Closes #2548

MANIFEST.in

@@ -1,4 +1,5 @@
 recursive-include changedetectionio/api *
+recursive-include changedetectionio/apprise_plugin *
 recursive-include changedetectionio/blueprint *
 recursive-include changedetectionio/content_fetchers *
 recursive-include changedetectionio/model *

changedetectionio/__init__.py

@@ -2,7 +2,7 @@
 
 # Read more https://github.com/dgtlmoon/changedetection.io/wiki
 
-__version__ = '0.46.04'
+__version__ = '0.47.03'
 
 from changedetectionio.strtobool import strtobool
 from json.decoder import JSONDecodeError

changedetectionio/api/api_v1.py

@@ -58,7 +58,7 @@ class Watch(Resource):
             abort(404, message='No watch exists with the UUID of {}'.format(uuid))
 
         if request.args.get('recheck'):
-            self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': True}))
+            self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
             return "OK", 200
         if request.args.get('paused', '') == 'paused':
             self.datastore.data['watching'].get(uuid).pause()
@@ -246,7 +246,7 @@ class CreateWatch(Resource):
 
         new_uuid = self.datastore.add_watch(url=url, extras=extras, tag=tags)
         if new_uuid:
-            self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': new_uuid, 'skip_when_checksum_same': True}))
+            self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': new_uuid}))
             return {'uuid': new_uuid}, 201
         else:
             return "Invalid or unsupported URL", 400
@@ -303,7 +303,7 @@ class CreateWatch(Resource):
 
         if request.args.get('recheck_all'):
             for uuid in self.datastore.data['watching'].keys():
-                self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': True}))
+                self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
             return {'status': "OK"}, 200
 
         return list, 200

changedetectionio/blueprint/check_proxies/__init__.py

@@ -1,4 +1,7 @@
+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
@@ -30,7 +33,6 @@ 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': ''}
@@ -38,8 +40,12 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         contents = ''
         now = time.time()
         try:
-            update_handler = text_json_diff.perform_site_check(datastore=datastore, watch_uuid=uuid)
-            update_handler.call_browser()
+            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)
         # title, size is len contents not len xfer
         except content_fetcher_exceptions.Non200ErrorCodeReceived as e:
             if e.status_code == 404:
@@ -48,7 +54,7 @@ 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 text_json_diff.FilterNotFoundInResponse:
+        except 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/blueprint/price_data_follower/__init__.py

@@ -19,7 +19,7 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q: PriorityQueue
         datastore.data['watching'][uuid]['track_ldjson_price_data'] = PRICE_DATA_TRACK_ACCEPT
         datastore.data['watching'][uuid]['processor'] = 'restock_diff'
         datastore.data['watching'][uuid].clear_watch()
-        update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': False}))
+        update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
         return redirect(url_for("index"))
 
     @login_required

changedetectionio/blueprint/tags/templates/edit-tag.html

@@ -17,7 +17,6 @@
 </script>
 
 <script src="{{url_for('static_content', group='js', filename='watch-settings.js')}}" defer></script>
-<!--<script src="{{url_for('static_content', group='js', filename='limit.js')}}" defer></script>-->
 <script src="{{url_for('static_content', group='js', filename='notifications.js')}}" defer></script>
 
 <div class="edit-form monospaced-textarea">

changedetectionio/content_fetchers/requests.py

@@ -75,6 +75,7 @@ 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

@@ -788,7 +788,6 @@ 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
@@ -796,7 +795,7 @@ def changedetection_app(config=None, datastore_o=None):
             datastore.needs_write_urgent = True
 
             # Queue the watch for immediate recheck, with a higher priority
-            update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': False}))
+            update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
 
             # Diff page [edit] link should go back to diff page
             if request.args.get("next") and request.args.get("next") == 'diff':
@@ -977,7 +976,7 @@ def changedetection_app(config=None, datastore_o=None):
                 importer = import_url_list()
                 importer.run(data=request.values.get('urls'), flash=flash, datastore=datastore, processor=request.values.get('processor', 'text_json_diff'))
                 for uuid in importer.new_uuids:
-                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': True}))
+                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
 
                 if len(importer.remaining_data) == 0:
                     return redirect(url_for('index'))
@@ -990,7 +989,7 @@ def changedetection_app(config=None, datastore_o=None):
                 d_importer = import_distill_io_json()
                 d_importer.run(data=request.values.get('distill-io'), flash=flash, datastore=datastore)
                 for uuid in d_importer.new_uuids:
-                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': True}))
+                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
 
             # XLSX importer
             if request.files and request.files.get('xlsx_file'):
@@ -1014,7 +1013,7 @@ def changedetection_app(config=None, datastore_o=None):
                     w_importer.run(data=file, flash=flash, datastore=datastore)
 
                 for uuid in w_importer.new_uuids:
-                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': True}))
+                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
 
         # Could be some remaining, or we could be on GET
         form = forms.importForm(formdata=request.form if request.method == 'POST' else None)
@@ -1443,7 +1442,7 @@ def changedetection_app(config=None, datastore_o=None):
         new_uuid = datastore.clone(uuid)
         if new_uuid:
             if not datastore.data['watching'].get(uuid).get('paused'):
-                update_q.put(queuedWatchMetaData.PrioritizedItem(priority=5, item={'uuid': new_uuid, 'skip_when_checksum_same': True}))
+                update_q.put(queuedWatchMetaData.PrioritizedItem(priority=5, item={'uuid': new_uuid}))
             flash('Cloned.')
 
         return redirect(url_for('index'))
@@ -1464,7 +1463,7 @@ def changedetection_app(config=None, datastore_o=None):
 
         if uuid:
             if uuid not in running_uuids:
-                update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': False}))
+                update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
             i = 1
 
         elif tag:
@@ -1475,7 +1474,7 @@ def changedetection_app(config=None, datastore_o=None):
                         continue
                     if watch_uuid not in running_uuids and not datastore.data['watching'][watch_uuid]['paused']:
                         update_q.put(
-                            queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid, 'skip_when_checksum_same': False})
+                            queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid})
                         )
                         i += 1
 
@@ -1485,9 +1484,8 @@ def changedetection_app(config=None, datastore_o=None):
                 if watch_uuid not in running_uuids and not datastore.data['watching'][watch_uuid]['paused']:
                     if with_errors and not watch.get('last_error'):
                         continue
-                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid, 'skip_when_checksum_same': False}))
+                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid}))
                     i += 1
-
         flash(f"{i} watches queued for rechecking.")
         return redirect(url_for('index', tag=tag))
 
@@ -1544,7 +1542,7 @@ def changedetection_app(config=None, datastore_o=None):
                 uuid = uuid.strip()
                 if datastore.data['watching'].get(uuid):
                     # Recheck and require a full reprocessing
-                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': False}))
+                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
             flash("{} watches queued for rechecking".format(len(uuids)))
 
         elif (op == 'clear-errors'):
@@ -1868,7 +1866,7 @@ def ticker_thread_check_time_launch_checks():
                         f"{now - watch['last_checked']:0.2f}s since last checked")
 
                     # Into the queue with you
-                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=priority, item={'uuid': uuid, 'skip_when_checksum_same': True}))
+                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=priority, item={'uuid': uuid}))
 
                     # Reset for next time
                     watch.jitter_seconds = 0

changedetectionio/forms.py

@@ -476,7 +476,7 @@ class processor_text_json_diff_form(commonSettingsForm):
 
     title = StringField('Title', default='')
 
-    ignore_text = StringListField('Remove lines containing', [ValidateListRegex()])
+    ignore_text = StringListField('Ignore lines containing', [ValidateListRegex()])
     headers = StringDictKeyValue('Request headers')
     body = TextAreaField('Request body', [validators.Optional()])
     method = SelectField('Request method', choices=valid_method, default=default_method)

changedetectionio/html_tools.py

@@ -3,11 +3,11 @@ from lxml import etree
 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>"
-
+TRANSLATE_WHITESPACE_TABLE = str.maketrans('', '', '\r\n\t ')
 PERL_STYLE_REGEX = r'^/(.*?)/([a-z]*)?$'
+
 # 'price' , 'lowPrice', 'highPrice' are usually under here
 # All of those may or may not appear on different websites - I didnt find a way todo case-insensitive searching here
 LD_JSON_PRODUCT_OFFER_SELECTORS = ["json:$..offers", "json:$..Offers"]
@@ -326,6 +326,7 @@ def extract_json_as_string(content, json_filter, ensure_is_ldjson_info_type=None
 #          - "line numbers" return a list of line numbers that match (int list)
 #
 # wordlist - list of regex's (str) or words (str)
+# Preserves all linefeeds and other whitespacing, its not the job of this to remove that
 def strip_ignore_text(content, wordlist, mode="content"):
     i = 0
     output = []
@@ -341,32 +342,30 @@ def strip_ignore_text(content, wordlist, mode="content"):
         else:
             ignore_text.append(k.strip())
 
-    for line in content.splitlines():
+    for line in content.splitlines(keepends=True):
         i += 1
         # Always ignore blank lines in this mode. (when this function gets called)
         got_match = False
-        if len(line.strip()):
-            for l in ignore_text:
-                if l.lower() in line.lower():
+        for l in ignore_text:
+            if l.lower() in line.lower():
+                got_match = True
+
+        if not got_match:
+            for r in ignore_regex:
+                if r.search(line):
                     got_match = True
 
-            if not got_match:
-                for r in ignore_regex:
-                    if r.search(line):
-                        got_match = True
-
-            if not got_match:
-                # Not ignored
-                output.append(line.encode('utf8'))
-            else:
-                ignored_line_numbers.append(i)
-
+        if not got_match:
+            # Not ignored, and should preserve "keepends"
+            output.append(line)
+        else:
+            ignored_line_numbers.append(i)
 
     # Used for finding out what to highlight
     if mode == "line numbers":
         return ignored_line_numbers
 
-    return "\n".encode('utf8').join(output)
+    return ''.join(output)
 
 def cdata_in_document_to_text(html_content: str, render_anchor_tag_content=False) -> str:
     from xml.sax.saxutils import escape as xml_escape

changedetectionio/model/Watch.py

@@ -6,6 +6,8 @@ import re
 from pathlib import Path
 from loguru import logger
 
+from ..html_tools import TRANSLATE_WHITESPACE_TABLE
+
 # Allowable protocols, protects against javascript: etc
 # file:// is further checked by ALLOW_FILE_URI
 SAFE_PROTOCOL_REGEX='^(http|https|ftp|file):'
@@ -312,13 +314,13 @@ class model(watch_base):
             dest = os.path.join(self.watch_data_dir, snapshot_fname)
             if not os.path.exists(dest):
                 with open(dest, 'wb') as f:
-                    f.write(brotli.compress(contents, mode=brotli.MODE_TEXT))
+                    f.write(brotli.compress(contents.encode('utf-8'), mode=brotli.MODE_TEXT))
         else:
             snapshot_fname = f"{snapshot_id}.txt"
             dest = os.path.join(self.watch_data_dir, snapshot_fname)
             if not os.path.exists(dest):
                 with open(dest, 'wb') as f:
-                    f.write(contents)
+                    f.write(contents.encode('utf-8'))
 
         # Append to index
         # @todo check last char was \n
@@ -350,14 +352,32 @@ class model(watch_base):
         return seconds
 
     # Iterate over all history texts and see if something new exists
-    def lines_contain_something_unique_compared_to_history(self, lines: list):
-        local_lines = set([l.decode('utf-8').strip().lower() for l in lines])
+    # Always applying .strip() to start/end but optionally replace any other whitespace
+    def lines_contain_something_unique_compared_to_history(self, lines: list, ignore_whitespace=False):
+        local_lines = []
+        if lines:
+            if ignore_whitespace:
+                if isinstance(lines[0], str): # Can be either str or bytes depending on what was on the disk
+                    local_lines = set([l.translate(TRANSLATE_WHITESPACE_TABLE).lower() for l in lines])
+                else:
+                    local_lines = set([l.decode('utf-8').translate(TRANSLATE_WHITESPACE_TABLE).lower() for l in lines])
+            else:
+                if isinstance(lines[0], str): # Can be either str or bytes depending on what was on the disk
+                    local_lines = set([l.strip().lower() for l in lines])
+                else:
+                    local_lines = set([l.decode('utf-8').strip().lower() for l in lines])
+
 
         # Compare each lines (set) against each history text file (set) looking for something new..
         existing_history = set({})
         for k, v in self.history.items():
             content = self.get_history_snapshot(k)
-            alist = set([line.strip().lower() for line in content.splitlines()])
+
+            if ignore_whitespace:
+                alist = set([line.translate(TRANSLATE_WHITESPACE_TABLE).lower() for line in content.splitlines()])
+            else:
+                alist = set([line.strip().lower() for line in content.splitlines()])
+
             existing_history = existing_history.union(alist)
 
         # Check that everything in local_lines(new stuff) already exists in existing_history - it should

changedetectionio/processors/__init__.py

@@ -18,6 +18,7 @@ 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)
@@ -26,7 +27,8 @@ class difference_detection_processor():
         # Generic fetcher that should be extended (requests, playwright etc)
         self.fetcher = Fetcher()
 
-    def call_browser(self):
+    def call_browser(self, preferred_proxy_id=None):
+
         from requests.structures import CaseInsensitiveDict
 
         # Protect against file:// access
@@ -42,7 +44,7 @@ class difference_detection_processor():
         prefer_fetch_backend = self.watch.get('fetch_backend', 'system')
 
         # Proxy ID "key"
-        preferred_proxy_id = self.datastore.get_preferred_proxy_for_watch(uuid=self.watch.get('uuid'))
+        preferred_proxy_id = preferred_proxy_id if preferred_proxy_id else 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':
@@ -155,7 +157,7 @@ class difference_detection_processor():
         # After init, call run_changedetection() which will do the actual change-detection
 
     @abstractmethod
-    def run_changedetection(self, watch, skip_when_checksum_same: bool = True):
+    def run_changedetection(self, watch):
         update_obj = {'last_notification_error': False, 'last_error': False}
         some_data = 'xxxxx'
         update_obj["previous_md5"] = hashlib.md5(some_data.encode('utf-8')).hexdigest()

changedetectionio/processors/restock_diff/processor.py

@@ -27,22 +27,27 @@ def _search_prop_by_value(matches, value):
                 return prop[1]  # Yield the desired value and exit the function
 
 def _deduplicate_prices(data):
-    seen = set()
-    unique_data = []
+    import re
 
+    '''
+    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 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
+        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)
 
 
 # should return Restock()
@@ -83,14 +88,13 @@ 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?
-            prices_found = set(str(item.value).replace('$', '') for item in price_result)
-            if len(price_result) > 1 and len(prices_found) > 1:
+            if len(price_result) > 1 and len(price_result) > 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 {prices_found}, throwing exception, cant use this plugin.")
+                logger.warning(f"More than one price found {price_result}, throwing exception, cant use this plugin.")
                 raise MoreThanOnePriceFound()
 
-            value['price'] = price_result[0].value
+            value['price'] = price_result[0]
 
         pricecurrency_result = pricecurrency_parse.find(data)
         if pricecurrency_result:
@@ -140,7 +144,7 @@ class perform_site_check(difference_detection_processor):
     screenshot = None
     xpath_data = None
 
-    def run_changedetection(self, watch, skip_when_checksum_same=True):
+    def run_changedetection(self, watch):
         import hashlib
 
         if not watch:
@@ -220,7 +224,7 @@ 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'):
+        if not self.fetcher.instock_data and not itemprop_availability.get('availability') and not itemprop_availability.get('price'):
             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'),
@@ -307,4 +311,4 @@ class perform_site_check(difference_detection_processor):
         # Always record the new checksum
         update_obj["previous_md5"] = fetched_md5
 
-        return changed_detected, update_obj, snapshot_content.encode('utf-8').strip()
+        return changed_detected, update_obj, snapshot_content.strip()

changedetectionio/processors/text_json_diff/__init__.py

@@ -11,10 +11,7 @@ def _task(watch, update_handler):
 
     try:
         # The slow process (we run 2 of these in parallel)
-        changed_detected, update_obj, text_after_filter = update_handler.run_changedetection(
-            watch=watch,
-            skip_when_checksum_same=False,
-        )
+        changed_detected, update_obj, text_after_filter = update_handler.run_changedetection(watch=watch)
     except FilterNotFoundInResponse as e:
         text_after_filter = f"Filter not found in HTML: {str(e)}"
     except ReplyWithContentButNoText as e:
@@ -46,6 +43,9 @@ def prepare_filter_prevew(datastore, watch_uuid):
 
     text_after_filter = ''
     text_before_filter = ''
+    trigger_line_numbers = []
+    ignore_line_numbers = []
+
     tmp_watch = deepcopy(datastore.data['watching'].get(watch_uuid))
 
     if tmp_watch and tmp_watch.history and os.path.isdir(tmp_watch.watch_data_dir):
@@ -72,7 +72,7 @@ def prepare_filter_prevew(datastore, watch_uuid):
                                                                  )
             # Use the last loaded HTML as the input
             update_handler.datastore = datastore
-            update_handler.fetcher.content = decompressed_data
+            update_handler.fetcher.content = str(decompressed_data) # str() because playwright/puppeteer/requests return string
             update_handler.fetcher.headers['content-type'] = tmp_watch.get('content-type')
 
             # Process our watch with filters and the HTML from disk, and also a blank watch with no filters but also with the same HTML from disk
@@ -84,9 +84,7 @@ def prepare_filter_prevew(datastore, watch_uuid):
                 text_after_filter = future1.result()
                 text_before_filter = future2.result()
 
-    trigger_line_numbers = []
     try:
-
         trigger_line_numbers = html_tools.strip_ignore_text(content=text_after_filter,
                                                             wordlist=tmp_watch['trigger_text'],
                                                             mode='line numbers'
@@ -94,6 +92,15 @@ def prepare_filter_prevew(datastore, watch_uuid):
     except Exception as e:
         text_before_filter = f"Error: {str(e)}"
 
+    try:
+        text_to_ignore = tmp_watch.get('ignore_text', []) + datastore.data['settings']['application'].get('global_ignore_text', [])
+        ignore_line_numbers = html_tools.strip_ignore_text(content=text_after_filter,
+                                                           wordlist=text_to_ignore,
+                                                           mode='line numbers'
+                                                           )
+    except Exception as e:
+        text_before_filter = f"Error: {str(e)}"
+
     logger.trace(f"Parsed in {time.time() - now:.3f}s")
 
     return jsonify(
@@ -102,6 +109,7 @@ def prepare_filter_prevew(datastore, watch_uuid):
             'before_filter': text_before_filter.decode('utf-8') if isinstance(text_before_filter, bytes) else text_before_filter,
             'duration': time.time() - now,
             'trigger_line_numbers': trigger_line_numbers,
+            'ignore_line_numbers': ignore_line_numbers,
         }
     )
 

changedetectionio/processors/text_json_diff/processor.py

@@ -7,7 +7,7 @@ import re
 import urllib3
 
 from changedetectionio.processors import difference_detection_processor
-from changedetectionio.html_tools import PERL_STYLE_REGEX, cdata_in_document_to_text
+from changedetectionio.html_tools import PERL_STYLE_REGEX, cdata_in_document_to_text, TRANSLATE_WHITESPACE_TABLE
 from changedetectionio import html_tools, content_fetchers
 from changedetectionio.blueprint.price_data_follower import PRICE_DATA_TRACK_ACCEPT, PRICE_DATA_TRACK_REJECT
 from loguru import logger
@@ -35,8 +35,7 @@ class PDFToHTMLToolNotFound(ValueError):
 # (set_proxy_from_list)
 class perform_site_check(difference_detection_processor):
 
-    def run_changedetection(self, watch, skip_when_checksum_same=True):
-
+    def run_changedetection(self, watch):
         changed_detected = False
         html_content = ""
         screenshot = False  # as bytes
@@ -59,9 +58,6 @@ class perform_site_check(difference_detection_processor):
         # Watches added automatically in the queue manager will skip if its the same checksum as the previous run
         # Saves a lot of CPU
         update_obj['previous_md5_before_filters'] = hashlib.md5(self.fetcher.content.encode('utf-8')).hexdigest()
-        if skip_when_checksum_same:
-            if update_obj['previous_md5_before_filters'] == watch.get('previous_md5_before_filters'):
-                raise content_fetchers.exceptions.checksumFromPreviousCheckWasTheSame()
 
         # Fetching complete, now filters
 
@@ -205,22 +201,14 @@ class perform_site_check(difference_detection_processor):
         if watch.get('trim_text_whitespace'):
             stripped_text_from_html = '\n'.join(line.strip() for line in stripped_text_from_html.replace("\n\n", "\n").splitlines())
 
-        if watch.get('remove_duplicate_lines'):
-            stripped_text_from_html = '\n'.join(dict.fromkeys(line for line in stripped_text_from_html.replace("\n\n", "\n").splitlines()))
-
-        if watch.get('sort_text_alphabetically'):
-            # Note: Because a <p>something</p> will add an extra line feed to signify the paragraph gap
-            # we end up with 'Some text\n\n', sorting will add all those extra \n at the start, so we remove them here.
-            stripped_text_from_html = stripped_text_from_html.replace("\n\n", "\n")
-            stripped_text_from_html = '\n'.join(sorted(stripped_text_from_html.splitlines(), key=lambda x: x.lower()))
-
         # Re #340 - return the content before the 'ignore text' was applied
         # Also used to calculate/show what was removed
-        text_content_before_ignored_filter = stripped_text_from_html.encode('utf-8')
+        text_content_before_ignored_filter = stripped_text_from_html
 
         # @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
@@ -235,12 +223,12 @@ class perform_site_check(difference_detection_processor):
                                              line_feed_sep="\n",
                                              include_change_type_prefix=False)
 
-            watch.save_last_text_fetched_before_filters(text_content_before_ignored_filter)
+            watch.save_last_text_fetched_before_filters(text_content_before_ignored_filter.encode('utf-8'))
 
             if not rendered_diff and stripped_text_from_html:
                 # We had some content, but no differences were found
                 # Store our new file as the MD5 so it will trigger in the future
-                c = hashlib.md5(stripped_text_from_html.encode('utf-8').translate(None, b'\r\n\t ')).hexdigest()
+                c = hashlib.md5(stripped_text_from_html.translate(TRANSLATE_WHITESPACE_TABLE).encode('utf-8')).hexdigest()
                 return False, {'previous_md5': c}, stripped_text_from_html.encode('utf-8')
             else:
                 stripped_text_from_html = rendered_diff
@@ -261,14 +249,6 @@ class perform_site_check(difference_detection_processor):
 
         update_obj["last_check_status"] = self.fetcher.get_last_status_code()
 
-        # If there's text to skip
-        # @todo we could abstract out the get_text() to handle this cleaner
-        text_to_ignore = watch.get('ignore_text', []) + self.datastore.data['settings']['application'].get('global_ignore_text', [])
-        if len(text_to_ignore):
-            stripped_text_from_html = html_tools.strip_ignore_text(stripped_text_from_html, text_to_ignore)
-        else:
-            stripped_text_from_html = stripped_text_from_html.encode('utf8')
-
         # 615 Extract text by regex
         extract_text = watch.get('extract_text', [])
         if len(extract_text) > 0:
@@ -277,39 +257,53 @@ class perform_site_check(difference_detection_processor):
                 # incase they specified something in '/.../x'
                 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)
+                    result = re.findall(regex, 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']
+                            regex_matched_output += list(l) + ['\n']
                         else:
                             # @todo - some formatter option default (between each ungrouped result)
-                            regex_matched_output += [l] + [b'\n']
+                            regex_matched_output += [l] + ['\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)
+                    r = re.compile(re.escape(s_re), re.IGNORECASE)
                     res = r.findall(stripped_text_from_html)
                     if res:
                         for match in res:
-                            regex_matched_output += [match] + [b'\n']
+                            regex_matched_output += [match] + ['\n']
 
             ##########################################################
-            stripped_text_from_html = b''
-            text_content_before_ignored_filter = b''
+            stripped_text_from_html = ''
+
             if regex_matched_output:
                 # @todo some formatter for presentation?
-                stripped_text_from_html = b''.join(regex_matched_output)
-                text_content_before_ignored_filter = stripped_text_from_html
+                stripped_text_from_html = ''.join(regex_matched_output)
+
+        if watch.get('remove_duplicate_lines'):
+            stripped_text_from_html = '\n'.join(dict.fromkeys(line for line in stripped_text_from_html.replace("\n\n", "\n").splitlines()))
 
 
+        if watch.get('sort_text_alphabetically'):
+            # Note: Because a <p>something</p> will add an extra line feed to signify the paragraph gap
+            # we end up with 'Some text\n\n', sorting will add all those extra \n at the start, so we remove them here.
+            stripped_text_from_html = stripped_text_from_html.replace("\n\n", "\n")
+            stripped_text_from_html = '\n'.join(sorted(stripped_text_from_html.splitlines(), key=lambda x: x.lower()))
+
+### CALCULATE MD5
+        # If there's text to ignore
+        text_to_ignore = watch.get('ignore_text', []) + self.datastore.data['settings']['application'].get('global_ignore_text', [])
+        text_for_checksuming = stripped_text_from_html
+        if text_to_ignore:
+            text_for_checksuming = html_tools.strip_ignore_text(stripped_text_from_html, text_to_ignore)
 
         # 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()
+        if text_for_checksuming and self.datastore.data['settings']['application'].get('ignore_whitespace', False):
+            fetched_md5 = hashlib.md5(text_for_checksuming.translate(TRANSLATE_WHITESPACE_TABLE).encode('utf-8')).hexdigest()
         else:
-            fetched_md5 = hashlib.md5(stripped_text_from_html).hexdigest()
+            fetched_md5 = hashlib.md5(text_for_checksuming.encode('utf-8')).hexdigest()
 
         ############ Blocking rules, after checksum #################
         blocked = False
@@ -337,19 +331,33 @@ class perform_site_check(difference_detection_processor):
             if result:
                 blocked = True
 
-        # The main thing that all this at the moment comes down to :)
-        if watch.get('previous_md5') != fetched_md5:
-            changed_detected = True
 
         # Looks like something changed, but did it match all the rules?
         if blocked:
             changed_detected = False
+        else:
+            # The main thing that all this at the moment comes down to :)
+            if watch.get('previous_md5') != fetched_md5:
+                changed_detected = True
+
+            # Always record the new checksum
+            update_obj["previous_md5"] = fetched_md5
+
+            # On the first run of a site, watch['previous_md5'] will be None, set it the current one.
+            if not watch.get('previous_md5'):
+                watch['previous_md5'] = fetched_md5
 
         logger.debug(f"Watch UUID {watch.get('uuid')} content check - Previous MD5: {watch.get('previous_md5')}, Fetched MD5 {fetched_md5}")
 
         if changed_detected:
             if watch.get('check_unique_lines', False):
-                has_unique_lines = watch.lines_contain_something_unique_compared_to_history(lines=stripped_text_from_html.splitlines())
+                ignore_whitespace = self.datastore.data['settings']['application'].get('ignore_whitespace')
+
+                has_unique_lines = watch.lines_contain_something_unique_compared_to_history(
+                    lines=stripped_text_from_html.splitlines(),
+                    ignore_whitespace=ignore_whitespace
+                )
+
                 # One or more lines? unsure?
                 if not has_unique_lines:
                     logger.debug(f"check_unique_lines: UUID {watch.get('uuid')} didnt have anything new setting change_detected=False")
@@ -357,12 +365,6 @@ class perform_site_check(difference_detection_processor):
                 else:
                     logger.debug(f"check_unique_lines: UUID {watch.get('uuid')} had unique content")
 
-        # Always record the new checksum
-        update_obj["previous_md5"] = fetched_md5
-
-        # On the first run of a site, watch['previous_md5'] will be None, set it the current one.
-        if not watch.get('previous_md5'):
-            watch['previous_md5'] = fetched_md5
 
         # stripped_text_from_html - Everything after filters and NO 'ignored' content
         return changed_detected, update_obj, stripped_text_from_html

changedetectionio/static/js/recheck-proxy.js

@@ -1,14 +1,14 @@
 $(function () {
     /* add container before each proxy location to show status */
-
-    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 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>');
+    }
 
     function set_proxy_check_status(proxy_key, state) {
         // select input by value name
@@ -59,8 +59,14 @@ $(function () {
     }
 
     $('#check-all-proxies').click(function (e) {
+
         e.preventDefault()
-        $('body').addClass('proxy-check-active');
+
+        if (!$('body').hasClass('proxy-check-active')) {
+            setup_html_widget();
+            $('body').addClass('proxy-check-active');
+        }
+
         $('.proxy-check-details').html('');
         $('.proxy-status').html('<span class="spinner"></span>').fadeIn();
         $('.proxy-timing').html('');

changedetectionio/static/js/tabs.js

@@ -26,8 +26,7 @@ function set_active_tab() {
     if (tab.length) {
         tab[0].parentElement.className = "active";
     }
-    // hash could move the page down
-    window.scrollTo(0, 0);
+
 }
 
 function focus_error_tab() {

changedetectionio/static/js/watch-settings.js

@@ -42,8 +42,12 @@ function request_textpreview_update() {
                 {
                     'color': '#ee0000',
                     'lines': data['trigger_line_numbers']
+                },
+                {
+                    'color': '#757575',
+                    'lines': data['ignore_line_numbers']
                 }
-            ]);
+            ])
     }).fail(function (error) {
         if (error.statusText === 'abort') {
             console.log('Request was aborted due to a new request being fired.');
@@ -76,8 +80,8 @@ $(document).ready(function () {
         $('body').toggleClass('preview-text-enabled')
         request_textpreview_update();
         const method = $('body').hasClass('preview-text-enabled') ? 'on' : 'off';
-        $('textarea:visible')[method]('keyup blur', request_textpreview_update.throttle(1000));
-        $('input:visible')[method]('keyup blur change', request_textpreview_update.throttle(1000));
+        $('#filters-and-triggers textarea')[method]('blur', request_textpreview_update.throttle(1000));
+        $('#filters-and-triggers input')[method]('change', request_textpreview_update.throttle(1000));
         $("#filters-and-triggers-tab")[method]('click', request_textpreview_update.throttle(1000));
     });
     $('.minitabs-wrapper').miniTabs({

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

@@ -25,15 +25,19 @@ 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: 4em;
+      padding-left: 2em;
+      max-width: 500px;
     }
 
     .proxy-timing {

changedetectionio/static/styles/scss/styles.scss

@@ -147,8 +147,14 @@ body.spinner-active {
   }
 }
 
+
+.tab-pane-inner {
+  // .tab-pane-inner will have the #id that the tab button jumps/anchors to
+  scroll-margin-top: 200px;
+}
+
 section.content {
-  padding-top: 5em;
+  padding-top: 100px;
   padding-bottom: 1em;
   flex-direction: column;
   display: flex;
@@ -931,6 +937,7 @@ $form-edge-padding: 20px;
 }
 
 .tab-pane-inner {
+
   &:not(:target) {
     display: none;
   }

changedetectionio/static/styles/styles.css

@@ -119,19 +119,22 @@ 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: 4em; }
-
-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: 2em;
+    max-width: 500px; }
+  body.proxy-check-active #request .proxy-timing {
+    font-size: 80%;
+    padding-left: 1rem;
+    color: var(--color-link); }
 
 #recommended-proxy {
   display: grid;
@@ -602,8 +605,11 @@ body.spinner-active #pure-menu-horizontal-spinner {
     background-color: var(--color-background-menu-link-hover);
     color: var(--color-text-menu-link-hover); }
 
+.tab-pane-inner {
+  scroll-margin-top: 200px; }
+
 section.content {
-  padding-top: 5em;
+  padding-top: 100px;
   padding-bottom: 1em;
   flex-direction: column;
   display: flex;

changedetectionio/store.py

@@ -4,6 +4,7 @@ from flask import (
     flash
 )
 
+from .html_tools import TRANSLATE_WHITESPACE_TABLE
 from . model import App, Watch
 from copy import deepcopy, copy
 from os import path, unlink
@@ -750,17 +751,17 @@ class ChangeDetectionStore:
     def update_5(self):
         # If the watch notification body, title look the same as the global one, unset it, so the watch defaults back to using the main settings
         # In other words - the watch notification_title and notification_body are not needed if they are the same as the default one
-        current_system_body = self.data['settings']['application']['notification_body'].translate(str.maketrans('', '', "\r\n "))
-        current_system_title = self.data['settings']['application']['notification_body'].translate(str.maketrans('', '', "\r\n "))
+        current_system_body = self.data['settings']['application']['notification_body'].translate(TRANSLATE_WHITESPACE_TABLE)
+        current_system_title = self.data['settings']['application']['notification_body'].translate(TRANSLATE_WHITESPACE_TABLE)
         for uuid, watch in self.data['watching'].items():
             try:
                 watch_body = watch.get('notification_body', '')
-                if watch_body and watch_body.translate(str.maketrans('', '', "\r\n ")) == current_system_body:
+                if watch_body and watch_body.translate(TRANSLATE_WHITESPACE_TABLE) == current_system_body:
                     # Looks the same as the default one, so unset it
                     watch['notification_body'] = None
 
                 watch_title = watch.get('notification_title', '')
-                if watch_title and watch_title.translate(str.maketrans('', '', "\r\n ")) == current_system_title:
+                if watch_title and watch_title.translate(TRANSLATE_WHITESPACE_TABLE) == current_system_title:
                     # Looks the same as the default one, so unset it
                     watch['notification_title'] = None
             except Exception as e:

changedetectionio/templates/edit.html

@@ -26,7 +26,6 @@
 </script>
 <script src="{{url_for('static_content', group='js', filename='plugins.js')}}" defer></script>
 <script src="{{url_for('static_content', group='js', filename='watch-settings.js')}}" defer></script>
-<script src="{{url_for('static_content', group='js', filename='limit.js')}}" defer></script>
 <script src="{{url_for('static_content', group='js', filename='notifications.js')}}" defer></script>
 <script src="{{url_for('static_content', group='js', filename='visual-selector.js')}}" defer></script>
 {% if playwright_enabled %}
@@ -330,9 +329,9 @@ nav
                         {{ render_checkbox_field(form.filter_text_added) }}
                         {{ render_checkbox_field(form.filter_text_replaced) }}
                         {{ render_checkbox_field(form.filter_text_removed) }}
-                    <span class="pure-form-message-inline">Note: Depending on the length and similarity of the text on each line, the algorithm may consider an <strong>addition</strong> instead of <strong>replacement</strong> for example.</span>
-                    <span class="pure-form-message-inline">So it's always better to select <strong>Added</strong>+<strong>Replaced</strong> when you're interested in new content.</span><br>
-                    <span class="pure-form-message-inline">When content is merely moved in a list, it will also trigger an <strong>addition</strong>, consider enabling <code><strong>Only trigger when unique lines appear</strong></code></span>
+                    <span class="pure-form-message-inline">Note: Depending on the length and similarity of the text on each line, the algorithm may consider an <strong>addition</strong> instead of <strong>replacement</strong> for example.</span><br>
+                    <span class="pure-form-message-inline">&nbsp;So it's always better to select <strong>Added</strong>+<strong>Replaced</strong> when you're interested in new content.</span><br>
+                    <span class="pure-form-message-inline">&nbsp;When content is merely moved in a list, it will also trigger an <strong>addition</strong>, consider enabling <code><strong>Only trigger when unique lines appear</strong></code></span>
                 </fieldset>
                 <fieldset class="pure-control-group">
                     {{ render_checkbox_field(form.check_unique_lines) }}
@@ -371,7 +370,7 @@ nav
 ") }}
                     <span class="pure-form-message-inline">
                         <ul>
-                            <li>Matching text will be <strong>removed</strong> from the text snapshot</li>
+                            <li>Matching text will be <strong>ignored</strong> in the text snapshot (you can still see it but it wont trigger a change)</li>
                             <li>Each line processed separately, any line matching will be ignored (removed before creating the checksum)</li>
                             <li>Regular Expression support, wrap the entire line in forward slash <code>/regex/</code></li>
                             <li>Changing this will affect the comparison checksum which may trigger an alert</li>

changedetectionio/templates/settings.html

@@ -172,7 +172,7 @@ nav
                     <span class="pure-form-message-inline">Note: This is applied globally in addition to the per-watch rules.</span><br>
                     <span class="pure-form-message-inline">
                         <ul>
-                            <li>Matching text will be <strong>removed</strong> from the text snapshot</li>
+                            <li>Matching text will be <strong>ignored</strong> in the text snapshot (you can still see it but it wont trigger a change)</li>
                             <li>Note: This is applied globally in addition to the per-watch rules.</li>
                             <li>Each line processed separately, any line matching will be ignored (removed before creating the checksum)</li>
                             <li>Regular Expression support, wrap the entire line in forward slash <code>/regex/</code></li>

changedetectionio/tests/itemprop_test_examples/README.md

@@ -0,0 +1,6 @@
+# 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

@@ -0,0 +1,25 @@
+<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/proxy_list/test_proxy.py

@@ -16,4 +16,4 @@ def test_check_basic_change_detection_functionality(client, live_server, measure
     )
 
     assert b"1 Imported" in res.data
-    time.sleep(3)
+    wait_for_all_checks(client)

changedetectionio/tests/proxy_socks5/test_socks5_proxy.py

@@ -1,7 +1,8 @@
 #!/usr/bin/env python3
+import json
 import os
 from flask import url_for
-from changedetectionio.tests.util import live_server_setup, wait_for_all_checks
+from changedetectionio.tests.util import live_server_setup, wait_for_all_checks, extract_UUID_from_client
 
 
 def set_response():
@@ -18,7 +19,6 @@ def set_response():
         f.write(data)
     time.sleep(1)
 
-
 def test_socks5(client, live_server, measure_memory_usage):
     live_server_setup(live_server)
     set_response()
@@ -79,3 +79,24 @@ def test_socks5(client, live_server, measure_memory_usage):
 
     # Should see the proper string
     assert "Awesome, you made it".encode('utf-8') in res.data
+
+    # PROXY CHECKER WIDGET CHECK - this needs more checking
+    uuid = extract_UUID_from_client(client)
+
+    res = client.get(
+        url_for("check_proxies.start_check", uuid=uuid),
+        follow_redirects=True
+    )
+    # It's probably already finished super fast :(
+    #assert b"RUNNING" in res.data
+    
+    wait_for_all_checks(client)
+    res = client.get(
+        url_for("check_proxies.get_recheck_status", uuid=uuid),
+        follow_redirects=True
+    )
+    assert b"OK" in res.data
+
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data
+

changedetectionio/tests/test_add_replace_remove_filter.py

@@ -77,6 +77,8 @@ 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"))
@@ -151,7 +153,6 @@ 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)
@@ -173,6 +174,5 @@ 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_block_while_text_present.py

@@ -65,11 +65,8 @@ def test_check_block_changedetection_text_NOT_present(client, live_server, measu
     live_server_setup(live_server)
     # Use a mix of case in ZzZ to prove it works case-insensitive.
     ignore_text = "out of stoCk\r\nfoobar"
-
     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)
@@ -127,13 +124,24 @@ def test_check_block_changedetection_text_NOT_present(client, live_server, measu
     assert b'unviewed' not in res.data
     assert b'/test-endpoint' in res.data
 
+    # 2548
+    # Going back to the ORIGINAL should NOT trigger a change
+    set_original_ignore_response()
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    wait_for_all_checks(client)
+    res = client.get(url_for("index"))
+    assert b'unviewed' not in res.data
 
-    # Now we set a change where the text is gone, it should now trigger
+
+    # Now we set a change where the text is gone AND its different content, it should now trigger
     set_modified_response_minus_block_text()
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
     wait_for_all_checks(client)
     res = client.get(url_for("index"))
     assert b'unviewed' in res.data
 
+
+
+
     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
+from .util import live_server_setup, wait_for_all_checks
 
 
 def test_setup(live_server):
@@ -119,12 +119,10 @@ across multiple lines
 
 
 def test_element_removal_full(client, live_server, measure_memory_usage):
-    sleep_time_for_fetch_thread = 3
+    #live_server_setup(live_server)
 
     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)
@@ -132,7 +130,8 @@ 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
-    time.sleep(1)
+    wait_for_all_checks(client)
+
     # 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"
@@ -148,6 +147,7 @@ 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
-    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    assert b'1 watches queued for rechecking.' in res.data
 
-    # Give the thread time to pick it up
-    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"))
@@ -168,10 +168,11 @@ def test_element_removal_full(client, live_server, measure_memory_usage):
     set_modified_response()
 
     # Trigger a check
-    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    assert b'1 watches queued for rechecking.' in res.data
 
     # Give the thread time to pick it up
-    time.sleep(sleep_time_for_fetch_thread)
+    wait_for_all_checks(client)
 
     # There should not be an unviewed change, as changes should be removed
     res = client.get(url_for("index"))

changedetectionio/tests/test_extract_regex.py

@@ -71,7 +71,7 @@ def test_setup(client, live_server, measure_memory_usage):
     live_server_setup(live_server)
 
 def test_check_filter_multiline(client, live_server, measure_memory_usage):
-    #live_server_setup(live_server)
+   # live_server_setup(live_server)
     set_multiline_response()
 
     # Add our URL to the import page

changedetectionio/tests/test_ignore_regex_text.py

@@ -33,13 +33,17 @@ def test_strip_regex_text_func():
 
     stripped_content = html_tools.strip_ignore_text(test_content, ignore_lines)
 
-    assert b"but 1 lines" in stripped_content
-    assert b"igNORe-cAse text" not in stripped_content
-    assert b"but 1234 lines" not in stripped_content
-    assert b"really" not in stripped_content
-    assert b"not this" not in stripped_content
+    assert "but 1 lines" in stripped_content
+    assert "igNORe-cAse text" not in stripped_content
+    assert "but 1234 lines" not in stripped_content
+    assert "really" not in stripped_content
+    assert "not this" not in stripped_content
 
     # Check line number reporting
     stripped_content = html_tools.strip_ignore_text(test_content, ignore_lines, mode="line numbers")
     assert stripped_content == [2, 5, 6, 7, 8, 10]
 
+    # Check that linefeeds are preserved when there are is no matching ignores
+    content = "some text\n\nand other text\n"
+    stripped_content = html_tools.strip_ignore_text(content, ignore_lines)
+    assert content == stripped_content

changedetectionio/tests/test_ignore_text.py

@@ -22,10 +22,15 @@ def test_strip_text_func():
     ignore_lines = ["sometimes"]
 
     stripped_content = html_tools.strip_ignore_text(test_content, ignore_lines)
+    assert "sometimes" not in stripped_content
+    assert "Some content" in stripped_content
 
-    assert b"sometimes" not in stripped_content
-    assert b"Some content" in stripped_content
+    # Check that line feeds dont get chewed up when something is found
+    test_content = "Some initial text\n\nWhich is across multiple lines\n\nZZZZz\n\n\nSo let's see what happens."
+    ignore = ['something irrelevent but just to check', 'XXXXX', 'YYYYY', 'ZZZZZ']
 
+    stripped_content = html_tools.strip_ignore_text(test_content, ignore)
+    assert stripped_content == "Some initial text\n\nWhich is across multiple lines\n\n\n\nSo let's see what happens."
 
 def set_original_ignore_response():
     test_return_data = """<html>
@@ -141,8 +146,6 @@ def test_check_ignore_text_functionality(client, live_server, measure_memory_usa
 
 
 
-
-
     # Just to be sure.. set a regular modified change..
     set_modified_original_ignore_response()
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
@@ -153,17 +156,17 @@ def test_check_ignore_text_functionality(client, live_server, measure_memory_usa
 
     res = client.get(url_for("preview_page", uuid="first"))
 
-    # Should no longer be in the preview
-    assert b'new ignore stuff' not in res.data
+    # SHOULD BE be in the preview, it was added in set_modified_original_ignore_response()
+    # and we have "new ignore stuff" in ignore_text
+    # it is only ignored, it is not removed (it will be highlighted too)
+    assert b'new ignore stuff' in res.data
 
     res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
     assert b'Deleted' in res.data
 
+# When adding some ignore text, it should not trigger a change, even if something else on that line changes
 def test_check_global_ignore_text_functionality(client, live_server, measure_memory_usage):
-
-    # Give the endpoint time to spin up
-    time.sleep(1)
-
+    #live_server_setup(live_server)
     ignore_text = "XXXXX\r\nYYYYY\r\nZZZZZ"
     set_original_ignore_response()
 
@@ -172,6 +175,7 @@ def test_check_global_ignore_text_functionality(client, live_server, measure_mem
         url_for("settings_page"),
         data={
             "requests-time_between_check-minutes": 180,
+            "application-ignore_whitespace": "y",
             "application-global_ignore_text": ignore_text,
             'application-fetch_backend': "html_requests"
         },
@@ -192,9 +196,7 @@ def test_check_global_ignore_text_functionality(client, live_server, measure_mem
     # Give the thread time to pick it up
     wait_for_all_checks(client)
 
-
-    # Goto the edit page of the item, add our ignore text
-    # Add our URL to the import page
+    #Adding some ignore text should not trigger a change
     res = client.post(
         url_for("edit_page", uuid="first"),
         data={"ignore_text": "something irrelevent but just to check", "url": test_url, 'fetch_backend': "html_requests"},
@@ -210,20 +212,15 @@ def test_check_global_ignore_text_functionality(client, live_server, measure_mem
 
     # Trigger a check
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
-
-    # Give the thread time to pick it up
     wait_for_all_checks(client)
-
-    # so that we are sure everything is viewed and in a known 'nothing changed' state
-    res = client.get(url_for("diff_history_page", uuid="first"))
-
-    # It should report nothing found (no new 'unviewed' class)
+    # It should report nothing found (no new 'unviewed' class), adding random ignore text should not cause a change
     res = client.get(url_for("index"))
     assert b'unviewed' not in res.data
     assert b'/test-endpoint' in res.data
+#####
 
-
-    #  Make a change which includes the ignore text
+    # Make a change which includes the ignore text, it should be ignored and no 'change' triggered
+    # It adds text with "ZZZZzzzz" and "ZZZZ" is in the ignore list
     set_modified_ignore_response()
 
     # Trigger a check
@@ -233,6 +230,7 @@ def test_check_global_ignore_text_functionality(client, live_server, measure_mem
 
     # It should report nothing found (no new 'unviewed' class)
     res = client.get(url_for("index"))
+
     assert b'unviewed' not in res.data
     assert b'/test-endpoint' in res.data
 

changedetectionio/tests/test_live_preview.py

@@ -0,0 +1,78 @@
+#!/usr/bin/env python3
+
+from flask import url_for
+from changedetectionio.tests.util import live_server_setup, wait_for_all_checks, extract_UUID_from_client
+
+
+def set_response():
+
+    data = f"""<html>
+       <body>Awesome, you made it<br>
+yeah the socks request worked<br>
+something to ignore<br>
+something to trigger<br>
+     </body>
+     </html>
+    """
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(data)
+
+def test_content_filter_live_preview(client, live_server, measure_memory_usage):
+    live_server_setup(live_server)
+    set_response()
+
+    test_url = url_for('test_endpoint', _external=True)
+
+    res = client.post(
+        url_for("form_quick_watch_add"),
+        data={"url": test_url, "tags": ''},
+        follow_redirects=True
+    )
+    uuid = extract_UUID_from_client(client)
+    res = client.post(
+        url_for("edit_page", uuid=uuid),
+        data={
+            "include_filters": "",
+            "fetch_backend": 'html_requests',
+            "ignore_text": "something to ignore",
+            "trigger_text": "something to trigger",
+            "url": test_url,
+        },
+        follow_redirects=True
+    )
+    assert b"Updated watch." in res.data
+    wait_for_all_checks(client)
+
+    # The endpoint is a POST and accepts the form values to override the watch preview
+    import json
+
+    # DEFAULT OUTPUT WITHOUT ANYTHING UPDATED/CHANGED - SHOULD SEE THE WATCH DEFAULTS
+    res = client.post(
+        url_for("watch_get_preview_rendered", uuid=uuid)
+    )
+    default_return = json.loads(res.data.decode('utf-8'))
+    assert default_return.get('after_filter')
+    assert default_return.get('before_filter')
+    assert default_return.get('ignore_line_numbers') == [3] # "something to ignore" line 3
+    assert default_return.get('trigger_line_numbers') == [4] # "something to trigger" line 4
+
+    # SEND AN UPDATE AND WE SHOULD SEE THE OUTPUT CHANGE SO WE KNOW TO HIGHLIGHT NEW STUFF
+    res = client.post(
+        url_for("watch_get_preview_rendered", uuid=uuid),
+        data={
+            "include_filters": "",
+            "fetch_backend": 'html_requests',
+            "ignore_text": "sOckS", # Also be sure case insensitive works
+            "trigger_text": "AweSOme",
+            "url": test_url,
+        },
+    )
+    reply = json.loads(res.data.decode('utf-8'))
+    assert reply.get('after_filter')
+    assert reply.get('before_filter')
+    assert reply.get('ignore_line_numbers') == [2]  # Ignored - "socks" on line 2
+    assert reply.get('trigger_line_numbers') == [1]  # Triggers "Awesome" in line 1
+
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data

changedetectionio/tests/test_preview_endpoints.py

@@ -0,0 +1,72 @@
+#!/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, extract_UUID_from_client, wait_for_notification_endpoint_output
+from .util import live_server_setup, wait_for_all_checks, wait_for_notification_endpoint_output
 from ..notification import default_notification_format
 
 instock_props = [
@@ -413,3 +413,31 @@ 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

changedetectionio/tests/unit/test_watch_model.py

@@ -18,12 +18,13 @@ class TestDiffBuilder(unittest.TestCase):
 
         watch['last_viewed'] = 110
 
-        watch.save_history_text(contents=b"hello world", timestamp=100, snapshot_id=str(uuid_builder.uuid4()))
-        watch.save_history_text(contents=b"hello world", timestamp=105, snapshot_id=str(uuid_builder.uuid4()))
-        watch.save_history_text(contents=b"hello world", timestamp=109, snapshot_id=str(uuid_builder.uuid4()))
-        watch.save_history_text(contents=b"hello world", timestamp=112, snapshot_id=str(uuid_builder.uuid4()))
-        watch.save_history_text(contents=b"hello world", timestamp=115, snapshot_id=str(uuid_builder.uuid4()))
-        watch.save_history_text(contents=b"hello world", timestamp=117, snapshot_id=str(uuid_builder.uuid4()))
+        # Contents from the browser are always returned from the browser/requests/etc as str, str is basically UTF-16 in python
+        watch.save_history_text(contents="hello world", timestamp=100, snapshot_id=str(uuid_builder.uuid4()))
+        watch.save_history_text(contents="hello world", timestamp=105, snapshot_id=str(uuid_builder.uuid4()))
+        watch.save_history_text(contents="hello world", timestamp=109, snapshot_id=str(uuid_builder.uuid4()))
+        watch.save_history_text(contents="hello world", timestamp=112, snapshot_id=str(uuid_builder.uuid4()))
+        watch.save_history_text(contents="hello world", timestamp=115, snapshot_id=str(uuid_builder.uuid4()))
+        watch.save_history_text(contents="hello world", timestamp=117, snapshot_id=str(uuid_builder.uuid4()))
 
         p = watch.get_next_snapshot_key_to_last_viewed
         assert p == "112", "Correct last-viewed timestamp was detected"

changedetectionio/update_worker.py

@@ -260,9 +260,6 @@ class update_worker(threading.Thread):
                     try:
                         # Processor is what we are using for detecting the "Change"
                         processor = watch.get('processor', 'text_json_diff')
-                        # Abort processing when the content was the same as the last fetch
-                        skip_when_same_checksum = queued_item_data.item.get('skip_when_checksum_same')
-
 
                         # Init a new 'difference_detection_processor', first look in processors
                         processor_module_name = f"changedetectionio.processors.{processor}.processor"
@@ -278,16 +275,13 @@ class update_worker(threading.Thread):
 
                         update_handler.call_browser()
 
-                        changed_detected, update_obj, contents = update_handler.run_changedetection(
-                            watch=watch,
-                            skip_when_checksum_same=skip_when_same_checksum,
-                        )
+                        changed_detected, update_obj, contents = update_handler.run_changedetection(watch=watch)
 
                         # Re #342
                         # In Python 3, all strings are sequences of Unicode characters. There is a bytes type that holds raw bytes.
                         # We then convert/.decode('utf-8') for the notification etc
-                        if not isinstance(contents, (bytes, bytearray)):
-                            raise Exception("Error - returned data from the fetch handler SHOULD be bytes")
+#                        if not isinstance(contents, (bytes, bytearray)):
+#                            raise Exception("Error - returned data from the fetch handler SHOULD be bytes")
                     except PermissionError as e:
                         logger.critical(f"File permission error updating file, watch: {uuid}")
                         logger.critical(str(e))