch.update(apply_extras)
-            self.__data['watching'][new_uuid] = new_watch
+            self.__data['watching'][new_uuid]=new_watch
 
         self.__data['watching'][new_uuid].ensure_data_dir_exists()
 
         if write_to_disk_now:
             self.sync_to_json()
-
         return new_uuid
 
     def visualselector_data_is_ready(self, watch_uuid):
@@ -604,14 +584,3 @@ class ChangeDetectionStore:
         for v in ['User-Agent', 'Accept', 'Accept-Encoding', 'Accept-Language']:
             if self.data['settings']['headers'].get(v):
                 del self.data['settings']['headers'][v]
-
-    # Convert filters to a list of filters css_filter -> include_filters
-    def update_8(self):
-        for uuid, watch in self.data['watching'].items():
-            try:
-                existing_filter = watch.get('css_filter', '')
-                if existing_filter:
-                    watch['include_filters'] = [existing_filter]
-            except:
-                continue
-        return

changedetectionio/templates/diff.html

@@ -21,9 +21,6 @@
 
             <label for="diffChars" class="pure-checkbox">
                 <input type="radio" name="diff_type" id="diffChars" value="diffChars"/> Chars</label>
-            <!-- @todo - when mimetype is JSON, select this by default? -->
-            <label for="diffJson" class="pure-checkbox">
-                <input type="radio" name="diff_type" id="diffJson" value="diffJson" /> JSON</label>
 
             {% if versions|length >= 1 %}
             <label for="diff-version">Compare newest (<span id="current-v-date"></span>) with</label>
@@ -40,11 +37,6 @@
     </form>
     <del>Removed text</del>
     <ins>Inserted Text</ins>
-    <span>
-        <!-- https://github.com/kpdecker/jsdiff/issues/389 ? -->
-        <label for="ignoreWhitespace" class="pure-checkbox" id="label-diff-ignorewhitespace">
-            <input type="checkbox" id="ignoreWhitespace" name="ignoreWhitespace"/> Ignore Whitespace</label>
-    </span>
 </div>
 
 <div id="diff-jump">
@@ -110,12 +102,122 @@
      </div>
 </div>
 
-<script>
-    const newest_version_timestamp = {{newest_version_timestamp}};
-</script>
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='diff.min.js')}}"></script>
 
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='diff-render.js')}}"></script>
+<script type="text/javascript" src="{{url_for('static_content', group='js', filename='diff.js')}}"></script>
+
+<script defer="">
+
+var a = document.getElementById('a');
+var b = document.getElementById('b');
+var result = document.getElementById('result');
+
+function changed() {
+	var diff = JsDiff[window.diffType](a.textContent, b.textContent);
+	var fragment = document.createDocumentFragment();
+	for (var i=0; i < diff.length; i++) {
+
+		if (diff[i].added && diff[i + 1] && diff[i + 1].removed) {
+			var swap = diff[i];
+			diff[i] = diff[i + 1];
+			diff[i + 1] = swap;
+		}
+
+		var node;
+		if (diff[i].removed) {
+			node = document.createElement('del');
+			node.classList.add("change");
+			node.appendChild(document.createTextNode(diff[i].value));
+
+		} else if (diff[i].added) {
+			node = document.createElement('ins');
+			node.classList.add("change");
+			node.appendChild(document.createTextNode(diff[i].value));
+		} else {
+			node = document.createTextNode(diff[i].value);
+		}
+		fragment.appendChild(node);
+	}
+
+	result.textContent = '';
+	result.appendChild(fragment);
+
+	// Jump at start
+	inputs.current=0;
+    next_diff();
+}
+
+window.onload = function() {
+
+
+    /* Convert what is options from UTC time.time() to local browser time */
+    var diffList=document.getElementById("diff-version");
+    if (typeof(diffList) != 'undefined' && diffList != null) {
+        for (var option of diffList.options) {
+          var dateObject = new Date(option.value*1000);
+          option.label=dateObject.toLocaleString();
+        }
+    }
+
+    /* Set current version date as local time in the browser also */
+    var current_v = document.getElementById("current-v-date");
+    var dateObject = new Date({{ newest_version_timestamp }}*1000);
+    current_v.innerHTML=dateObject.toLocaleString();
+
+
+	onDiffTypeChange(document.querySelector('#settings [name="diff_type"]:checked'));
+	changed();
+
+};
+
+a.onpaste = a.onchange =
+b.onpaste = b.onchange = changed;
+
+if ('oninput' in a) {
+	a.oninput = b.oninput = changed;
+} else {
+	a.onkeyup = b.onkeyup = changed;
+}
+
+function onDiffTypeChange(radio) {
+	window.diffType = radio.value;
+// Not necessary 
+//	document.title = "Diff " + radio.value.slice(4);
+}
+
+var radio = document.getElementsByName('diff_type');
+for (var i = 0; i < radio.length; i++) {
+	radio[i].onchange = function(e) {
+		onDiffTypeChange(e.target);
+		changed();
+	}
+}
+
+
+var inputs = document.getElementsByClassName('change');
+inputs.current=0;
+
+
+function next_diff() {
+
+    var element = inputs[inputs.current];
+    var headerOffset = 80;
+    var elementPosition = element.getBoundingClientRect().top;
+    var offsetPosition = elementPosition - headerOffset +  window.scrollY;
+
+    window.scrollTo({
+         top: offsetPosition,
+         behavior: "smooth"
+    });
+
+    inputs.current++;
+    if(inputs.current >= inputs.length) {
+      inputs.current=0;
+    }
+}
+
+
+
+</script>
 
 
 {% endblock %}

changedetectionio/templates/edit.html

@@ -141,14 +141,6 @@ User-Agent: wonderbra 1.0") }}
                     <div  class="pure-control-group inline-radio">
                       {{ render_checkbox_field(form.notification_muted) }}
                     </div>
-                    {% if is_html_webdriver %}
-                    <span class="pure-control-group inline-radio">
-                      {{ render_checkbox_field(form.notification_screenshot) }}
-                        <span class="pure-form-message-inline">
-                            <strong>Use with caution!</strong> This will easily fill up your email storage quota or flood other storages.
-                        </span>
-                    </div>
-                    {% endif %}
                     <div class="field-group" id="notification-field-group">
                         {% if has_default_notification_urls %}
                         <div class="inline-warning">
@@ -182,17 +174,15 @@ User-Agent: wonderbra 1.0") }}
                         </div>
                     </fieldset>
                     <div class="pure-control-group">
-                        {% set field = render_field(form.include_filters,
-                            rows=5,
-                            placeholder="#example
-xpath://body/div/span[contains(@class, 'example-class')]",
+                        {% set field = render_field(form.css_filter,
+                            placeholder=".class-name or #some-id, or other CSS selector rule.",
                             class="m-d")
                         %}
                         {{ field }}
                         {% if '/text()' in  field %}
                           <span class="pure-form-message-inline"><strong>Note!: //text() function does not work where the &lt;element&gt; contains &lt;![CDATA[]]&gt;</strong></span><br/>
                         {% endif %}
-                        <span class="pure-form-message-inline">One rule per line, <i>any</i> rules that matches will be used.<br/>
+                        <span class="pure-form-message-inline">
                     <ul>
                         <li>CSS - Limit text to this CSS rule, only text matching this CSS rule is included.</li>
                         <li>JSON - Limit text to this JSON rule, using either <a href="https://pypi.org/project/jsonpath-ng/" target="new">JSONPath</a> or <a href="https://stedolan.github.io/jq/" target="new">jq</a> (if installed).

changedetectionio/templates/watch-overview.html

@@ -96,7 +96,7 @@
                     <div class="fetch-error">{{ watch.last_error }}</div>
                     {% endif %}
                     {% if watch.last_notification_error is defined and watch.last_notification_error != False %}
-                    <div class="fetch-error notification-error"><a href="{{url_for('notification_logs')}}">{{ watch.last_notification_error }}</a></div>
+                    <div class="fetch-error notification-error">{{ watch.last_notification_error }}</div>
                     {% endif %}
                     {% if not active_tag %}
                     <span class="watch-tag-list">{{ watch.tag}}</span>

changedetectionio/tests/proxy_list/test_multiple_proxy.py

@@ -24,7 +24,7 @@ def test_preferred_proxy(client, live_server):
     res = client.post(
         url_for("edit_page", uuid="first"),
         data={
-                "include_filters": "",
+                "css_filter": "",
                 "fetch_backend": "html_requests",
                 "headers": "",
                 "proxy": "proxy-two",

changedetectionio/tests/test_auth.py

@@ -23,7 +23,7 @@ def test_basic_auth(client, live_server):
     # Check form validation
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"include_filters": "", "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
+        data={"css_filter": "", "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
         follow_redirects=True
     )
     assert b"Updated watch." in res.data

changedetectionio/tests/test_css_selector.py

@@ -46,23 +46,22 @@ def set_modified_response():
 
 
 # Test that the CSS extraction works how we expect, important here is the right placing of new lines \n's
-def test_include_filters_output():
+def test_css_filter_output():
+    from changedetectionio import fetch_site_status
     from inscriptis import get_text
 
     # Check text with sub-parts renders correctly
     content = """<html> <body><div id="thingthing" >  Some really <b>bold</b> text  </div> </body> </html>"""
-    html_blob = include_filters(include_filters="#thingthing", html_content=content)
+    html_blob = css_filter(css_filter="#thingthing", html_content=content)
     text = get_text(html_blob)
     assert text == "  Some really bold text"
 
     content = """<html> <body>
     <p>foo bar blah</p>
-    <DIV class="parts">Block A</DiV> <div class="parts">Block B</DIV></body> 
+    <div class="parts">Block A</div> <div class="parts">Block B</div></body> 
     </html>
 """
-
-    # in xPath this would be //*[@class='parts']
-    html_blob = include_filters(include_filters=".parts", html_content=content)
+    html_blob = css_filter(css_filter=".parts", html_content=content)
     text = get_text(html_blob)
 
     # Divs are converted to 4 whitespaces by inscriptis
@@ -70,10 +69,10 @@ def test_include_filters_output():
 
 
 # Tests the whole stack works with the CSS Filter
-def test_check_markup_include_filters_restriction(client, live_server):
+def test_check_markup_css_filter_restriction(client, live_server):
     sleep_time_for_fetch_thread = 3
 
-    include_filters = "#sametext"
+    css_filter = "#sametext"
 
     set_original_response()
 
@@ -99,7 +98,7 @@ def test_check_markup_include_filters_restriction(client, live_server):
     # Add our URL to the import page
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"include_filters": include_filters, "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
+        data={"css_filter": css_filter, "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
         follow_redirects=True
     )
     assert b"Updated watch." in res.data
@@ -108,7 +107,7 @@ def test_check_markup_include_filters_restriction(client, live_server):
     res = client.get(
         url_for("edit_page", uuid="first"),
     )
-    assert bytes(include_filters.encode('utf-8')) in res.data
+    assert bytes(css_filter.encode('utf-8')) in res.data
 
     # Trigger a check
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
@@ -127,58 +126,3 @@ def test_check_markup_include_filters_restriction(client, live_server):
     # Because it should be looking at only that 'sametext' id
     res = client.get(url_for("index"))
     assert b'unviewed' in res.data
-
-
-# Tests the whole stack works with the CSS Filter
-def test_check_multiple_filters(client, live_server):
-    sleep_time_for_fetch_thread = 3
-
-    include_filters = "#blob-a\r\nxpath://*[contains(@id,'blob-b')]"
-
-    with open("test-datastore/endpoint-content.txt", "w") as f:
-        f.write("""<html><body>
-     <div id="blob-a">Blob A</div>
-     <div id="blob-b">Blob B</div>
-     <div id="blob-c">Blob C</div>
-     </body>
-     </html>
-    """)
-
-    # Give the endpoint time to spin up
-    time.sleep(1)
-
-    # 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
-    time.sleep(1)
-
-    # Goto the edit page, add our ignore text
-    # Add our URL to the import page
-    res = client.post(
-        url_for("edit_page", uuid="first"),
-        data={"include_filters": include_filters,
-              "url": test_url,
-              "tag": "",
-              "headers": "",
-              'fetch_backend': "html_requests"},
-        follow_redirects=True
-    )
-    assert b"Updated watch." in res.data
-
-    # Give the thread time to pick it up
-    time.sleep(sleep_time_for_fetch_thread)
-
-    res = client.get(
-        url_for("preview_page", uuid="first"),
-        follow_redirects=True
-    )
-
-    # Only the two blobs should be here
-    assert b"Blob A" in res.data # CSS was ok
-    assert b"Blob B" in res.data # xPath was ok
-    assert b"Blob C" not in res.data # Should not be included

changedetectionio/tests/test_extract_regex.py

@@ -88,7 +88,7 @@ def test_check_filter_multiline(client, live_server):
     # Add our URL to the import page
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"include_filters": '',
+        data={"css_filter": '',
               'extract_text': '/something.+?6 billion.+?lines/si',
               "url": test_url,
               "tag": "",
@@ -116,7 +116,7 @@ def test_check_filter_multiline(client, live_server):
 
 def test_check_filter_and_regex_extract(client, live_server):
     sleep_time_for_fetch_thread = 3
-    include_filters = ".changetext"
+    css_filter = ".changetext"
 
     set_original_response()
 
@@ -143,7 +143,7 @@ def test_check_filter_and_regex_extract(client, live_server):
     # Add our URL to the import page
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"include_filters": include_filters,
+        data={"css_filter": css_filter,
               'extract_text': '\d+ online\r\n\d+ guests\r\n/somecase insensitive \d+/i\r\n/somecase insensitive (345\d)/i',
               "url": test_url,
               "tag": "",

changedetectionio/tests/test_filter_exist_changes.py

@@ -92,7 +92,7 @@ def test_filter_doesnt_exist_then_exists_should_get_notification(client, live_se
         "tag": "my tag",
         "title": "my title",
         "headers": "",
-        "include_filters": '.ticket-available',
+        "css_filter": '.ticket-available',
         "fetch_backend": "html_requests"})
 
     res = client.post(

changedetectionio/tests/test_filter_failure_notification.py

@@ -76,7 +76,7 @@ def run_filter_test(client, content_filter):
         "title": "my title",
         "headers": "",
         "filter_failure_notification_send": 'y',
-        "include_filters": content_filter,
+        "css_filter": content_filter,
         "fetch_backend": "html_requests"})
 
     res = client.post(
@@ -95,7 +95,7 @@ def run_filter_test(client, content_filter):
         time.sleep(3)
 
     # We should see something in the frontend
-    assert b'Warning, no filters were found' in res.data
+    assert b'Warning, filter' in res.data
 
     # Now it should exist and contain our "filter not found" alert
     assert os.path.isfile("test-datastore/notification.txt")
@@ -131,7 +131,7 @@ def run_filter_test(client, content_filter):
 def test_setup(live_server):
     live_server_setup(live_server)
 
-def test_check_include_filters_failure_notification(client, live_server):
+def test_check_css_filter_failure_notification(client, live_server):
     set_original_response()
     time.sleep(1)
     run_filter_test(client, '#nope-doesnt-exist')

changedetectionio/tests/test_jsonpath_jq_selector.py

@@ -132,7 +132,7 @@ def set_original_response():
     return None
 
 
-def set_json_response_with_html():
+def set_response_with_html():
     test_return_data = """
     {
       "test": [
@@ -176,7 +176,7 @@ def set_modified_response():
 def test_check_json_without_filter(client, live_server):
     # Request a JSON document from a application/json source containing HTML
     # and be sure it doesn't get chewed up by instriptis
-    set_json_response_with_html()
+    set_response_with_html()
 
     # Give the endpoint time to spin up
     time.sleep(1)
@@ -189,6 +189,9 @@ def test_check_json_without_filter(client, live_server):
         follow_redirects=True
     )
 
+    # Trigger a check
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+
     # Give the thread time to pick it up
     time.sleep(3)
 
@@ -197,7 +200,6 @@ def test_check_json_without_filter(client, live_server):
         follow_redirects=True
     )
 
-    # Should still see '"html": "<b>"'
     assert b'&#34;&lt;b&gt;' in res.data
     assert res.data.count(b'{\n') >= 2
 
@@ -219,6 +221,9 @@ def check_json_filter(json_filter, client, live_server):
     )
     assert b"1 Imported" in res.data
 
+    # Trigger a check
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+
     # Give the thread time to pick it up
     time.sleep(3)
 
@@ -226,7 +231,7 @@ def check_json_filter(json_filter, client, live_server):
     # Add our URL to the import page
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"include_filters": json_filter,
+        data={"css_filter": json_filter,
               "url": test_url,
               "tag": "",
               "headers": "",
@@ -242,6 +247,9 @@ def check_json_filter(json_filter, client, live_server):
     )
     assert bytes(escape(json_filter).encode('utf-8')) in res.data
 
+    # Trigger a check
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+
     # Give the thread time to pick it up
     time.sleep(3)
     #  Make a change
@@ -293,7 +301,7 @@ def check_json_filter_bool_val(json_filter, client, live_server):
     # Add our URL to the import page
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"include_filters": json_filter,
+        data={"css_filter": json_filter,
               "url": test_url,
               "tag": "",
               "headers": "",
@@ -303,6 +311,11 @@ def check_json_filter_bool_val(json_filter, client, live_server):
     )
     assert b"Updated watch." in res.data
 
+    time.sleep(3)
+
+    # Trigger a check
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+
     # Give the thread time to pick it up
     time.sleep(3)
     #  Make a change
@@ -347,6 +360,9 @@ def check_json_ext_filter(json_filter, client, live_server):
     )
     assert b"1 Imported" in res.data
 
+    # Trigger a check
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+
     # Give the thread time to pick it up
     time.sleep(3)
 
@@ -354,7 +370,7 @@ def check_json_ext_filter(json_filter, client, live_server):
     # Add our URL to the import page
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"include_filters": json_filter,
+        data={"css_filter": json_filter,
               "url": test_url,
               "tag": "",
               "headers": "",
@@ -370,6 +386,9 @@ def check_json_ext_filter(json_filter, client, live_server):
     )
     assert bytes(escape(json_filter).encode('utf-8')) in res.data
 
+    # Trigger a check
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+
     # Give the thread time to pick it up
     time.sleep(3)
     #  Make a change

changedetectionio/tests/test_notification.py

@@ -1,12 +1,9 @@
-import json
 import os
 import time
 import re
 from flask import url_for
 from . util import set_original_response, set_modified_response, set_more_modified_response, live_server_setup
-from . util import  extract_UUID_from_client
 import logging
-import base64
 
 from changedetectionio.notification import (
     default_notification_body,
@@ -21,6 +18,7 @@ def test_setup(live_server):
 # Hard to just add more live server URLs when one test is already running (I think)
 # So we add our test here (was in a different file)
 def test_check_notification(client, live_server):
+
     set_original_response()
 
     # Give the endpoint time to spin up
@@ -70,15 +68,6 @@ def test_check_notification(client, live_server):
     # Give the thread time to pick up the first version
     time.sleep(3)
 
-    # We write the PNG to disk, but a JPEG should appear in the notification
-    testimage_png = 'iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAQAAAC1HAwCAAAAC0lEQVR42mNkYAAAAAYAAjCB0C8AAAAASUVORK5CYII='
-    # Write the last screenshot png
-
-    uuid = extract_UUID_from_client(client)
-    datastore = 'test-datastore'
-    with open(os.path.join(datastore, str(uuid), 'last-screenshot.png'), 'wb') as f:
-        f.write(base64.b64decode(testimage_png))
-
     # Goto the edit page, add our ignore text
     # Add our URL to the import page
 
@@ -97,7 +86,6 @@ def test_check_notification(client, live_server):
                                                    "Diff: {diff}\n"
                                                    "Diff Full: {diff_full}\n"
                                                    ":-)",
-                              "notification_screenshot": True,
                               "notification_format": "Text"}
 
     notification_form_data.update({
@@ -155,19 +143,6 @@ def test_check_notification(client, live_server):
     assert ":-)" in notification_submission
     assert "New ChangeDetection.io Notification - {}".format(test_url) in notification_submission
 
-    # Check the attachment was added, and that it is a JPEG from the original PNG
-    notification_submission_object = json.loads(notification_submission)
-    assert notification_submission_object['attachments'][0]['filename'] == 'last-screenshot.jpg'
-    assert len(notification_submission_object['attachments'][0]['base64'])
-    assert notification_submission_object['attachments'][0]['mimetype'] == 'image/jpeg'
-    jpeg_in_attachment = base64.b64decode(notification_submission_object['attachments'][0]['base64'])
-    assert b'JFIF' in jpeg_in_attachment
-    assert testimage_png not in notification_submission
-    # Assert that the JPEG is readable (didn't get chewed up somewhere)
-    from PIL import Image
-    import io
-    assert Image.open(io.BytesIO(jpeg_in_attachment))
-
     if env_base_url:
         # Re #65 - did we see our BASE_URl ?
         logging.debug (">>> BASE_URL checking in notification: %s", env_base_url)

changedetectionio/tests/test_share_watch.py

@@ -14,7 +14,7 @@ def test_share_watch(client, live_server):
     live_server_setup(live_server)
 
     test_url = url_for('test_endpoint', _external=True)
-    include_filters = ".nice-filter"
+    css_filter = ".nice-filter"
 
     # Add our URL to the import page
     res = client.post(
@@ -29,7 +29,7 @@ def test_share_watch(client, live_server):
     # Add our URL to the import page
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"include_filters": include_filters, "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
+        data={"css_filter": css_filter, "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
         follow_redirects=True
     )
     assert b"Updated watch." in res.data
@@ -37,7 +37,7 @@ def test_share_watch(client, live_server):
     res = client.get(
         url_for("edit_page", uuid="first"),
     )
-    assert bytes(include_filters.encode('utf-8')) in res.data
+    assert bytes(css_filter.encode('utf-8')) in res.data
 
     # click share the link
     res = client.get(
@@ -73,8 +73,4 @@ def test_share_watch(client, live_server):
     res = client.get(
         url_for("edit_page", uuid="first"),
     )
-    assert bytes(include_filters.encode('utf-8')) in res.data
-
-    # Check it saved the URL
-    res = client.get(url_for("index"))
-    assert bytes(test_url.encode('utf-8')) in res.data
+    assert bytes(css_filter.encode('utf-8')) in res.data

changedetectionio/tests/test_source.py

@@ -57,9 +57,10 @@ def test_check_basic_change_detection_functionality_source(client, live_server):
 
 
 
-# `subtractive_selectors` should still work in `source:` type requests
+
 def test_check_ignore_elements(client, live_server):
     set_original_response()
+
     time.sleep(2)
     test_url = 'source:'+url_for('test_endpoint', _external=True)
     # Add our URL to the import page
@@ -76,9 +77,9 @@ def test_check_ignore_elements(client, live_server):
     #####################
     # We want <span> and <p> ONLY, but ignore span with .foobar-detection
 
-    client.post(
+    res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"include_filters": 'span,p', "url": test_url, "tag": "", "subtractive_selectors": ".foobar-detection", 'fetch_backend': "html_requests"},
+        data={"css_filter": 'span,p', "url": test_url, "tag": "", "subtractive_selectors": ".foobar-detection", 'fetch_backend': "html_requests"},
         follow_redirects=True
     )
 
@@ -88,6 +89,7 @@ def test_check_ignore_elements(client, live_server):
         url_for("preview_page", uuid="first"),
         follow_redirects=True
     )
+
     assert b'foobar-detection' not in res.data
     assert b'&lt;br' not in res.data
     assert b'&lt;p' in res.data

changedetectionio/tests/test_trigger_regex_with_filter.py

@@ -49,7 +49,7 @@ def test_trigger_regex_functionality_with_filter(client, live_server):
         url_for("edit_page", uuid="first"),
         data={"trigger_text": "/cool.stuff/",
               "url": test_url,
-              "include_filters": '#in-here',
+              "css_filter": '#in-here',
               "fetch_backend": "html_requests"},
         follow_redirects=True
     )

changedetectionio/tests/test_watch_fields_storage.py

@@ -22,7 +22,7 @@ def test_check_watch_field_storage(client, live_server):
         url_for("edit_page", uuid="first"),
         data={ "notification_urls": "json://127.0.0.1:30000\r\njson://128.0.0.1\r\n",
                "time_between_check-minutes": 126,
-               "include_filters" : ".fooclass",
+               "css_filter" : ".fooclass",
                "title" : "My title",
                "ignore_text" : "ignore this",
                "url": test_url,

changedetectionio/tests/test_xpath_selector.py

@@ -89,7 +89,7 @@ def test_check_xpath_filter_utf8(client, live_server):
     time.sleep(1)
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"include_filters": filter, "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
+        data={"css_filter": filter, "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
         follow_redirects=True
     )
     assert b"Updated watch." in res.data
@@ -143,7 +143,7 @@ def test_check_xpath_text_function_utf8(client, live_server):
     time.sleep(1)
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"include_filters": filter, "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
+        data={"css_filter": filter, "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
         follow_redirects=True
     )
     assert b"Updated watch." in res.data
@@ -182,6 +182,9 @@ def test_check_markup_xpath_filter_restriction(client, live_server):
     )
     assert b"1 Imported" in res.data
 
+    # Trigger a check
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+
     # Give the thread time to pick it up
     time.sleep(sleep_time_for_fetch_thread)
 
@@ -189,7 +192,7 @@ def test_check_markup_xpath_filter_restriction(client, live_server):
     # Add our URL to the import page
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"include_filters": xpath_filter, "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
+        data={"css_filter": xpath_filter, "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
         follow_redirects=True
     )
     assert b"Updated watch." in res.data
@@ -227,11 +230,10 @@ def test_xpath_validation(client, live_server):
         follow_redirects=True
     )
     assert b"1 Imported" in res.data
-    time.sleep(2)
 
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"include_filters": "/something horrible", "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
+        data={"css_filter": "/something horrible", "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
         follow_redirects=True
     )
     assert b"is not a valid XPath expression" in res.data
@@ -240,7 +242,7 @@ def test_xpath_validation(client, live_server):
 
 
 # actually only really used by the distll.io importer, but could be handy too
-def test_check_with_prefix_include_filters(client, live_server):
+def test_check_with_prefix_css_filter(client, live_server):
     res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
     assert b'Deleted' in res.data
 
@@ -261,7 +263,7 @@ def test_check_with_prefix_include_filters(client, live_server):
 
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"include_filters":  "xpath://*[contains(@class, 'sametext')]", "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
+        data={"css_filter":  "xpath://*[contains(@class, 'sametext')]", "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
         follow_redirects=True
     )
 

changedetectionio/update_worker.py

@@ -4,7 +4,7 @@ import queue
 import time
 
 from changedetectionio import content_fetcher
-from changedetectionio.fetch_site_status import FilterNotFoundInResponse
+from changedetectionio.html_tools import FilterNotFoundInResponse
 
 # A single update worker
 #
@@ -74,7 +74,6 @@ class update_worker(threading.Thread):
             n_object.update({
                 'watch_url': watch['url'],
                 'uuid': watch_uuid,
-                'screenshot': watch.get_screenshot_as_jpeg() if watch.get('notification_screenshot') else None,
                 'current_snapshot': snapshot_contents.decode('utf-8'),
                 'diff': diff.render_diff(watch_history[dates[-2]], watch_history[dates[-1]], line_feed_sep=line_feed_sep),
                 'diff_full': diff.render_diff(watch_history[dates[-2]], watch_history[dates[-1]], True, line_feed_sep=line_feed_sep)
@@ -92,8 +91,8 @@ class update_worker(threading.Thread):
             return
 
         n_object = {'notification_title': 'Changedetection.io - Alert - CSS/xPath filter was not present in the page',
-                    'notification_body': "Your configured CSS/xPath filters of '{}' for {{watch_url}} did not appear on the page after {} attempts, did the page change layout?\n\nLink: {{base_url}}/edit/{{watch_uuid}}\n\nThanks - Your omniscient changedetection.io installation :)\n".format(
-                        ", ".join(watch['include_filters']),
+                    'notification_body': "Your configured CSS/xPath filter of '{}' for {{watch_url}} did not appear on the page after {} attempts, did the page change layout?\n\nLink: {{base_url}}/edit/{{watch_uuid}}\n\nThanks - Your omniscient changedetection.io installation :)\n".format(
+                        watch['css_filter'],
                         threshold),
                     'notification_format': 'text'}
 
@@ -107,8 +106,7 @@ class update_worker(threading.Thread):
         if 'notification_urls' in n_object:
             n_object.update({
                 'watch_url': watch['url'],
-                'uuid': watch_uuid,
-                'screenshot': None
+                'uuid': watch_uuid
             })
             self.notification_q.put(n_object)
             print("Sent filter not found notification for {}".format(watch_uuid))
@@ -191,7 +189,7 @@ class update_worker(threading.Thread):
                         if not self.datastore.data['watching'].get(uuid):
                             continue
 
-                        err_text = "Warning, no filters were found, no change detection ran."
+                        err_text = "Warning, filter '{}' not found".format(str(e))
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
                                                                            # So that we get a trigger when the content is added again
                                                                            'previous_md5': ''})
@@ -284,19 +282,16 @@ class update_worker(threading.Thread):
                             self.app.logger.error("Exception reached processing watch UUID: %s - %s", uuid, str(e))
                             self.datastore.update_watch(uuid=uuid, update_obj={'last_error': str(e)})
 
-                    if self.datastore.data['watching'].get(uuid):
-                        # Always record that we atleast tried
-                        count = self.datastore.data['watching'][uuid].get('check_count', 0) + 1
-                        self.datastore.update_watch(uuid=uuid, update_obj={'fetch_time': round(time.time() - now, 3),
-                                                                           'last_checked': round(time.time()),
-                                                                           'check_count': count
-                                                                           })
 
-                        # Always save the screenshot if it's available
-                        if update_handler.screenshot:
-                            self.datastore.save_screenshot(watch_uuid=uuid, screenshot=update_handler.screenshot)
-                        if update_handler.xpath_data:
-                            self.datastore.save_xpath_data(watch_uuid=uuid, data=update_handler.xpath_data)
+                    # Always record that we atleast tried
+                    self.datastore.update_watch(uuid=uuid, update_obj={'fetch_time': round(time.time() - now, 3),
+                                                                       'last_checked': round(time.time())})
+
+                    # Always save the screenshot if it's available
+                    if update_handler.screenshot:
+                        self.datastore.save_screenshot(watch_uuid=uuid, screenshot=update_handler.screenshot)
+                    if update_handler.xpath_data:
+                        self.datastore.save_xpath_data(watch_uuid=uuid, data=update_handler.xpath_data)
 
 
                 self.current_uuid = None  # Done

requirements.txt

@@ -23,7 +23,7 @@ jsonpath-ng~=1.5.3
 # jq not available on Windows so must be installed manually
 
 # Notification library
-apprise~=1.2.0
+apprise~=1.1.0
 
 # apprise mqtt https://github.com/dgtlmoon/changedetection.io/issues/315
 paho-mqtt
@@ -52,9 +52,7 @@ jinja2-time
 
 # 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 == "linux"
+playwright~=1.26; python_version >= "3.8" and "arm" not in platform_machine and "aarch" not in platform_machine
 
-# Any current modern version, required so far for screenshot PNG->JPEG conversion but will be used more in the future
-pillow
-# playwright is installed at Dockerfile build time because it's not available on all platforms