Handle multiple products error

changedetectionio/processors/exceptions.py

@@ -0,0 +1,10 @@
+class ProcessorException(Exception):
+    def __init__(self, message=None, status_code=None, url=None, screenshot=None, has_filters=False, html_content='', xpath_data=None):
+        self.message = message
+        self.status_code = status_code
+        self.url = url
+        self.screenshot = screenshot
+        self.has_filters = has_filters
+        self.html_content = html_content
+        self.xpath_data = xpath_data
+        return

changedetectionio/processors/restock_diff/__init__.py

@@ -6,7 +6,7 @@ from babel.numbers import parse_decimal
 class Restock(dict):
 
     def parse_currency(self, raw_value: str) -> float:
-        # Clean and standardize the value
+        # 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
 
         if ',' in standardized_value and '.' in standardized_value:

changedetectionio/processors/restock_diff/processor.py

@@ -1,4 +1,5 @@
 from .. import difference_detection_processor
+from ..exceptions import ProcessorException
 from . import Restock
 from loguru import logger
 import hashlib
@@ -16,6 +17,10 @@ class UnableToExtractRestockData(Exception):
         self.status_code = status_code
         return
 
+class MoreThanOnePriceFound(Exception):
+    def __init__(self):
+        return
+
 def _search_prop_by_value(matches, value):
     for properties in matches:
         for prop in properties:
@@ -54,6 +59,9 @@ def get_itemprop_availability(html_content) -> Restock:
 
         price_result = price_parse.find(data)
         if price_result:
+            if len(price_result) > 1:
+                raise MoreThanOnePriceFound()
+
             value['price'] = price_result[0].value
 
         pricecurrency_result = pricecurrency_parse.find(data)
@@ -119,7 +127,18 @@ class perform_site_check(difference_detection_processor):
         update_obj['content_type'] = self.fetcher.headers.get('Content-Type', '')
         update_obj["last_check_status"] = self.fetcher.get_last_status_code()
 
+        itemprop_availability = {}
+        try:
             itemprop_availability = get_itemprop_availability(html_content=self.fetcher.content)
+        except MoreThanOnePriceFound as e:
+            # Add the real data
+            raise ProcessorException(message="Cannot run, more than one price detected, this plugin is only for product pages with ONE product, try the content-change detection mode.",
+                                     url=watch.get('url'),
+                                     status_code=self.fetcher.get_last_status_code(),
+                                     screenshot=self.fetcher.screenshot,
+                                     xpath_data=self.fetcher.xpath_data
+                                     )
+
         # Something valid in get_itemprop_availability() by scraping metadata ?
         if itemprop_availability.get('price') or itemprop_availability.get('availability'):
             # Store for other usage

changedetectionio/templates/watch-overview.html

@@ -154,6 +154,7 @@
                       <span class="watch-tag-list">{{ watch_tag.title }}</span>
                     {% endfor %}
                 </td>
+            <!-- @todo make it so any watch handler obj can expose this --->
 {% if any_has_restock_price_processor %}
                 <td class="restock-and-price">
                     {% if watch['processor'] == 'restock_diff'  %}
@@ -173,8 +174,6 @@
                         {% elif not watch.has_restock_info %}
                             <span class="restock-label error">No information</span>
                         {% endif %}
-
-
                     {% endif %}
                 </td>
 {% endif %}

changedetectionio/update_worker.py

@@ -1,4 +1,6 @@
+from .processors.exceptions import ProcessorException
 from . import content_fetchers
+
 from .processors.restock_diff.processor import UnableToExtractRestockData
 from changedetectionio.processors.text_json_diff.processor import FilterNotFoundInResponse
 from changedetectionio import html_tools
@@ -287,6 +289,16 @@ class update_worker(threading.Thread):
                         logger.critical(f"File permission error updating file, watch: {uuid}")
                         logger.critical(str(e))
                         process_changedetection_results = False
+
+                    # A generic other-exception thrown by processors
+                    except ProcessorException as e:
+                        if e.screenshot:
+                            watch.save_screenshot(screenshot=e.screenshot)
+                        if e.xpath_data:
+                            watch.save_xpath_data(data=e.xpath_data)
+                        self.datastore.update_watch(uuid=uuid, update_obj={'last_error': e.message})
+                        process_changedetection_results = False
+
                     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