Oops

changedetectionio/__init__.py

@@ -2,7 +2,7 @@
 
 # Read more https://github.com/dgtlmoon/changedetection.io/wiki
 
-__version__ = '0.46.04'
+__version__ = '0.46.01'
 
 from changedetectionio.strtobool import strtobool
 from json.decoder import JSONDecodeError

changedetectionio/blueprint/browser_steps/__init__.py

@@ -85,8 +85,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         browsersteps_start_session['browserstepper'] = browser_steps.browsersteps_live_ui(
             playwright_browser=browsersteps_start_session['browser'],
             proxy=proxy,
-            start_url=datastore.data['watching'][watch_uuid].get('url'),
-            headers=datastore.data['watching'][watch_uuid].get('headers')
+            start_url=datastore.data['watching'][watch_uuid].get('url')
         )
 
         # For test

changedetectionio/content_fetchers/base.py

@@ -65,8 +65,8 @@ class Fetcher():
 
     def __init__(self):
         import importlib.resources
-        self.xpath_element_js = importlib.resources.files("changedetectionio.content_fetchers.res").joinpath('xpath_element_scraper.js').read_text(encoding='utf-8')
-        self.instock_data_js = importlib.resources.files("changedetectionio.content_fetchers.res").joinpath('stock-not-in-stock.js').read_text(encoding='utf-8')
+        self.xpath_element_js = importlib.resources.files("changedetectionio.content_fetchers.res").joinpath('xpath_element_scraper.js').read_text()
+        self.instock_data_js = importlib.resources.files("changedetectionio.content_fetchers.res").joinpath('stock-not-in-stock.js').read_text()
 
     @abstractmethod
     def get_error(self):
@@ -81,8 +81,7 @@ class Fetcher():
             request_method,
             ignore_status_codes=False,
             current_include_filters=None,
-            is_binary=False,
-            empty_pages_are_a_change=False):
+            is_binary=False):
         # Should set self.error, self.status_code and self.content
         pass
 

changedetectionio/content_fetchers/playwright.py

@@ -83,8 +83,7 @@ class fetcher(Fetcher):
             request_method,
             ignore_status_codes=False,
             current_include_filters=None,
-            is_binary=False,
-            empty_pages_are_a_change=False):
+            is_binary=False):
 
         from playwright.sync_api import sync_playwright
         import playwright._impl._errors
@@ -131,7 +130,7 @@ class fetcher(Fetcher):
             if response is None:
                 context.close()
                 browser.close()
-                logger.debug("Content Fetcher > Response object from the browser communication was none")
+                logger.debug("Content Fetcher > Response object was none")
                 raise EmptyReply(url=url, status_code=None)
 
             try:
@@ -167,10 +166,10 @@ class fetcher(Fetcher):
 
                 raise Non200ErrorCodeReceived(url=url, status_code=self.status_code, screenshot=screenshot)
 
-            if not empty_pages_are_a_change and len(self.page.content().strip()) == 0:
-                logger.debug("Content Fetcher > Content was empty, empty_pages_are_a_change = False")
+            if len(self.page.content().strip()) == 0:
                 context.close()
                 browser.close()
+                logger.debug("Content Fetcher > Content was empty")
                 raise EmptyReply(url=url, status_code=response.status)
 
             # Run Browser Steps here

changedetectionio/content_fetchers/puppeteer.py

@@ -75,8 +75,7 @@ class fetcher(Fetcher):
                          request_method,
                          ignore_status_codes,
                          current_include_filters,
-                         is_binary,
-                         empty_pages_are_a_change
+                         is_binary
                          ):
 
         from changedetectionio.content_fetchers import visualselector_xpath_selectors
@@ -154,7 +153,7 @@ class fetcher(Fetcher):
         if response is None:
             await self.page.close()
             await browser.close()
-            logger.warning("Content Fetcher > Response object was none (as in, the response from the browser was empty, not just the content)")
+            logger.warning("Content Fetcher > Response object was none")
             raise EmptyReply(url=url, status_code=None)
 
         self.headers = response.headers
@@ -187,11 +186,10 @@ class fetcher(Fetcher):
 
             raise Non200ErrorCodeReceived(url=url, status_code=self.status_code, screenshot=screenshot)
         content = await self.page.content
-
-        if not empty_pages_are_a_change and len(content.strip()) == 0:
-            logger.error("Content Fetcher > Content was empty (empty_pages_are_a_change is False), closing browsers")
+        if len(content.strip()) == 0:
             await self.page.close()
             await browser.close()
+            logger.error("Content Fetcher > Content was empty")
             raise EmptyReply(url=url, status_code=response.status)
 
         # Run Browser Steps here
@@ -249,7 +247,7 @@ class fetcher(Fetcher):
         await self.fetch_page(**kwargs)
 
     def run(self, url, timeout, request_headers, request_body, request_method, ignore_status_codes=False,
-            current_include_filters=None, is_binary=False, empty_pages_are_a_change=False):
+            current_include_filters=None, is_binary=False):
 
         #@todo make update_worker async which could run any of these content_fetchers within memory and time constraints
         max_time = os.getenv('PUPPETEER_MAX_PROCESSING_TIMEOUT_SECONDS', 180)
@@ -264,8 +262,7 @@ class fetcher(Fetcher):
                 request_method=request_method,
                 ignore_status_codes=ignore_status_codes,
                 current_include_filters=current_include_filters,
-                is_binary=is_binary,
-                empty_pages_are_a_change=empty_pages_are_a_change
+                is_binary=is_binary
             ), timeout=max_time))
         except asyncio.TimeoutError:
             raise(BrowserFetchTimedOut(msg=f"Browser connected but was unable to process the page in {max_time} seconds."))

changedetectionio/content_fetchers/requests.py

@@ -1,8 +1,9 @@
-from loguru import logger
-import chardet
 import hashlib
 import os
+
+import chardet
 import requests
+
 from changedetectionio import strtobool
 from changedetectionio.content_fetchers.exceptions import BrowserStepsInUnsupportedFetcher, EmptyReply, Non200ErrorCodeReceived
 from changedetectionio.content_fetchers.base import Fetcher
@@ -25,8 +26,7 @@ class fetcher(Fetcher):
             request_method,
             ignore_status_codes=False,
             current_include_filters=None,
-            is_binary=False,
-            empty_pages_are_a_change=False):
+            is_binary=False):
 
         if self.browser_steps_get_valid_steps():
             raise BrowserStepsInUnsupportedFetcher(url=url)
@@ -74,10 +74,7 @@ class fetcher(Fetcher):
         self.headers = r.headers
 
         if not r.content or not len(r.content):
-            if not empty_pages_are_a_change:
-                raise EmptyReply(url=url, status_code=r.status_code)
-            else:
-                logger.debug(f"URL {url} gave zero byte content reply with Status Code {r.status_code}, but empty_pages_are_a_change = True")
+            raise EmptyReply(url=url, status_code=r.status_code)
 
         # @todo test this
         # @todo maybe you really want to test zero-byte return pages?

changedetectionio/content_fetchers/res/stock-not-in-stock.js

@@ -75,7 +75,6 @@ function isItemInStock() {
         'vergriffen',
         'vorbestellen',
         'vorbestellung ist bald möglich',
-        'we don\'t currently have any',
         'we couldn\'t find any products that match',
         'we do not currently have an estimate of when this product will be back in stock.',
         'we don\'t know when or if this item will be back in stock.',
@@ -174,8 +173,7 @@ function isItemInStock() {
         const element = elementsToScan[i];
         // outside the 'fold' or some weird text in the heading area
         // .getBoundingClientRect() was causing a crash in chrome 119, can only be run on contentVisibility != hidden
-        // Note: theres also an automated test that places the 'out of stock' text fairly low down
-        if (element.getBoundingClientRect().top + window.scrollY >= vh + 250 || element.getBoundingClientRect().top + window.scrollY <= 100) {
+        if (element.getBoundingClientRect().top + window.scrollY >= vh + 150 || element.getBoundingClientRect().top + window.scrollY <= 100) {
             continue
         }
         elementText = "";
@@ -189,7 +187,7 @@ function isItemInStock() {
             // and these mean its out of stock
             for (const outOfStockText of outOfStockTexts) {
                 if (elementText.includes(outOfStockText)) {
-                    console.log(`Selected 'Out of Stock' - found text "${outOfStockText}" - "${elementText}" - offset top ${element.getBoundingClientRect().top}, page height is ${vh}`)
+                    console.log(`Selected 'Out of Stock' - found text "${outOfStockText}" - "${elementText}"`)
                     return outOfStockText; // item is out of stock
                 }
             }

changedetectionio/content_fetchers/res/xpath_element_scraper.js

@@ -164,15 +164,6 @@ visibleElementsArray.forEach(function (element) {
         }
     }
 
-    let label = "not-interesting" // A placeholder, the actual labels for training are done by hand for now
-
-    let text = element.textContent.trim().slice(0, 30).trim();
-    while (/\n{2,}|\t{2,}/.test(text)) {
-        text = text.replace(/\n{2,}/g, '\n').replace(/\t{2,}/g, '\t')
-    }
-
-    // Try to identify any possible currency amounts "Sale: 4000" or "Sale now 3000 Kc", can help with the training.
-    const hasDigitCurrency = (/\d/.test(text.slice(0, 6)) || /\d/.test(text.slice(-6)) ) &&  /([€£$¥₩₹]|USD|AUD|EUR|Kč|kr|SEK|,–)/.test(text) ;
 
     size_pos.push({
         xpath: xpath_result,
@@ -180,16 +171,9 @@ visibleElementsArray.forEach(function (element) {
         height: Math.round(bbox['height']),
         left: Math.floor(bbox['left']),
         top: Math.floor(bbox['top']) + scroll_y,
-        // tagName used by Browser Steps
         tagName: (element.tagName) ? element.tagName.toLowerCase() : '',
-        // tagtype used by Browser Steps
         tagtype: (element.tagName.toLowerCase() === 'input' && element.type) ? element.type.toLowerCase() : '',
-        isClickable: window.getComputedStyle(element).cursor === "pointer",
-        // Used by the keras trainer
-        fontSize: window.getComputedStyle(element).getPropertyValue('font-size'),
-        fontWeight: window.getComputedStyle(element).getPropertyValue('font-weight'),
-        hasDigitCurrency: hasDigitCurrency,
-        label: label,
+        isClickable: window.getComputedStyle(element).cursor == "pointer"
     });
 
 });

changedetectionio/content_fetchers/webdriver_selenium.py

@@ -56,8 +56,7 @@ class fetcher(Fetcher):
             request_method,
             ignore_status_codes=False,
             current_include_filters=None,
-            is_binary=False,
-            empty_pages_are_a_change=False):
+            is_binary=False):
 
         from selenium import webdriver
         from selenium.webdriver.chrome.options import Options as ChromeOptions

changedetectionio/flask_app.py

@@ -1377,19 +1377,17 @@ def changedetection_app(config=None, datastore_o=None):
         import brotli
 
         watch = datastore.data['watching'].get(uuid)
-        if watch and watch.history.keys() and os.path.isdir(watch.watch_data_dir):
-            latest_filename = list(watch.history.keys())[-1]
+        if watch and os.path.isdir(watch.watch_data_dir):
+            latest_filename = list(watch.history.keys())[0]
             html_fname = os.path.join(watch.watch_data_dir, f"{latest_filename}.html.br")
-            with open(html_fname, 'rb') as f:
-                if html_fname.endswith('.br'):
-                    # Read and decompress the Brotli file
+            if html_fname.endswith('.br'):
+                # Read and decompress the Brotli file
+                with open(html_fname, 'rb') as f:
                     decompressed_data = brotli.decompress(f.read())
-                else:
-                    decompressed_data = f.read()
 
-            buffer = BytesIO(decompressed_data)
+                buffer = BytesIO(decompressed_data)
 
-            return send_file(buffer, as_attachment=True, download_name=f"{latest_filename}.html", mimetype='text/html')
+                return send_file(buffer, as_attachment=True, download_name=f"{latest_filename}.html", mimetype='text/html')
 
 
         # Return a 500 error

changedetectionio/processors/__init__.py

@@ -26,8 +26,6 @@ class difference_detection_processor():
 
     def call_browser(self):
         from requests.structures import CaseInsensitiveDict
-        from changedetectionio.content_fetchers.exceptions import EmptyReply
-
         # Protect against file:// access
         if re.search(r'^file://', self.watch.get('url', '').strip(), re.IGNORECASE):
             if not strtobool(os.getenv('ALLOW_FILE_URI', 'false')):
@@ -135,18 +133,8 @@ class difference_detection_processor():
         is_binary = self.watch.is_pdf
 
         # And here we go! call the right browser with browser-specific settings
-        empty_pages_are_a_change = self.datastore.data['settings']['application'].get('empty_pages_are_a_change', False)
-
-        self.fetcher.run(url=url,
-                         timeout=timeout,
-                         request_headers=request_headers,
-                         request_body=request_body,
-                         request_method=request_method,
-                         ignore_status_codes=ignore_status_codes,
-                         current_include_filters=self.watch.get('include_filters'),
-                         is_binary=is_binary,
-                         empty_pages_are_a_change=empty_pages_are_a_change
-                         )
+        self.fetcher.run(url, timeout, request_headers, request_body, request_method, ignore_status_codes, self.watch.get('include_filters'),
+                    is_binary=is_binary)
 
         #@todo .quit here could go on close object, so we can run JS if change-detected
         self.fetcher.quit()

changedetectionio/processors/restock_diff/__init__.py

@@ -1,12 +1,11 @@
 
-from babel.numbers import parse_decimal
 from changedetectionio.model.Watch import model as BaseWatch
-from typing import Union
 import re
+from babel.numbers import parse_decimal
 
 class Restock(dict):
 
-    def parse_currency(self, raw_value: str) -> Union[float, None]:
+    def parse_currency(self, raw_value: str) -> float:
         # Clean and standardize the value (ie 1,400.00 should be 1400.00), even better would be store the whole thing as an integer.
         standardized_value = raw_value
 
@@ -22,11 +21,8 @@ class Restock(dict):
         # Remove any non-numeric characters except for the decimal point
         standardized_value = re.sub(r'[^\d.-]', '', standardized_value)
 
-        if standardized_value:
-            # Convert to float
-            return float(parse_decimal(standardized_value, locale='en'))
-
-        return None
+        # Convert to float
+        return float(parse_decimal(standardized_value, locale='en'))
 
     def __init__(self, *args, **kwargs):
         # Define default values

changedetectionio/processors/restock_diff/processor.py

@@ -40,16 +40,13 @@ def get_itemprop_availability(html_content) -> Restock:
     import extruct
     logger.trace(f"Imported extruct module in {time.time() - now:.3f}s")
 
+    value = {}
     now = time.time()
-
     # Extruct is very slow, I'm wondering if some ML is going to be faster (800ms on my i7), 'rdfa' seems to be the heaviest.
-    syntaxes = ['dublincore', 'json-ld', 'microdata', 'microformat', 'opengraph']
-    try:
-        data = extruct.extract(html_content, syntaxes=syntaxes)
-    except Exception as e:
-        logger.warning(f"Unable to extract data, document parsing with extruct failed with {type(e).__name__} - {str(e)}")
-        return Restock()
 
+    syntaxes = ['dublincore', 'json-ld', 'microdata', 'microformat', 'opengraph']
+
+    data = extruct.extract(html_content, syntaxes=syntaxes)
     logger.trace(f"Extruct basic extract of all metadata done in {time.time() - now:.3f}s")
 
     # First phase, dead simple scanning of anything that looks useful

changedetectionio/templates/settings.html

@@ -76,7 +76,7 @@
                     </div>
                     <div class="pure-control-group">
                         {{ render_checkbox_field(form.application.form.empty_pages_are_a_change) }}
-                        <span class="pure-form-message-inline">When a request returns no content, or the HTML does not contain any text, is this considered a change?</span>
+                        <span class="pure-form-message-inline">When a page contains HTML, but no renderable text appears (empty page), is this considered a change?</span>
                     </div>
                 {% if form.requests.proxy %}
                     <div class="pure-control-group inline-radio">

changedetectionio/tests/test_backend.py

@@ -69,12 +69,6 @@ def test_check_basic_change_detection_functionality(client, live_server, measure
 
     wait_for_all_checks(client)
 
-    uuid = extract_UUID_from_client(client)
-
-    # Check the 'get latest snapshot works'
-    res = client.get(url_for("watch_get_latest_html", uuid=uuid))
-    assert b'which has this one new line' in res.data
-
     # Now something should be ready, indicated by having a 'unviewed' class
     res = client.get(url_for("index"))
     assert b'unviewed' in res.data
@@ -92,7 +86,7 @@ def test_check_basic_change_detection_functionality(client, live_server, measure
     assert expected_url.encode('utf-8') in res.data
 
     # Following the 'diff' link, it should no longer display as 'unviewed' even after we recheck it a few times
-    res = client.get(url_for("diff_history_page", uuid=uuid))
+    res = client.get(url_for("diff_history_page", uuid="first"))
     assert b'selected=""' in res.data, "Confirm diff history page loaded"
 
     # Check the [preview] pulls the right one
@@ -149,12 +143,18 @@ def test_check_basic_change_detection_functionality(client, live_server, measure
     assert b'unviewed' not in res.data
 
     # #2458 "clear history" should make the Watch object update its status correctly when the first snapshot lands again
+    uuid = extract_UUID_from_client(client)
     client.get(url_for("clear_watch_history", uuid=uuid))
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
     wait_for_all_checks(client)
     res = client.get(url_for("index"))
     assert b'preview/' in res.data
 
+
+    # Check the 'get latest snapshot works'
+    res = client.get(url_for("watch_get_latest_html", uuid=uuid))
+    assert b'<head><title>head title</title></head>' in res.data
+
     #
     # Cleanup everything
     res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)

changedetectionio/tests/test_nonrenderable_pages.py

@@ -1,7 +1,12 @@
 #!/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
+from urllib.request import urlopen
+from .util import set_original_response, set_modified_response, live_server_setup
+
+sleep_time_for_fetch_thread = 3
+
 
 def set_nonrenderable_response():
     test_return_data = """<html>
@@ -17,13 +22,6 @@ def set_nonrenderable_response():
 
     return None
 
-def set_zero_byte_response():
-
-    with open("test-datastore/endpoint-content.txt", "w") as f:
-        f.write("")
-
-    return None
-
 def test_check_basic_change_detection_functionality(client, live_server, measure_memory_usage):
     set_original_response()
     live_server_setup(live_server)
@@ -37,11 +35,18 @@ def test_check_basic_change_detection_functionality(client, live_server, measure
 
     assert b"1 Imported" in res.data
 
-    wait_for_all_checks(client)
+    time.sleep(sleep_time_for_fetch_thread)
 
-    # It should report nothing found (no new 'unviewed' class)
-    res = client.get(url_for("index"))
-    assert b'unviewed' not in res.data
+    # Do this a few times.. ensures we dont accidently set the status
+    for n in range(3):
+        client.get(url_for("form_watch_checknow"), follow_redirects=True)
+
+        # Give the thread time to pick it up
+        time.sleep(sleep_time_for_fetch_thread)
+
+        # It should report nothing found (no new 'unviewed' class)
+        res = client.get(url_for("index"))
+        assert b'unviewed' not in res.data
 
 
     #####################
@@ -59,7 +64,7 @@ def test_check_basic_change_detection_functionality(client, live_server, measure
     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)
 
     # It should report nothing found (no new 'unviewed' class)
     res = client.get(url_for("index"))
@@ -81,20 +86,14 @@ def test_check_basic_change_detection_functionality(client, live_server, measure
     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)
 
     # It should report nothing found (no new 'unviewed' class)
     res = client.get(url_for("index"))
     assert b'unviewed' in res.data
-    client.get(url_for("mark_all_viewed"), follow_redirects=True)
 
-    # A totally zero byte (#2528) response should also not trigger an error
-    set_zero_byte_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' in res.data # A change should have registered because empty_pages_are_a_change is ON
-    assert b'fetch-error' not in res.data
+
+
 
     #
     # Cleanup everything

changedetectionio/update_worker.py

@@ -1,5 +1,6 @@
 from .processors.exceptions import ProcessorException
-import changedetectionio.content_fetchers.exceptions as content_fetchers_exceptions
+from . import content_fetchers
+
 from changedetectionio.processors.text_json_diff.processor import FilterNotFoundInResponse
 from changedetectionio import html_tools
 
@@ -300,7 +301,7 @@ class update_worker(threading.Thread):
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': e.message})
                         process_changedetection_results = False
 
-                    except content_fetchers_exceptions.ReplyWithContentButNoText as e:
+                    except content_fetchers.exceptions.ReplyWithContentButNoText as e:
                         # Totally fine, it's by choice - just continue on, nothing more to care about
                         # Page had elements/content but no renderable text
                         # Backend (not filters) gave zero output
@@ -326,7 +327,7 @@ class update_worker(threading.Thread):
                             
                         process_changedetection_results = False
 
-                    except content_fetchers_exceptions.Non200ErrorCodeReceived as e:
+                    except content_fetchers.exceptions.Non200ErrorCodeReceived as e:
                         if e.status_code == 403:
                             err_text = "Error - 403 (Access denied) received"
                         elif e.status_code == 404:
@@ -379,23 +380,23 @@ class update_worker(threading.Thread):
 
                         process_changedetection_results = False
 
-                    except content_fetchers_exceptions.checksumFromPreviousCheckWasTheSame as e:
+                    except content_fetchers.exceptions.checksumFromPreviousCheckWasTheSame as e:
                         # Yes fine, so nothing todo, don't continue to process.
                         process_changedetection_results = False
                         changed_detected = False
-                    except content_fetchers_exceptions.BrowserConnectError as e:
+                    except content_fetchers.exceptions.BrowserConnectError as e:
                         self.datastore.update_watch(uuid=uuid,
                                                     update_obj={'last_error': e.msg
                                                                 }
                                                     )
                         process_changedetection_results = False
-                    except content_fetchers_exceptions.BrowserFetchTimedOut as e:
+                    except content_fetchers.exceptions.BrowserFetchTimedOut as e:
                         self.datastore.update_watch(uuid=uuid,
                                                     update_obj={'last_error': e.msg
                                                                 }
                                                     )
                         process_changedetection_results = False
-                    except content_fetchers_exceptions.BrowserStepsStepException as e:
+                    except content_fetchers.exceptions.BrowserStepsStepException as e:
 
                         if not self.datastore.data['watching'].get(uuid):
                             continue
@@ -437,25 +438,25 @@ class update_worker(threading.Thread):
 
                         process_changedetection_results = False
 
-                    except content_fetchers_exceptions.EmptyReply as e:
+                    except content_fetchers.exceptions.EmptyReply as e:
                         # Some kind of custom to-str handler in the exception handler that does this?
                         err_text = "EmptyReply - try increasing 'Wait seconds before extracting text', Status Code {}".format(e.status_code)
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
                                                                            'last_check_status': e.status_code})
                         process_changedetection_results = False
-                    except content_fetchers_exceptions.ScreenshotUnavailable as e:
+                    except content_fetchers.exceptions.ScreenshotUnavailable as e:
                         err_text = "Screenshot unavailable, page did not render fully in the expected time or page was too long - try increasing 'Wait seconds before extracting text'"
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
                                                                            'last_check_status': e.status_code})
                         process_changedetection_results = False
-                    except content_fetchers_exceptions.JSActionExceptions as e:
+                    except content_fetchers.exceptions.JSActionExceptions as e:
                         err_text = "Error running JS Actions - Page request - "+e.message
                         if e.screenshot:
                             watch.save_screenshot(screenshot=e.screenshot, as_error=True)
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
                                                                            'last_check_status': e.status_code})
                         process_changedetection_results = False
-                    except content_fetchers_exceptions.PageUnloadable as e:
+                    except content_fetchers.exceptions.PageUnloadable as e:
                         err_text = "Page request from server didnt respond correctly"
                         if e.message:
                             err_text = "{} - {}".format(err_text, e.message)
@@ -467,7 +468,7 @@ class update_worker(threading.Thread):
                                                                            'last_check_status': e.status_code,
                                                                            'has_ldjson_price_data': None})
                         process_changedetection_results = False
-                    except content_fetchers_exceptions.BrowserStepsInUnsupportedFetcher as e:
+                    except content_fetchers.exceptions.BrowserStepsInUnsupportedFetcher as e:
                         err_text = "This watch has Browser Steps configured and so it cannot run with the 'Basic fast Plaintext/HTTP Client', either remove the Browser Steps or select a Chrome fetcher."
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text})
                         process_changedetection_results = False

docker-compose.yml

@@ -18,7 +18,7 @@ services:
   #
   #        Log levels are in descending order. (TRACE is the most detailed one)
   #        Log output levels: TRACE, DEBUG(default), INFO, SUCCESS, WARNING, ERROR, CRITICAL
-  #      - LOGGER_LEVEL=TRACE
+  #      - LOGGER_LEVEL=DEBUG
   #
   #       Alternative WebDriver/selenium URL, do not use "'s or 's!
   #      - WEBDRIVER_URL=http://browser-chrome:4444/wd/hub
@@ -29,9 +29,8 @@ services:
   #
   #             https://selenium-python.readthedocs.io/api.html#module-selenium.webdriver.common.proxy
   #
-  #       Alternative target "Chrome" Playwright URL, do not use "'s or 's!
-  #       "Playwright" is a driver/librarythat allows changedetection to talk to a Chrome or similar browser.
-  #      - PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000
+  #       Alternative Playwright URL, do not use "'s or 's!
+  #      - PLAYWRIGHT_DRIVER_URL=ws://playwright-chrome:3000
   #
   #       Playwright proxy settings playwright_proxy_server, playwright_proxy_bypass, playwright_proxy_username, playwright_proxy_password
   #
@@ -74,10 +73,10 @@ services:
 #              condition: service_started
 
 
-     # Sockpuppetbrowser is basically chrome wrapped in an API for allowing fast fetching of web-pages.
+     # Used for fetching pages via Playwright+Chrome where you need Javascript support.
      # RECOMMENDED FOR FETCHING PAGES WITH CHROME
-#    sockpuppetbrowser:
-#        hostname: sockpuppetbrowser
+#    playwright-chrome:
+#        hostname: playwright-chrome
 #        image: dgtlmoon/sockpuppetbrowser:latest
 #        cap_add:
 #            - SYS_ADMIN

requirements.txt

@@ -79,9 +79,8 @@ pyppeteerstealth>=0.0.4
 pytest ~=7.2
 pytest-flask ~=1.2
 
-# Anything 4.0 and up but not 5.0
-jsonschema ~= 4.0
-
+# Pin jsonschema version to prevent build errors on armv6 while rpds-py wheels aren't available (1708)
+jsonschema==4.17.3
 
 loguru