0.45.3

.github/test/Dockerfile-alpine

@@ -2,7 +2,7 @@
 # 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
+FROM ghcr.io/linuxserver/baseimage-alpine:3.18
 ENV PYTHONUNBUFFERED=1
 
 COPY requirements.txt /requirements.txt
@@ -26,6 +26,6 @@ RUN \
     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 && \
+  pip3 install -U --no-cache-dir --find-links https://wheel-index.linuxserver.io/alpine-3.18/ -r /requirements.txt && \
   apk del --purge \
     build-dependencies

.github/workflows/containers.yml

@@ -40,10 +40,10 @@ jobs:
     if: ${{ github.event.workflow_run.conclusion == 'success' }} || ${{ github.event.release.tag_name }} != ''
     steps:
       - uses: actions/checkout@v4
-      - name: Set up Python 3.9
+      - name: Set up Python 3.11
         uses: actions/setup-python@v4
         with:
-          python-version: 3.9
+          python-version: 3.11
 
       - name: Install dependencies
         run: |

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

@@ -25,10 +25,10 @@ jobs:
     runs-on: ubuntu-latest
     steps:
         - uses: actions/checkout@v4
-        - name: Set up Python 3.9
+        - name: Set up Python 3.11
           uses: actions/setup-python@v4
           with:
-            python-version: 3.9
+            python-version: 3.11
 
         # Just test that the build works, some libraries won't compile on ARM/rPi etc
         - name: Set up QEMU

.github/workflows/test-only.yml

@@ -10,10 +10,10 @@ jobs:
       - uses: actions/checkout@v4
 
       # Mainly just for link/flake8
-      - name: Set up Python 3.10
+      - name: Set up Python 3.11
         uses: actions/setup-python@v4
         with:
-          python-version: '3.10'
+          python-version: '3.11'
 
       - name: Lint with flake8
         run: |
@@ -98,4 +98,4 @@ jobs:
 
 #export WEBDRIVER_URL=http://localhost:4444/wd/hub
 #pytest tests/fetchers/test_content.py
-#pytest tests/test_errorhandling.py
+#pytest tests/test_errorhandling.py

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

@@ -13,10 +13,10 @@ jobs:
     steps:
         - uses: actions/checkout@v4
 
-        - name: Set up Python 3.9
+        - name: Set up Python 3.11
           uses: actions/setup-python@v4
           with:
-            python-version: 3.9
+            python-version: 3.11
 
 
         - name: Test that the basic pip built package runs without error

Dockerfile

@@ -1,5 +1,5 @@
 # pip dependencies install stage
-FROM python:3.10-slim-bullseye as builder
+FROM python:3.11-slim-bullseye as builder
 
 # See `cryptography` pin comment in requirements.txt
 ARG CRYPTOGRAPHY_DONT_BUILD_RUST=1
@@ -29,7 +29,7 @@ RUN pip install --target=/dependencies playwright~=1.27.1 \
     || echo "WARN: Failed to install Playwright. The application can still run, but the Playwright option will be disabled."
 
 # Final image stage
-FROM python:3.10-slim-bullseye
+FROM python:3.11-slim-bullseye
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
     libssl1.1 \

README-pip.md

@@ -2,19 +2,44 @@
 
 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://changedetection.io)
+[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot.png" style="max-width:100%;" alt="Self-hosted web page change monitoring, list of websites with changes"  title="Self-hosted web page change monitoring, list of websites with changes"  />](https://changedetection.io)
 
 
 [**Don't have time? Let us host it for you! try our extremely affordable subscription use our proxies and support!**](https://changedetection.io) 
 
 
-#### Example use cases
+### Target specific parts of the webpage using the Visual Selector tool.
+
+Available when connected to a <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Playwright-content-fetcher">playwright content fetcher</a> (included as part of our subscription service)
+
+[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/visualselector-anim.gif" style="max-width:100%;" alt="Select parts and elements of a web page to monitor for changes"  title="Select parts and elements of a web page to monitor for changes" />](https://changedetection.io?src=pip)
+
+### Easily see what changed, examine by word, line, or individual character.
+
+[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot-diff.png" style="max-width:100%;" alt="Self-hosted web page change monitoring context difference "  title="Self-hosted web page change monitoring context difference " />](https://changedetection.io?src=pip)
+
+
+### Perform interactive browser steps
+
+Fill in text boxes, click buttons and more, setup your changedetection scenario. 
+
+Using the **Browser Steps** configuration, add basic steps before performing change detection, such as logging into websites, adding a product to a cart, accept cookie logins, entering dates and refining searches.
+
+[<img src="docs/browsersteps-anim.gif" style="max-width:100%;" alt="Website change detection with interactive browser steps, detect changes behind login and password, search queries and more"  title="Website change detection with interactive browser steps, detect changes behind login and password, search queries and more" />](https://changedetection.io?src=pip)
+
+After **Browser Steps** have been run, then visit the **Visual Selector** tab to refine the content you're interested in.
+Requires Playwright to be enabled.
+
+
+### Example use cases
 
 - Products and services have a change in pricing
 - _Out of stock notification_ and _Back In stock notification_
+- Monitor and track PDF file changes, know when a PDF file has text changes.
 - Governmental department updates (changes are often only on their websites)
 - New software releases, security advisories when you're not on their mailing list.
 - Festivals with changes
+- Discogs restock alerts and monitoring
 - Realestate listing changes
 - Know when your favourite whiskey is on sale, or other special deals are announced before anyone else
 - COVID related news from government websites
@@ -27,18 +52,34 @@ Live your data-life pro-actively, track website content changes and receive noti
 - Create RSS feeds based on changes in web content
 - Monitor HTML source code for unexpected changes, strengthen your PCI compliance
 - You have a very sensitive list of URLs to watch and you do _not_ want to use the paid alternatives. (Remember, _you_ are the product)
+- Get notified when certain keywords appear in Twitter search results
+- Proactively search for jobs, get notified when companies update their careers page, search job portals for keywords.
+- Get alerts when new job positions are open on Bamboo HR and other job platforms
+- Website defacement monitoring
+- Pokémon Card Restock Tracker / Pokémon TCG Tracker
+- RegTech - stay ahead of regulatory changes, regulatory compliance
 
 _Need an actual Chrome runner with Javascript support? We support fetching via WebDriver and Playwright!</a>_
 
 #### Key Features
 
 - Lots of trigger filters, such as "Trigger on text", "Remove text by selector", "Ignore text", "Extract text", also using regular-expressions!
-- Target elements with xPath and CSS Selectors, Easily monitor complex JSON with JSONPath or jq
+- Target elements with xPath(1.0) and CSS Selectors, Easily monitor complex JSON with JSONPath or jq
 - Switch between fast non-JS and Chrome JS based "fetchers"
+- Track changes in PDF files (Monitor text changed in the PDF, Also monitor PDF filesize and checksums)
 - Easily specify how often a site should be checked
 - Execute JS before extracting text (Good for logging in, see examples in the UI!)
 - 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.
+
+[Oxylabs](https://oxylabs.go2cloud.org/SH2d) is also an excellent proxy provider and well worth using, they offer Residental, ISP, Rotating and many other proxy types to suit your project. 
+
+Please :star: star :star: this project and help it grow! https://github.com/dgtlmoon/changedetection.io/
+
 
 
 ```bash

README.md

@@ -5,7 +5,7 @@
 _Live your data-life pro-actively._ 
 
 
-[<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://changedetection.io?src=github)
+[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot.png" style="max-width:100%;" alt="Self-hosted web site page change monitoring"  title="Self-hosted web site page change monitoring"  />](https://changedetection.io?src=github)
 
 [![Release Version][release-shield]][release-link] [![Docker Pulls][docker-pulls]][docker-link] [![License][license-shield]](LICENSE.md)
 
@@ -22,7 +22,7 @@ _Live your data-life pro-actively._
 
 Available when connected to a <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Playwright-content-fetcher">playwright content fetcher</a> (included as part of our subscription service)
 
-[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/visualselector-anim.gif" style="max-width:100%;" alt="Self-hosted web page change monitoring context difference "  title="Self-hosted web page change monitoring context difference " />](https://changedetection.io?src=github)
+[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/visualselector-anim.gif" style="max-width:100%;" alt="Select parts and elements of a web page to monitor for changes"  title="Select parts and elements of a web page to monitor for changes" />](https://changedetection.io?src=github)
 
 ### Easily see what changed, examine by word, line, or individual character.
 
@@ -35,7 +35,7 @@ Fill in text boxes, click buttons and more, setup your changedetection scenario.
 
 Using the **Browser Steps** configuration, add basic steps before performing change detection, such as logging into websites, adding a product to a cart, accept cookie logins, entering dates and refining searches.
 
-[<img src="docs/browsersteps-anim.gif" style="max-width:100%;" alt="Self-hosted web page change monitoring context difference "  title="Website change detection with interactive browser steps, login, cookies etc" />](https://changedetection.io?src=github)
+[<img src="docs/browsersteps-anim.gif" style="max-width:100%;" alt="Website change detection with interactive browser steps, detect changes behind login and password, search queries and more"  title="Website change detection with interactive browser steps, detect changes behind login and password, search queries and more" />](https://changedetection.io?src=github)
 
 After **Browser Steps** have been run, then visit the **Visual Selector** tab to refine the content you're interested in.
 Requires Playwright to be enabled.
@@ -226,7 +226,7 @@ The application also supports notifying you that it can follow this information
 
 ## Proxy Configuration
 
-See the wiki https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration , we also support using [Bright Data proxy services where possible]( https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support)
+See the wiki https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration , we also support using [Bright Data proxy services where possible](https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support) and [Oxylabs](https://oxylabs.go2cloud.org/SH2d) proxy services.
 
 ## Raspberry Pi support?
 

changedetectionio/__init__.py

@@ -38,7 +38,7 @@ from flask_paginate import Pagination, get_page_parameter
 from changedetectionio import html_tools
 from changedetectionio.api import api_v1
 
-__version__ = '0.45.2'
+__version__ = '0.45.3'
 
 from changedetectionio.store import BASE_URL_NOT_SET_TEXT
 

changedetectionio/html_tools.py

@@ -7,17 +7,35 @@ 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>"
 
+PERL_STYLE_REGEX = r'^/(.*?)/([a-z]*)?$'
 # 'price' , 'lowPrice', 'highPrice' are usually under here
-# all of those may or may not appear on different websites
-LD_JSON_PRODUCT_OFFER_SELECTOR = "json:$..offers"
+# All of those may or may not appear on different websites - I didnt find a way todo case-insensitive searching here
+LD_JSON_PRODUCT_OFFER_SELECTORS = ["json:$..offers", "json:$..Offers"]
 
 class JSONNotFound(ValueError):
     def __init__(self, msg):
         ValueError.__init__(self, msg)
-        
+
+
+# Doesn't look like python supports forward slash auto enclosure in re.findall
+# So convert it to inline flag "(?i)foobar" type configuration
+def perl_style_slash_enclosed_regex_to_options(regex):
+
+    res = re.search(PERL_STYLE_REGEX, regex, re.IGNORECASE)
+
+    if res:
+        flags = res.group(2) if res.group(2) else 'i'
+        regex = f"(?{flags}){res.group(1)}"
+    else:
+        # Fall back to just ignorecase as an option
+        regex = f"(?i){regex}"
+
+    return regex
+
 # 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):
     soup = BeautifulSoup(html_content, "html.parser")
@@ -144,7 +162,6 @@ def extract_json_as_string(content, json_filter, ensure_is_ldjson_info_type=None
 
         # Foreach <script json></script> blob.. just return the first that matches json_filter
         # As a last resort, try to parse the whole <body>
-        s = []
         soup = BeautifulSoup(content, 'html.parser')
 
         if ensure_is_ldjson_info_type:
@@ -170,13 +187,24 @@ def extract_json_as_string(content, json_filter, ensure_is_ldjson_info_type=None
         
         for json_data in bs_jsons:
             stripped_text_from_html = _parse_json(json_data, json_filter)
+
             if ensure_is_ldjson_info_type:
                 # Could sometimes be list, string or something else random
                 if isinstance(json_data, dict):
                     # If it has LD JSON 'key' @type, and @type is 'product', and something was found for the search
                     # (Some sites have multiple of the same ld+json @type='product', but some have the review part, some have the 'price' part)
-                    if json_data.get('@type', False) and json_data.get('@type','').lower() == ensure_is_ldjson_info_type.lower() and stripped_text_from_html:
-                        break
+                    # @type could also be a list (Product, SubType)
+                    # LD_JSON auto-extract also requires some content PLUS the ldjson to be present
+                    # 1833 - could be either str or dict, should not be anything else
+                    if json_data.get('@type') and stripped_text_from_html:
+                        try:
+                            if json_data.get('@type') == str or json_data.get('@type') == dict:
+                                types = [json_data.get('@type')] if isinstance(json_data.get('@type'), str) else json_data.get('@type')
+                                if ensure_is_ldjson_info_type.lower() in [x.lower().strip() for x in types]:
+                                    break
+                        except:
+                            continue
+
             elif stripped_text_from_html:
                 break
 
@@ -195,23 +223,14 @@ def strip_ignore_text(content, wordlist, mode="content"):
     output = []
     ignore_text = []
     ignore_regex = []
-
     ignored_line_numbers = []
 
     for k in wordlist:
         # Is it a regex?
-        x = re.search('^\/(.*)\/(.*)', k.strip())
-        if x:
-            # Starts with / but doesn't look like a regex
-            p = x.group(1)
-            try:
-                # @Todo python regex options can go before the regex str, but not really many of the options apply on a per-line basis
-                ignore_regex.append(re.compile(rf"{p}", re.IGNORECASE))
-            except Exception as e:
-                # Badly formed regex, treat as text
-                ignore_text.append(k.strip())
+        res = re.search(PERL_STYLE_REGEX, k, re.IGNORECASE)
+        if res:
+            ignore_regex.append(re.compile(perl_style_slash_enclosed_regex_to_options(k)))
         else:
-            # Had a / but doesn't work as regex
             ignore_text.append(k.strip())
 
     for line in content.splitlines():
@@ -275,9 +294,18 @@ def html_to_text(html_content: str, render_anchor_tag_content=False) -> str:
 
 # Does LD+JSON exist with a @type=='product' and a .price set anywhere?
 def has_ldjson_product_info(content):
+    pricing_data = ''
+
     try:
-        pricing_data = extract_json_as_string(content=content, json_filter=LD_JSON_PRODUCT_OFFER_SELECTOR, ensure_is_ldjson_info_type="product")
-    except JSONNotFound as e:
+        if not 'application/ld+json' in content:
+            return False
+
+        for filter in LD_JSON_PRODUCT_OFFER_SELECTORS:
+            pricing_data += extract_json_as_string(content=content,
+                                                  json_filter=filter,
+                                                  ensure_is_ldjson_info_type="product")
+
+    except Exception as e:
         # Totally fine
         return False
     x=bool(pricing_data)

changedetectionio/processors/text_json_diff.py

@@ -11,17 +11,19 @@ from changedetectionio import content_fetcher, html_tools
 from changedetectionio.blueprint.price_data_follower import PRICE_DATA_TRACK_ACCEPT, PRICE_DATA_TRACK_REJECT
 from copy import deepcopy
 from . import difference_detection_processor
+from ..html_tools import PERL_STYLE_REGEX
 
 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 
-
-name =  'Webpage Text/HTML, JSON and PDF changes'
+name = 'Webpage Text/HTML, JSON and PDF changes'
 description = 'Detects all text changes where possible'
+json_filter_prefixes = ['json:', 'jq:']
 
 class FilterNotFoundInResponse(ValueError):
     def __init__(self, msg):
         ValueError.__init__(self, msg)
 
+
 class PDFToHTMLToolNotFound(ValueError):
     def __init__(self, msg):
         ValueError.__init__(self, msg)
@@ -37,19 +39,6 @@ class perform_site_check(difference_detection_processor):
         super().__init__(*args, **kwargs)
         self.datastore = datastore
 
-    # Doesn't look like python supports forward slash auto enclosure in re.findall
-    # So convert it to inline flag "foobar(?i)" type configuration
-    def forward_slash_enclosed_regex_to_options(self, regex):
-        res = re.search(r'^/(.*?)/(\w+)$', regex, re.IGNORECASE)
-
-        if res:
-            regex = res.group(1)
-            regex += '(?{})'.format(res.group(2))
-        else:
-            regex += '(?{})'.format('i')
-
-        return regex
-
     def run(self, uuid, skip_when_checksum_same=True, preferred_proxy=None):
         changed_detected = False
         screenshot = False  # as bytes
@@ -135,7 +124,8 @@ class perform_site_check(difference_detection_processor):
         # requests for PDF's, images etc should be passwd the is_binary flag
         is_binary = watch.is_pdf
 
-        fetcher.run(url, timeout, request_headers, request_body, request_method, ignore_status_codes, watch.get('include_filters'), is_binary=is_binary)
+        fetcher.run(url, timeout, request_headers, request_body, request_method, ignore_status_codes, watch.get('include_filters'),
+                    is_binary=is_binary)
         fetcher.quit()
 
         self.screenshot = fetcher.screenshot
@@ -151,7 +141,6 @@ class perform_site_check(difference_detection_processor):
             if update_obj['previous_md5_before_filters'] == watch.get('previous_md5_before_filters'):
                 raise content_fetcher.checksumFromPreviousCheckWasTheSame()
 
-
         # Fetching complete, now filters
         # @todo move to class / maybe inside of fetcher abstract base?
 
@@ -207,7 +196,7 @@ class perform_site_check(difference_detection_processor):
 
         # Inject a virtual LD+JSON price tracker rule
         if watch.get('track_ldjson_price_data', '') == PRICE_DATA_TRACK_ACCEPT:
-            include_filters_rule.append(html_tools.LD_JSON_PRODUCT_OFFER_SELECTOR)
+            include_filters_rule += html_tools.LD_JSON_PRODUCT_OFFER_SELECTORS
 
         has_filter_rule = len(include_filters_rule) and len(include_filters_rule[0].strip())
         has_subtractive_selectors = len(subtractive_selectors) and len(subtractive_selectors[0].strip())
@@ -225,14 +214,11 @@ class perform_site_check(difference_detection_processor):
                 pass
 
         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 is_html or is_source:
 
             # CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text
@@ -283,7 +269,6 @@ class perform_site_check(difference_detection_processor):
         # Re #340 - return the content before the 'ignore text' was applied
         text_content_before_ignored_filter = stripped_text_from_html.encode('utf-8')
 
-
         # @todo whitespace coming from missing rtrim()?
         # stripped_text_from_html could be based on their preferences, replace the processed text with only that which they want to know about.
         # Rewrite's the processing text based on only what diff result they want to see
@@ -293,13 +278,13 @@ class perform_site_check(difference_detection_processor):
             # needs to not include (added) etc or it may get used twice
             # Replace the processed text with the preferred result
             rendered_diff = diff.render_diff(previous_version_file_contents=watch.get_last_fetched_before_filters(),
-                                                       newest_version_file_contents=stripped_text_from_html,
-                                                       include_equal=False,  # not the same lines
-                                                       include_added=watch.get('filter_text_added', True),
-                                                       include_removed=watch.get('filter_text_removed', True),
-                                                       include_replaced=watch.get('filter_text_replaced', True),
-                                                       line_feed_sep="\n",
-                                                       include_change_type_prefix=False)
+                                             newest_version_file_contents=stripped_text_from_html,
+                                             include_equal=False,  # not the same lines
+                                             include_added=watch.get('filter_text_added', True),
+                                             include_removed=watch.get('filter_text_removed', True),
+                                             include_replaced=watch.get('filter_text_replaced', True),
+                                             line_feed_sep="\n",
+                                             include_change_type_prefix=False)
 
             watch.save_last_fetched_before_filters(text_content_before_ignored_filter)
 
@@ -340,16 +325,25 @@ class perform_site_check(difference_detection_processor):
             regex_matched_output = []
             for s_re in extract_text:
                 # incase they specified something in '/.../x'
-                regex = self.forward_slash_enclosed_regex_to_options(s_re)
-                result = re.findall(regex.encode('utf-8'), stripped_text_from_html)
+                if re.search(PERL_STYLE_REGEX, s_re, re.IGNORECASE):
+                    regex = html_tools.perl_style_slash_enclosed_regex_to_options(s_re)
+                    result = re.findall(regex.encode('utf-8'), stripped_text_from_html)
 
-                for l in result:
-                    if type(l) is tuple:
-                        # @todo - some formatter option default (between groups)
-                        regex_matched_output += list(l) + [b'\n']
-                    else:
-                        # @todo - some formatter option default (between each ungrouped result)
-                        regex_matched_output += [l] + [b'\n']
+                    for l in result:
+                        if type(l) is tuple:
+                            # @todo - some formatter option default (between groups)
+                            regex_matched_output += list(l) + [b'\n']
+                        else:
+                            # @todo - some formatter option default (between each ungrouped result)
+                            regex_matched_output += [l] + [b'\n']
+                else:
+                    # Doesnt look like regex, just hunt for plaintext and return that which matches
+                    # `stripped_text_from_html` will be bytes, so we must encode s_re also to bytes
+                    r = re.compile(re.escape(s_re.encode('utf-8')), re.IGNORECASE)
+                    res = r.findall(stripped_text_from_html)
+                    if res:
+                        for match in res:
+                            regex_matched_output += [match] + [b'\n']
 
             # Now we will only show what the regex matched
             stripped_text_from_html = b''

changedetectionio/templates/edit.html

@@ -378,15 +378,16 @@ Unavailable") }}
                         {{ render_field(form.extract_text, rows=5, placeholder="\d+ online") }}
                         <span class="pure-form-message-inline">
                     <ul>
-                        <li>Extracts text in the final output (line by line) after other filters using regular expressions;
+                        <li>Extracts text in the final output (line by line) after other filters using regular expressions or string match;
                             <ul>
                                 <li>Regular expression &dash; example <code>/reports.+?2022/i</code></li>
+                                <li>Don't forget to consider the white-space at the start of a line <code>/.+?reports.+?2022/i</code></li>
                                 <li>Use <code>//(?aiLmsux))</code> type flags (more <a href="https://docs.python.org/3/library/re.html#index-15">information here</a>)<br></li>
                                 <li>Keyword example &dash; example <code>Out of stock</code></li>
                                 <li>Use groups to extract just that text &dash; example <code>/reports.+?(\d+)/i</code> returns a list of years only</li>
                             </ul>
                         </li>
-                        <li>One line per regular-expression/ string match</li>
+                        <li>One line per regular-expression/string match</li>
                     </ul>
                         </span>
                     </div>

changedetectionio/tests/test_automatic_follow_ldjson_price.py

@@ -2,7 +2,8 @@
 
 import time
 from flask import url_for
-from .util import live_server_setup, extract_UUID_from_client, extract_api_key_from_UI
+from .util import live_server_setup, extract_UUID_from_client, extract_api_key_from_UI, wait_for_all_checks
+
 
 def set_response_with_ldjson():
     test_return_data = """<html>
@@ -27,7 +28,7 @@ def set_response_with_ldjson():
            "description":"You dont need it",
            "mpn":"111111",
            "sku":"22222",
-           "offers":{
+           "Offers":{
               "@type":"AggregateOffer",
               "lowPrice":8097000,
               "highPrice":8099900,
@@ -75,12 +76,11 @@ def set_response_without_ldjson():
         f.write(test_return_data)
     return None
 
-# actually only really used by the distll.io importer, but could be handy too
-def test_check_ldjson_price_autodetect(client, live_server):
+def test_setup(client, live_server):
     live_server_setup(live_server)
 
-    # Give the endpoint time to spin up
-    time.sleep(1)
+# actually only really used by the distll.io importer, but could be handy too
+def test_check_ldjson_price_autodetect(client, live_server):
 
     set_response_with_ldjson()
 
@@ -92,7 +92,7 @@ def test_check_ldjson_price_autodetect(client, live_server):
         follow_redirects=True
     )
     assert b"1 Imported" in res.data
-    time.sleep(3)
+    wait_for_all_checks(client)
 
     # Should get a notice that it's available
     res = client.get(url_for("index"))
@@ -102,11 +102,11 @@ def test_check_ldjson_price_autodetect(client, live_server):
     uuid = extract_UUID_from_client(client)
 
     client.get(url_for('price_data_follower.accept', uuid=uuid, follow_redirects=True))
-    time.sleep(2)
+    wait_for_all_checks(client)
 
     # Trigger a check
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
-    time.sleep(2)
+    wait_for_all_checks(client)
     # Offer should be gone
     res = client.get(url_for("index"))
     assert b'Embedded price data' not in res.data
@@ -138,9 +138,97 @@ def test_check_ldjson_price_autodetect(client, live_server):
         follow_redirects=True
     )
     assert b"1 Imported" in res.data
-    time.sleep(3)
+    wait_for_all_checks(client)
     res = client.get(url_for("index"))
     assert b'ldjson-price-track-offer' not in res.data
     
     ##########################################################################################
     client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+
+
+def _test_runner_check_bad_format_ignored(live_server, client, has_ldjson_price_data):
+
+    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
+    wait_for_all_checks(client)
+
+    for k,v in client.application.config.get('DATASTORE').data['watching'].items():
+        assert v.get('last_error') == False
+        assert v.get('has_ldjson_price_data') == has_ldjson_price_data
+
+
+    ##########################################################################################
+    client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+
+
+def test_bad_ldjson_is_correctly_ignored(client, live_server):
+    #live_server_setup(live_server)
+    test_return_data = """
+            <html>
+            <head>
+                <script type="application/ld+json">
+                    {
+                        "@context": "http://schema.org",
+                        "@type": ["Product", "SubType"],
+                        "name": "My test product",
+                        "description": "",
+                        "offers": {
+                            "note" : "You can see the case-insensitive OffERS key, it should work",
+                            "@type": "Offer",
+                            "offeredBy": {
+                                "@type": "Organization",
+                                "name":"Person",
+                                "telephone":"+1 999 999 999"
+                            },
+                            "price": "1",
+                            "priceCurrency": "EUR",
+                            "url": "/some/url"
+                        }
+                    }
+                </script>
+            </head>
+            <body>
+            <div class="yes">Some extra stuff</div>
+            </body></html>
+     """
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(test_return_data)
+
+    _test_runner_check_bad_format_ignored(live_server=live_server, client=client, has_ldjson_price_data=True)
+    test_return_data = """
+            <html>
+            <head>
+                <script type="application/ld+json">
+                    {
+                        "@context": "http://schema.org",
+                        "@type": ["Product", "SubType"],
+                        "name": "My test product",
+                        "description": "",
+                        "BrokenOffers": {
+                            "@type": "Offer",
+                            "offeredBy": {
+                                "@type": "Organization",
+                                "name":"Person",
+                                "telephone":"+1 999 999 999"
+                            },
+                            "price": "1",
+                            "priceCurrency": "EUR",
+                            "url": "/some/url"
+                        }
+                    }
+                </script>
+            </head>
+            <body>
+            <div class="yes">Some extra stuff</div>
+            </body></html>
+     """
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(test_return_data)
+
+    _test_runner_check_bad_format_ignored(live_server=live_server, client=client, has_ldjson_price_data=False)
+

changedetectionio/tests/test_extract_regex.py

@@ -2,7 +2,7 @@
 
 import time
 from flask import url_for
-from .util import live_server_setup
+from .util import live_server_setup, wait_for_all_checks
 
 from ..html_tools import *
 
@@ -55,6 +55,8 @@ def set_multiline_response():
      </p>
      
      <div>aaand something lines</div>
+     <br>
+     <div>and this should be</div>
      </body>
      </html>
     """
@@ -66,11 +68,10 @@ def set_multiline_response():
 
 
 def test_setup(client, live_server):
-
     live_server_setup(live_server)
 
 def test_check_filter_multiline(client, live_server):
-
+    #live_server_setup(live_server)
     set_multiline_response()
 
     # Add our URL to the import page
@@ -82,14 +83,15 @@ def test_check_filter_multiline(client, live_server):
     )
     assert b"1 Imported" in res.data
 
-    time.sleep(3)
+    wait_for_all_checks(client)
 
     # 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": '',
-              'extract_text': '/something.+?6 billion.+?lines/si',
+              # Test a regex and a plaintext
+              'extract_text': '/something.+?6 billion.+?lines/si\r\nand this should be',
               "url": test_url,
               "tags": "",
               "headers": "",
@@ -99,13 +101,19 @@ def test_check_filter_multiline(client, live_server):
     )
 
     assert b"Updated watch." in res.data
-    time.sleep(3)
+    wait_for_all_checks(client)
+
+    res = client.get(url_for("index"))
+
+    # Issue 1828
+    assert b'not at the start of the expression' not in res.data
 
     res = client.get(
         url_for("preview_page", uuid="first"),
         follow_redirects=True
     )
-
+    # Plaintext that doesnt look like a regex should match also
+    assert b'and this should be' in res.data
 
     assert b'<div class="">Something' in res.data
     assert b'<div class="">across 6 billion multiple' in res.data
@@ -115,14 +123,11 @@ def test_check_filter_multiline(client, live_server):
     assert b'aaand something lines' not in res.data
 
 def test_check_filter_and_regex_extract(client, live_server):
-    sleep_time_for_fetch_thread = 3
+    
     include_filters = ".changetext"
 
     set_original_response()
 
-    # 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(
@@ -132,19 +137,15 @@ def test_check_filter_and_regex_extract(client, live_server):
     )
     assert b"1 Imported" in res.data
 
-    time.sleep(1)
-    # 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)
+    wait_for_all_checks(client)
 
     # 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,
-              'extract_text': '\d+ online\r\n\d+ guests\r\n/somecase insensitive \d+/i\r\n/somecase insensitive (345\d)/i',
+              'extract_text': '/\d+ online/\r\n/\d+ guests/\r\n/somecase insensitive \d+/i\r\n/somecase insensitive (345\d)/i\r\n/issue1828.+?2022/i',
               "url": test_url,
               "tags": "",
               "headers": "",
@@ -155,8 +156,13 @@ def test_check_filter_and_regex_extract(client, live_server):
 
     assert b"Updated watch." in res.data
 
+
     # Give the thread time to pick it up
-    time.sleep(sleep_time_for_fetch_thread)
+    wait_for_all_checks(client)
+
+    res = client.get(url_for("index"))
+    #issue 1828
+    assert b'not at the start of the expression' not in res.data
 
     #  Make a change
     set_modified_response()
@@ -164,7 +170,7 @@ def test_check_filter_and_regex_extract(client, live_server):
     # 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)
+    wait_for_all_checks(client)
 
     # It should have 'unviewed' still
     # Because it should be looking at only that 'sametext' id

changedetectionio/tests/test_trigger_regex.py

@@ -2,7 +2,7 @@
 
 import time
 from flask import url_for
-from . util import live_server_setup
+from .util import live_server_setup, wait_for_all_checks
 
 
 def set_original_ignore_response():
@@ -26,13 +26,8 @@ def test_trigger_regex_functionality(client, live_server):
 
     live_server_setup(live_server)
 
-    sleep_time_for_fetch_thread = 3
-
     set_original_ignore_response()
 
-    # 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(
@@ -43,7 +38,7 @@ def test_trigger_regex_functionality(client, live_server):
     assert b"1 Imported" in res.data
 
     # Give the thread time to pick it up
-    time.sleep(sleep_time_for_fetch_thread)
+    wait_for_all_checks(client)
 
     # It should report nothing found (just a new one shouldnt have anything)
     res = client.get(url_for("index"))
@@ -57,7 +52,7 @@ def test_trigger_regex_functionality(client, live_server):
               "fetch_backend": "html_requests"},
         follow_redirects=True
     )
-    time.sleep(sleep_time_for_fetch_thread)
+    wait_for_all_checks(client)
     # so that we set the state to 'unviewed' after all the edits
     client.get(url_for("diff_history_page", uuid="first"))
 
@@ -65,7 +60,7 @@ def test_trigger_regex_functionality(client, live_server):
         f.write("some new noise")
 
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
-    time.sleep(sleep_time_for_fetch_thread)
+    wait_for_all_checks(client)
 
     # It should report nothing found (nothing should match the regex)
     res = client.get(url_for("index"))
@@ -75,7 +70,7 @@ def test_trigger_regex_functionality(client, live_server):
         f.write("regex test123<br>\nsomething 123")
 
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
-    time.sleep(sleep_time_for_fetch_thread)
+    wait_for_all_checks(client)
     res = client.get(url_for("index"))
     assert b'unviewed' in res.data
 

runtime.txt

@@ -1 +1 @@
-python-3.9.15
+python-3.11.5

setup.py

@@ -41,7 +41,7 @@ setup(
     include_package_data=True,
     install_requires=install_requires,
     license="Apache License 2.0",
-    python_requires=">= 3.6",
+    python_requires=">= 3.7",
     classifiers=['Intended Audience :: Customer Service',
                  'Intended Audience :: Developers',
                  'Intended Audience :: Education',