Fixing page update

(its utf-16 by default python string)

changedetectionio/blueprint/check_proxies/__init__.py

@@ -1,7 +1,4 @@
-import importlib
 from concurrent.futures import ThreadPoolExecutor
-
-from changedetectionio.processors.text_json_diff.processor import FilterNotFoundInResponse
 from changedetectionio.store import ChangeDetectionStore
 
 from functools import wraps
@@ -33,6 +30,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
     def long_task(uuid, preferred_proxy):
         import time
         from changedetectionio.content_fetchers import exceptions as content_fetcher_exceptions
+        from changedetectionio.processors.text_json_diff import text_json_diff
         from changedetectionio.safe_jinja import render as jinja_render
 
         status = {'status': '', 'length': 0, 'text': ''}
@@ -40,12 +38,8 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         contents = ''
         now = time.time()
         try:
-            processor_module = importlib.import_module("changedetectionio.processors.text_json_diff.processor")
-            update_handler = processor_module.perform_site_check(datastore=datastore,
-                                                                 watch_uuid=uuid
-                                                                 )
-
-            update_handler.call_browser(preferred_proxy_id=preferred_proxy)
+            update_handler = text_json_diff.perform_site_check(datastore=datastore, watch_uuid=uuid)
+            update_handler.call_browser()
         # title, size is len contents not len xfer
         except content_fetcher_exceptions.Non200ErrorCodeReceived as e:
             if e.status_code == 404:
@@ -54,7 +48,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
                 status.update({'status': 'ERROR', 'length': len(contents), 'text': f"{e.status_code} - Access denied"})
             else:
                 status.update({'status': 'ERROR', 'length': len(contents), 'text': f"Status code: {e.status_code}"})
-        except FilterNotFoundInResponse:
+        except text_json_diff.FilterNotFoundInResponse:
             status.update({'status': 'OK', 'length': len(contents), 'text': f"OK but CSS/xPath filter not found (page changed layout?)"})
         except content_fetcher_exceptions.EmptyReply as e:
             if e.status_code == 403 or e.status_code == 401:

changedetectionio/content_fetchers/requests.py

@@ -75,7 +75,6 @@ class fetcher(Fetcher):
         self.headers = r.headers
 
         if not r.content or not len(r.content):
-            logger.debug(f"Requests returned empty content for '{url}'")
             if not empty_pages_are_a_change:
                 raise EmptyReply(url=url, status_code=r.status_code)
             else:

changedetectionio/flask_app.py

@@ -788,6 +788,7 @@ def changedetection_app(config=None, datastore_o=None):
             # Recast it if need be to right data Watch handler
             watch_class = get_custom_watch_obj_for_processor(form.data.get('processor'))
             datastore.data['watching'][uuid] = watch_class(datastore_path=datastore_o.datastore_path, default=datastore.data['watching'][uuid])
+
             flash("Updated watch - unpaused!" if request.args.get('unpause_on_save') else "Updated watch.")
 
             # Re #286 - We wait for syncing new data to disk in another thread every 60 seconds
@@ -1486,6 +1487,7 @@ def changedetection_app(config=None, datastore_o=None):
                         continue
                     update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid, 'skip_when_checksum_same': False}))
                     i += 1
+
         flash(f"{i} watches queued for rechecking.")
         return redirect(url_for('index', tag=tag))
 

changedetectionio/processors/__init__.py

@@ -18,7 +18,6 @@ class difference_detection_processor():
     screenshot = None
     watch = None
     xpath_data = None
-    preferred_proxy = None
 
     def __init__(self, *args, datastore, watch_uuid, **kwargs):
         super().__init__(*args, **kwargs)
@@ -27,8 +26,7 @@ class difference_detection_processor():
         # Generic fetcher that should be extended (requests, playwright etc)
         self.fetcher = Fetcher()
 
-    def call_browser(self, preferred_proxy_id=None):
-
+    def call_browser(self):
         from requests.structures import CaseInsensitiveDict
 
         # Protect against file:// access
@@ -44,7 +42,7 @@ class difference_detection_processor():
         prefer_fetch_backend = self.watch.get('fetch_backend', 'system')
 
         # Proxy ID "key"
-        preferred_proxy_id = preferred_proxy_id if preferred_proxy_id else self.datastore.get_preferred_proxy_for_watch(uuid=self.watch.get('uuid'))
+        preferred_proxy_id = self.datastore.get_preferred_proxy_for_watch(uuid=self.watch.get('uuid'))
 
         # Pluggable content self.fetcher
         if not prefer_fetch_backend or prefer_fetch_backend == 'system':

changedetectionio/processors/restock_diff/processor.py

@@ -27,27 +27,22 @@ def _search_prop_by_value(matches, value):
                 return prop[1]  # Yield the desired value and exit the function
 
 def _deduplicate_prices(data):
-    import re
+    seen = set()
+    unique_data = []
 
-    '''
-    Some price data has multiple entries, OR it has a single entry with ['$159', '159', 159, "$ 159"] or just "159"
-    Get all the values, clean it and add it to a set then return the unique values
-    '''
-    unique_data = set()
-
-    # Return the complete 'datum' where its price was not seen before
     for datum in data:
+        # Convert 'value' to float if it can be a numeric string, otherwise leave it as is
+        try:
+            normalized_value = float(datum.value) if isinstance(datum.value, str) and datum.value.replace('.', '', 1).isdigit() else datum.value
+        except ValueError:
+            normalized_value = datum.value
 
-        if isinstance(datum.value, list):
-            # Process each item in the list
-            normalized_value = set([float(re.sub(r'[^\d.]', '', str(item))) for item in datum.value])
-            unique_data.update(normalized_value)
-        else:
-            # Process single value
-            v = float(re.sub(r'[^\d.]', '', str(datum.value)))
-            unique_data.add(v)
-
-    return list(unique_data)
+        # If the normalized value hasn't been seen yet, add it to unique data
+        if normalized_value not in seen:
+            unique_data.append(datum)
+            seen.add(normalized_value)
+    
+    return unique_data
 
 
 # should return Restock()
@@ -88,13 +83,14 @@ def get_itemprop_availability(html_content) -> Restock:
         if price_result:
             # Right now, we just support single product items, maybe we will store the whole actual metadata seperately in teh future and
             # parse that for the UI?
-            if len(price_result) > 1 and len(price_result) > 1:
+            prices_found = set(str(item.value).replace('$', '') for item in price_result)
+            if len(price_result) > 1 and len(prices_found) > 1:
                 # See of all prices are different, in the case that one product has many embedded data types with the same price
                 # One might have $121.95 and another 121.95 etc
-                logger.warning(f"More than one price found {price_result}, throwing exception, cant use this plugin.")
+                logger.warning(f"More than one price found {prices_found}, throwing exception, cant use this plugin.")
                 raise MoreThanOnePriceFound()
 
-            value['price'] = price_result[0]
+            value['price'] = price_result[0].value
 
         pricecurrency_result = pricecurrency_parse.find(data)
         if pricecurrency_result:
@@ -224,7 +220,7 @@ class perform_site_check(difference_detection_processor):
             itemprop_availability['original_price'] = itemprop_availability.get('price')
             update_obj['restock']["original_price"] = itemprop_availability.get('price')
 
-        if not self.fetcher.instock_data and not itemprop_availability.get('availability') and not itemprop_availability.get('price'):
+        if not self.fetcher.instock_data and not itemprop_availability.get('availability'):
             raise ProcessorException(
                 message=f"Unable to extract restock data for this page unfortunately. (Got code {self.fetcher.get_last_status_code()} from server), no embedded stock information was found and nothing interesting in the text, try using this watch with Chrome.",
                 url=watch.get('url'),

changedetectionio/processors/text_json_diff/processor.py

@@ -211,7 +211,6 @@ class perform_site_check(difference_detection_processor):
         # @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
-
         if watch.has_special_diff_filter_options_set() and len(watch.history.keys()):
             # Now the content comes from the diff-parser and not the returned HTTP traffic, so could be some differences
             from changedetectionio import diff

changedetectionio/static/js/recheck-proxy.js

@@ -1,14 +1,14 @@
 $(function () {
     /* add container before each proxy location to show status */
-    var isActive = false;
 
-    function setup_html_widget() {
-        var option_li = $('.fetch-backend-proxy li').filter(function () {
-            return $("input", this)[0].value.length > 0;
-        });
-        $(option_li).prepend('<div class="proxy-status"></div>');
-        $(option_li).append('<div class="proxy-timing"></div><div class="proxy-check-details"></div>');
-    }
+    var option_li = $('.fetch-backend-proxy li').filter(function() {
+        return $("input",this)[0].value.length >0;
+    });
+
+    //var option_li = $('.fetch-backend-proxy li');
+    var isActive = false;
+    $(option_li).prepend('<div class="proxy-status"></div>');
+    $(option_li).append('<div class="proxy-timing"></div><div class="proxy-check-details"></div>');
 
     function set_proxy_check_status(proxy_key, state) {
         // select input by value name
@@ -59,14 +59,8 @@ $(function () {
     }
 
     $('#check-all-proxies').click(function (e) {
-
         e.preventDefault()
-
-        if (!$('body').hasClass('proxy-check-active')) {
-            setup_html_widget();
-            $('body').addClass('proxy-check-active');
-        }
-
+        $('body').addClass('proxy-check-active');
         $('.proxy-check-details').html('');
         $('.proxy-status').html('<span class="spinner"></span>').fadeIn();
         $('.proxy-timing').html('');

changedetectionio/static/styles/scss/parts/_extra_proxies.scss

@@ -25,19 +25,15 @@ ul#requests-extra_proxies {
 
 body.proxy-check-active {
   #request {
-    // Padding set by flex layout
-    /*
     .proxy-status {
       width: 2em;
     }
-    */
 
     .proxy-check-details {
       font-size: 80%;
       color: #555;
       display: block;
-      padding-left: 2em;
-      max-width: 500px;
+      padding-left: 4em;
     }
 
     .proxy-timing {

changedetectionio/static/styles/styles.css

@@ -119,22 +119,19 @@ ul#requests-extra_proxies {
   #request label[for=proxy] {
     display: inline-block; }
 
-body.proxy-check-active #request {
-  /*
-    .proxy-status {
-      width: 2em;
-    }
-    */ }
-  body.proxy-check-active #request .proxy-check-details {
-    font-size: 80%;
-    color: #555;
-    display: block;
-    padding-left: 2em;
-    max-width: 500px; }
-  body.proxy-check-active #request .proxy-timing {
-    font-size: 80%;
-    padding-left: 1rem;
-    color: var(--color-link); }
+body.proxy-check-active #request .proxy-status {
+  width: 2em; }
+
+body.proxy-check-active #request .proxy-check-details {
+  font-size: 80%;
+  color: #555;
+  display: block;
+  padding-left: 4em; }
+
+body.proxy-check-active #request .proxy-timing {
+  font-size: 80%;
+  padding-left: 1rem;
+  color: var(--color-link); }
 
 #recommended-proxy {
   display: grid;

changedetectionio/tests/itemprop_test_examples/README.md

@@ -1,6 +0,0 @@
-# A list of real world examples!
-
-Always the price should be 666.66 for our tests
-
-see test_restock_itemprop.py::test_special_prop_examples
-

changedetectionio/tests/itemprop_test_examples/a.txt

@@ -1,25 +0,0 @@
-<div class="PriceSection PriceSection_PriceSection__Vx1_Q PriceSection_variantHuge__P9qxg PdpPriceSection"
-     data-testid="price-section"
-     data-optly-product-tile-price-section="true"><span
-        class="PriceRange ProductPrice variant-huge" itemprop="offers"
-        itemscope="" itemtype="http://schema.org/Offer"><div
-        class="VisuallyHidden_VisuallyHidden__VBD83">$155.55</div><span
-        aria-hidden="true" class="Price variant-huge" data-testid="price"
-        itemprop="price"><sup class="sup" data-testid="price-symbol"
-                              itemprop="priceCurrency" content="AUD">$</sup><span
-        class="dollars" data-testid="price-value" itemprop="price"
-        content="155.55">155.55</span><span class="extras"><span class="sup"
-                                                              data-testid="price-sup"></span></span></span></span>
-</div>
-
-<script type="application/ld+json">{
-                                "@type": "Product",
-                                "@context": "https://schema.org",
-                                "name": "test",
-                                "description": "test",
-                                "offers": {
-                                    "@type": "Offer",
-                                    "priceCurrency": "AUD",
-                                    "price": 155.55
-                                },
-                            }</script>

changedetectionio/tests/test_add_replace_remove_filter.py

@@ -77,8 +77,6 @@ def test_check_removed_line_contains_trigger(client, live_server, measure_memory
 
     # The trigger line is REMOVED,  this should trigger
     set_original(excluding='The golden line')
-
-    # Check in the processor here what's going on, its triggering empty-reply and no change.
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
     wait_for_all_checks(client)
     res = client.get(url_for("index"))
@@ -153,6 +151,7 @@ def test_check_add_line_contains_trigger(client, live_server, measure_memory_usa
 
     # A line thats not the trigger should not trigger anything
     res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
+
     assert b'1 watches queued for rechecking.' in res.data
 
     wait_for_all_checks(client)
@@ -174,5 +173,6 @@ def test_check_add_line_contains_trigger(client, live_server, measure_memory_usa
         assert b'-Oh yes please-' in response
         assert '网站监测 内容更新了'.encode('utf-8') in response
 
+
     res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
     assert b'Deleted' in res.data

changedetectionio/tests/test_element_removal.py

@@ -5,7 +5,7 @@ import time
 from flask import url_for
 
 from ..html_tools import *
-from .util import live_server_setup, wait_for_all_checks
+from .util import live_server_setup
 
 
 def test_setup(live_server):
@@ -119,10 +119,12 @@ across multiple lines
 
 
 def test_element_removal_full(client, live_server, measure_memory_usage):
-    #live_server_setup(live_server)
+    sleep_time_for_fetch_thread = 3
 
     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)
@@ -130,8 +132,7 @@ def test_element_removal_full(client, live_server, measure_memory_usage):
         url_for("import_page"), data={"urls": test_url}, follow_redirects=True
     )
     assert b"1 Imported" in res.data
-    wait_for_all_checks(client)
-
+    time.sleep(1)
     # Goto the edit page, add the filter data
     # Not sure why \r needs to be added - absent of the #changetext this is not necessary
     subtractive_selectors_data = "header\r\nfooter\r\nnav\r\n#changetext"
@@ -147,7 +148,6 @@ def test_element_removal_full(client, live_server, measure_memory_usage):
         follow_redirects=True,
     )
     assert b"Updated watch." in res.data
-    wait_for_all_checks(client)
 
     # Check it saved
     res = client.get(
@@ -156,10 +156,10 @@ def test_element_removal_full(client, live_server, measure_memory_usage):
     assert bytes(subtractive_selectors_data.encode("utf-8")) in res.data
 
     # Trigger a check
-    res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
-    assert b'1 watches queued for rechecking.' in res.data
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
-    wait_for_all_checks(client)
+    # Give the thread time to pick it up
+    time.sleep(sleep_time_for_fetch_thread)
 
     # so that we set the state to 'unviewed' after all the edits
     client.get(url_for("diff_history_page", uuid="first"))
@@ -168,11 +168,10 @@ def test_element_removal_full(client, live_server, measure_memory_usage):
     set_modified_response()
 
     # Trigger a check
-    res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
-    assert b'1 watches queued for rechecking.' in res.data
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
     # Give the thread time to pick it up
-    wait_for_all_checks(client)
+    time.sleep(sleep_time_for_fetch_thread)
 
     # There should not be an unviewed change, as changes should be removed
     res = client.get(url_for("index"))

changedetectionio/tests/test_preview_endpoints.py

@@ -1,72 +0,0 @@
-#!/usr/bin/env python3
-
-import time
-from flask import url_for
-from .util import set_original_response, set_modified_response, live_server_setup, wait_for_all_checks
-
-
-# `subtractive_selectors` should still work in `source:` type requests
-def test_fetch_pdf(client, live_server, measure_memory_usage):
-    import shutil
-    shutil.copy("tests/test.pdf", "test-datastore/endpoint-test.pdf")
-
-    live_server_setup(live_server)
-    test_url = url_for('test_pdf_endpoint', _external=True)
-    # Add our URL to the import page
-    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)
-
-    res = client.get(
-        url_for("preview_page", uuid="first"),
-        follow_redirects=True
-    )
-
-    # PDF header should not be there (it was converted to text)
-    assert b'PDF' not in res.data[:10]
-    assert b'hello world' in res.data
-
-    # So we know if the file changes in other ways
-    import hashlib
-    original_md5 = hashlib.md5(open("test-datastore/endpoint-test.pdf", 'rb').read()).hexdigest().upper()
-    # We should have one
-    assert len(original_md5) > 0
-    # And it's going to be in the document
-    assert b'Document checksum - ' + bytes(str(original_md5).encode('utf-8')) in res.data
-
-    shutil.copy("tests/test2.pdf", "test-datastore/endpoint-test.pdf")
-    changed_md5 = hashlib.md5(open("test-datastore/endpoint-test.pdf", 'rb').read()).hexdigest().upper()
-    res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
-    assert b'1 watches queued for rechecking.' in res.data
-
-    wait_for_all_checks(client)
-
-    # Now something should be ready, indicated by having a 'unviewed' class
-    res = client.get(url_for("index"))
-    assert b'unviewed' in res.data
-
-    # The original checksum should be not be here anymore (cdio adds it to the bottom of the text)
-
-    res = client.get(
-        url_for("preview_page", uuid="first"),
-        follow_redirects=True
-    )
-
-    assert original_md5.encode('utf-8') not in res.data
-    assert changed_md5.encode('utf-8') in res.data
-
-    res = client.get(
-        url_for("diff_history_page", uuid="first"),
-        follow_redirects=True
-    )
-
-    assert original_md5.encode('utf-8') in res.data
-    assert changed_md5.encode('utf-8') in res.data
-
-    assert b'here is a change' in res.data

changedetectionio/tests/test_restock_itemprop.py

@@ -3,7 +3,7 @@ import os
 import time
 
 from flask import url_for
-from .util import live_server_setup, wait_for_all_checks, wait_for_notification_endpoint_output
+from .util import live_server_setup, wait_for_all_checks, extract_UUID_from_client, wait_for_notification_endpoint_output
 from ..notification import default_notification_format
 
 instock_props = [
@@ -413,31 +413,3 @@ def test_data_sanity(client, live_server):
     res = client.get(
         url_for("edit_page", uuid="first"))
     assert test_url2.encode('utf-8') in res.data
-
-    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
-    assert b'Deleted' in res.data
-
-# All examples should give a prive of 666.66
-def test_special_prop_examples(client, live_server):
-    import glob
-    #live_server_setup(live_server)
-
-    test_url = url_for('test_endpoint', _external=True)
-    check_path = os.path.join(os.path.dirname(__file__), "itemprop_test_examples", "*.txt")
-    files = glob.glob(check_path)
-    assert files
-    for test_example_filename in files:
-        with open(test_example_filename, 'r') as example_f:
-            with open("test-datastore/endpoint-content.txt", "w") as test_f:
-                test_f.write(f"<html><body>{example_f.read()}</body></html>")
-
-            # Now fetch it and check the price worked
-            client.post(
-                url_for("form_quick_watch_add"),
-                data={"url": test_url, "tags": 'restock tests', 'processor': 'restock_diff'},
-                follow_redirects=True
-            )
-            wait_for_all_checks(client)
-            res = client.get(url_for("index"))
-            assert b'ception' not in res.data
-            assert b'155.55' in res.data