Merge branch 'master' into windows-diff-file-handling-improvements

Dockerfile

@@ -26,6 +26,11 @@ RUN pip install --target=/dependencies -r /requirements.txt
 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."
 
+
+RUN pip install --target=/dependencies jq~=1.3 \
+    || echo "WARN: Failed to install JQ. The application can still run, but the Jq: filter option will be disabled."
+
+
 # Final image stage
 FROM python:3.8-slim
 

MANIFEST.in

@@ -2,6 +2,7 @@ recursive-include changedetectionio/api *
 recursive-include changedetectionio/templates *
 recursive-include changedetectionio/static *
 recursive-include changedetectionio/model *
+recursive-include changedetectionio/tests *
 include changedetection.py
 global-exclude *.pyc
 global-exclude node_modules

README.md

@@ -121,8 +121,8 @@ See the wiki for more information https://github.com/dgtlmoon/changedetection.io
 
 
 ## Filters
-XPath, JSONPath, jq, and CSS support comes baked in! You can be as specific as you need, use XPath exported from various XPath element query creation tools.
 
+XPath, JSONPath, jq, and CSS support comes baked in! You can be as specific as you need, use XPath exported from various XPath element query creation tools. 
 (We support LXML `re:test`, `re:math` and `re:replace`.)
 
 ## Notifications
@@ -161,46 +161,14 @@ This will re-parse the JSON and apply formatting to the text, making it super ea
 
 ### JSONPath or jq?
 
-For more complex parsing, filtering, and modifying of JSON data, jq is recommended due to the built-in operators and functions. Refer to the [documentation](https://stedolan.github.io/jq/manual/) for more information on jq.
+For more complex parsing, filtering, and modifying of JSON data, jq is recommended due to the built-in operators and functions. Refer to the [documentation](https://stedolan.github.io/jq/manual/) for more specifc information on jq.
 
-The example below adds the price in dollars to each item in the JSON data, and then filters to only show items that are greater than 10.
+One big advantage of `jq` is that you can use logic in your JSON filter, such as filters to only show items that have a value greater than/less than etc.
 
-#### Sample input data from API
+See the wiki https://github.com/dgtlmoon/changedetection.io/wiki/JSON-Selector-Filter-help for more information and examples
-```
-{
-    "items": [
-        {
-           "name": "Product A",
-           "priceInCents": 2500
-        },
-        {
-           "name": "Product B",
-           "priceInCents": 500
-        },
-        {
-           "name": "Product C",
-           "priceInCents": 2000
-        }
-    ]
-}
-```
 
-#### Sample jq
+Note: `jq` library must be added separately (`pip3 install jq`)
-`jq:.items[] | . + { "priceInDollars": (.priceInCents / 100) } | select(.priceInDollars > 10)`
 
-#### Sample output data
-```
-{
-  "name": "Product A",
-  "priceInCents": 2500,
-  "priceInDollars": 25
-}
-{
-  "name": "Product C",
-  "priceInCents": 2000,
-  "priceInDollars": 20
-}
-```
 
 ### Parse JSON embedded in HTML!
 

changedetectionio/__init__.py

@@ -33,7 +33,7 @@ from flask_wtf import CSRFProtect
 from changedetectionio import html_tools
 from changedetectionio.api import api_v1
 
-__version__ = '0.39.20.1'
+__version__ = '0.39.20.3'
 
 datastore = None
 
@@ -636,20 +636,27 @@ def changedetection_app(config=None, datastore_o=None):
             # Only works reliably with Playwright
             visualselector_enabled = os.getenv('PLAYWRIGHT_DRIVER_URL', False) and default['fetch_backend'] == 'html_webdriver'
 
+            # JQ is difficult to install on windows and must be manually added (outside requirements.txt)
+            jq_support = True
+            try:
+                import jq
+            except ModuleNotFoundError:
+                jq_support = False
 
             output = render_template("edit.html",
-                                     uuid=uuid,
-                                     watch=datastore.data['watching'][uuid],
-                                     form=form,
-                                     has_empty_checktime=using_default_check_time,
-                                     has_default_notification_urls=True if len(datastore.data['settings']['application']['notification_urls']) else False,
-                                     using_global_webdriver_wait=default['webdriver_delay'] is None,
                                      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,
+                                     jq_support=jq_support,
+                                     playwright_enabled=os.getenv('PLAYWRIGHT_DRIVER_URL', False),
                                      settings_application=datastore.data['settings']['application'],
+                                     using_global_webdriver_wait=default['webdriver_delay'] is None,
+                                     uuid=uuid,
                                      visualselector_data_is_ready=visualselector_data_is_ready,
                                      visualselector_enabled=visualselector_enabled,
-                                     playwright_enabled=os.getenv('PLAYWRIGHT_DRIVER_URL', False)
+                                     watch=datastore.data['watching'][uuid],
                                      )
 
         return output
@@ -809,8 +816,10 @@ def changedetection_app(config=None, datastore_o=None):
 
         newest_file = history[dates[-1]]
 
+        # Read as binary and force decode as UTF-8
+        # Windows may fail decode in python if we just use 'r' mode (chardet decode exception)
         try:
-            with open(newest_file, 'r') as f:
+            with open(newest_file, 'r', encoding='utf-8', errors='ignore') as f:
                 newest_version_file_contents = f.read()
         except Exception as e:
             newest_version_file_contents = "Unable to read {}.\n".format(newest_file)
@@ -823,7 +832,7 @@ def changedetection_app(config=None, datastore_o=None):
             previous_file = history[dates[-2]]
 
         try:
-            with open(previous_file, 'r') as f:
+            with open(previous_file, 'r', encoding='utf-8', errors='ignore') as f:
                 previous_version_file_contents = f.read()
         except Exception as e:
             previous_version_file_contents = "Unable to read {}.\n".format(previous_file)
@@ -900,7 +909,7 @@ def changedetection_app(config=None, datastore_o=None):
         timestamp = list(watch.history.keys())[-1]
         filename = watch.history[timestamp]
         try:
-            with open(filename, 'r') as f:
+            with open(filename, 'r', encoding='utf-8', errors='ignore') as f:
                 tmp = f.readlines()
 
                 # Get what needs to be highlighted

changedetectionio/forms.py

@@ -303,12 +303,16 @@ class ValidateCSSJSONXPATHInput(object):
 
                 # Re #265 - maybe in the future fetch the page and offer a
                 # warning/notice that its possible the rule doesnt yet match anything?
-
-            if 'jq:' in line:
                 if not self.allow_json:
                     raise ValidationError("jq not permitted in this field!")
 
+            if 'jq:' in line:
+                try:
                     import jq
+                except ModuleNotFoundError:
+                    # `jq` requires full compilation in windows and so isn't generally available
+                    raise ValidationError("jq not support not found")
+
                 input = line.replace('jq:', '')
 
                 try:

changedetectionio/html_tools.py

@@ -1,12 +1,11 @@
-import json
-from typing import List
 
 from bs4 import BeautifulSoup
-from jsonpath_ng.ext import parse
-import jq
-import re
 from inscriptis import get_text
 from inscriptis.model.config import ParserConfig
+from jsonpath_ng.ext import parse
+from typing import List
+import json
+import re
 
 class FilterNotFoundInResponse(ValueError):
     def __init__(self, msg):
@@ -85,9 +84,18 @@ def _parse_json(json_data, json_filter):
         jsonpath_expression = parse(json_filter.replace('json:', ''))
         match = jsonpath_expression.find(json_data)
         return _get_stripped_text_from_json_match(match)
+
     if 'jq:' in json_filter:
+
+        try:
+            import jq
+        except ModuleNotFoundError:
+            # `jq` requires full compilation in windows and so isn't generally available
+            raise Exception("jq not support not found")
+
         jq_expression = jq.compile(json_filter.replace('jq:', ''))
         match = jq_expression.input(json_data).all()
+
         return _get_stripped_text_from_json_match(match)
 
 def _get_stripped_text_from_json_match(match):

changedetectionio/model/Watch.py

@@ -151,28 +151,30 @@ class model(dict):
         import uuid
         import logging
 
-        output_path = "{}/{}".format(self.__datastore_path, self['uuid'])
+        output_path = os.path.join(self.__datastore_path, self['uuid'])
 
         self.ensure_data_dir_exists()
+        snapshot_fname = os.path.join(output_path, str(uuid.uuid4()))
 
-        snapshot_fname = "{}/{}.stripped.txt".format(output_path, uuid.uuid4())
         logging.debug("Saving history text {}".format(snapshot_fname))
 
+        # in /diff/ and /preview/ we are going to assume for now that it's UTF-8 when reading
+        # most sites are utf-8 and some are even broken utf-8
         with open(snapshot_fname, 'wb') as f:
             f.write(contents)
             f.close()
 
         # Append to index
         # @todo check last char was \n
-        index_fname = "{}/history.txt".format(output_path)
+        index_fname = os.path.join(output_path, "history.txt")
         with open(index_fname, 'a') as f:
             f.write("{},{}\n".format(timestamp, snapshot_fname))
             f.close()
 
         self.__newest_history_key = timestamp
-        self.__history_n+=1
+        self.__history_n += 1
 
-        #@todo bump static cache of the last timestamp so we dont need to examine the file to set a proper ''viewed'' status
+        # @todo bump static cache of the last timestamp so we dont need to examine the file to set a proper ''viewed'' status
         return snapshot_fname
 
     @property

changedetectionio/run_all_tests.sh

@@ -23,6 +23,13 @@ export BASE_URL="https://really-unique-domain.io"
 pytest tests/test_notification.py
 
 
+## JQ + JSON: filter test
+# jq is not available on windows and we should just test it when the package is installed
+# this will re-test with jq support
+pip3 install jq~=1.3
+pytest tests/test_jsonpath_jq_selector.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
 

changedetectionio/templates/edit.html

@@ -184,10 +184,14 @@ User-Agent: wonderbra 1.0") }}
                         <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>.
+                        <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).
                             <ul>
                                 <li>JSONPath: Prefix with <code>json:</code>, use <code>json:$</code> to force re-formatting if required,  <a href="https://jsonpath.com/" target="new">test your JSONPath here</a>.</li>
+                                {% if jq_support %}
                                 <li>jq: Prefix with <code>jq:</code> and <a href="https://jqplay.org/" target="new">test your jq here</a>. Using <a href="https://stedolan.github.io/jq/" target="new">jq</a> allows for complex filtering and processing of JSON data with built-in functions, regex, filtering, and more. See examples and documentation <a href="https://stedolan.github.io/jq/manual/" target="new">here</a>.</li>
+                                {% else %}
+                                <li>jq support not installed</li>
+                                {% endif %}
                             </ul>
                         </li>
                         <li>XPath - Limit text to this XPath rule, simply start with a forward-slash,
@@ -198,7 +202,7 @@ User-Agent: wonderbra 1.0") }}
                             </ul>
                             </li>
                     </ul>
-                    Please be sure that you thoroughly understand how to write CSS, JSONPath, XPath, or jq selector rules before filing an issue on GitHub! <a
+                    Please be sure that you thoroughly understand how to write CSS, JSONPath, XPath{% if jq_support %}, or jq selector{%endif%} rules before filing an issue on GitHub! <a
                                 href="https://github.com/dgtlmoon/changedetection.io/wiki/CSS-Selector-help">here for more CSS selector help</a>.<br/>
                 </span>
                     </div>

changedetectionio/tests/test_jsonpath_jq_selector.py

@@ -5,7 +5,12 @@ import time
 from flask import url_for, escape
 from . util import live_server_setup
 import pytest
+jq_support = True
 
+try:
+    import jq
+except ModuleNotFoundError:
+    jq_support = False
 
 def test_setup(live_server):
     live_server_setup(live_server)
@@ -40,13 +45,14 @@ and it can also be repeated
     assert text == "23.5"
 
     # also check for jq
+    if jq_support:
         text = html_tools.extract_json_as_string(content, "jq:.offers.price")
         assert text == "23.5"
 
-    text = html_tools.extract_json_as_string('{"id":5}', "json:$.id")
+        text = html_tools.extract_json_as_string('{"id":5}', "jq:.id")
         assert text == "5"
 
-    text = html_tools.extract_json_as_string('{"id":5}', "jq:.id")
+    text = html_tools.extract_json_as_string('{"id":5}', "json:$.id")
     assert text == "5"
 
     # When nothing at all is found, it should throw JSONNOTFound
@@ -54,6 +60,7 @@ and it can also be repeated
     with pytest.raises(html_tools.JSONNotFound) as e_info:
         html_tools.extract_json_as_string('COMPLETE GIBBERISH, NO JSON!', "json:$.id")
 
+    if jq_support:
         with pytest.raises(html_tools.JSONNotFound) as e_info:
             html_tools.extract_json_as_string('COMPLETE GIBBERISH, NO JSON!', "jq:.id")
 
@@ -271,6 +278,7 @@ def test_check_jsonpath_filter(client, live_server):
     check_json_filter('json:boss.name', client, live_server)
 
 def test_check_jq_filter(client, live_server):
+    if jq_support:
         check_json_filter('jq:.boss.name', client, live_server)
 
 def check_json_filter_bool_val(json_filter, client, live_server):
@@ -329,6 +337,7 @@ def test_check_jsonpath_filter_bool_val(client, live_server):
     check_json_filter_bool_val("json:$['available']", client, live_server)
 
 def test_check_jq_filter_bool_val(client, live_server):
+    if jq_support:
         check_json_filter_bool_val("jq:.available", client, live_server)
 
 # Re #265 - Extended JSON selector test
@@ -408,4 +417,5 @@ def test_check_jsonpath_ext_filter(client, live_server):
     check_json_ext_filter('json:$[?(@.status==Sold)]', client, live_server)
 
 def test_check_jq_ext_filter(client, live_server):
+    if jq_support:
         check_json_ext_filter('jq:.[] | select(.status | contains("Sold"))', client, live_server)

changedetectionio/tests/visualselector/test_fetch_data.py

@@ -13,9 +13,9 @@ def test_visual_selector_content_ready(client, live_server):
     live_server_setup(live_server)
     time.sleep(1)
 
-    # Add our URL to the import page, maybe better to use something we control?
+    # Add our URL to the import page, because the docker container (playwright/selenium) wont be able to connect to our usual test url
-    # We use an external URL because the docker container is too difficult to setup to connect back to the pytest socket
+    test_url = "https://changedetection.io/ci-test/test-runjs.html"
-    test_url = 'https://news.ycombinator.com'
+
     res = client.post(
         url_for("form_quick_watch_add"),
         data={"url": test_url, "tag": '', 'edit_and_watch_submit_button': 'Edit > Watch'},
@@ -25,13 +25,27 @@ def test_visual_selector_content_ready(client, live_server):
 
     res = client.post(
         url_for("edit_page", uuid="first", unpause_on_save=1),
-        data={"css_filter": ".does-not-exist", "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_webdriver"},
+        data={
+              "url": test_url,
+              "tag": "",
+              "headers": "",
+              'fetch_backend': "html_webdriver",
+              'webdriver_js_execute_code': 'document.querySelector("button[name=test-button]").click();'
+        },
         follow_redirects=True
     )
     assert b"unpaused" in res.data
     time.sleep(1)
     wait_for_all_checks(client)
     uuid = extract_UUID_from_client(client)
+
+    # Check the JS execute code before extract worked
+    res = client.get(
+        url_for("preview_page", uuid="first"),
+        follow_redirects=True
+    )
+    assert b'I smell JavaScript' in res.data
+
     assert os.path.isfile(os.path.join('test-datastore', uuid, 'last-screenshot.png')), "last-screenshot.png should exist"
     assert os.path.isfile(os.path.join('test-datastore', uuid, 'elements.json')), "xpath elements.json data should exist"
 

requirements.txt

@@ -19,7 +19,8 @@ chardet > 2.3.0
 
 wtforms ~= 3.0
 jsonpath-ng ~= 1.5.3
-jq ~= 1.3.0
+
+# jq not available on Windows so must be installed manually
 
 # Notification library
 apprise ~= 1.1.0

x

@@ -0,0 +1,49 @@
+diff --git a/changedetectionio/__init__.py b/changedetectionio/__init__.py
+index c745dd3e..19873cce 100644
+--- a/changedetectionio/__init__.py
++++ b/changedetectionio/__init__.py
+@@ -819,8 +819,8 @@ def changedetection_app(config=None, datastore_o=None):
+         # Read as binary and force decode as UTF-8
+         # Windows may fail decode in python if we just use 'r' mode (chardet decode exception)
+         try:
+-            with open(newest_file, 'rb') as f:
+-                newest_version_file_contents = f.read().decode('utf-8')
++            with open(newest_file, 'r', encoding='utf-8', errors='ignore') as f:
++                newest_version_file_contents = f.read()
+         except Exception as e:
+             newest_version_file_contents = "Unable to read {}.\n".format(newest_file)
+ 
+@@ -832,8 +832,8 @@ def changedetection_app(config=None, datastore_o=None):
+             previous_file = history[dates[-2]]
+ 
+         try:
+-            with open(previous_file, 'rb') as f:
+-                previous_version_file_contents = f.read().decode('utf-8')
++            with open(previous_file, 'r', encoding='utf-8', errors='ignore') as f:
++                previous_version_file_contents = f.read()
+         except Exception as e:
+             previous_version_file_contents = "Unable to read {}.\n".format(previous_file)
+ 
+@@ -909,7 +909,7 @@ def changedetection_app(config=None, datastore_o=None):
+         timestamp = list(watch.history.keys())[-1]
+         filename = watch.history[timestamp]
+         try:
+-            with open(filename, 'r') as f:
++            with open(filename, 'r', encoding='utf-8', errors='ignore') as f:
+                 tmp = f.readlines()
+ 
+                 # Get what needs to be highlighted
+diff --git a/changedetectionio/model/Watch.py b/changedetectionio/model/Watch.py
+index 9a87ad71..566eb88e 100644
+--- a/changedetectionio/model/Watch.py
++++ b/changedetectionio/model/Watch.py
+@@ -158,7 +158,8 @@ class model(dict):
+ 
+         logging.debug("Saving history text {}".format(snapshot_fname))
+ 
+-        # in /diff/ we are going to assume for now that it's UTF-8 when reading
++        # in /diff/ and /preview/ we are going to assume for now that it's UTF-8 when reading
++        # most sites are utf-8 and some are even broken utf-8
+         with open(snapshot_fname, 'wb') as f:
+             f.write(contents)
+             f.close()