UI - Restock/pricing - Handle when price amount is sometimes string or integer (#3950)

Author: dgtlmoon

changedetectionio/blueprint/watchlist/templates/watch-overview.html

@@ -305,12 +305,20 @@
                         {%- endif -%}
 
                         {%- if watch.get('restock') and watch['restock'].get('price') -%}
-                                {%- if watch['restock']['price'] is number -%}
-                                <span class="restock-label price" title="{{ _('Price') }}">
-                                {{ watch['restock']['price']|format_number_locale if watch['restock'].get('price') else '' }} {{ watch['restock'].get('currency','') }}
-                                </span>
-                                {%- else -%} <!-- watch['restock']['price']' is not a number, cant output it -->
+                            {%- set restock = watch['restock'] -%}
+                            {%- set price = restock.get('price') -%}
+                            {%- set cur = restock.get('currency','') -%}
+
+                            {%- if price is not none and (price|string)|regex_search('\d') -%}
+                              <span class="restock-label price" title="{{ _('Price') }}">
+                              {# @todo: make parse_currency/parse_decimal aware of the locale of the actual web page and use that instead changedetectionio/processors/restock_diff/__init__.py #}
+                                {%- if price is number -%}{# It's a number so we can convert it to their locale' #}
+                                  {{ price|format_number_locale }} {{ cur }}<!-- as number -->
+                                {%- else -%}{# It's totally fine if it arrives as something else, the website might be something weird in this field #}
+                                  {{ price }} {{ cur }}<!-- as string -->
                                 {%- endif -%}
+                              </span>
+                            {%- endif -%}
                         {%- elif not watch.has_restock_info -%}
                             <span class="restock-label error">{{ _('No information') }}</span>
                         {%- endif -%}

changedetectionio/flask_app.py

@@ -217,9 +217,13 @@ def _jinja2_filter_format_number_locale(value: float) -> str:
     "Formats for example 4000.10 to the local locale default of 4,000.10"
     # Format the number with two decimal places (locale format string will return 6 decimal)
     formatted_value = locale.format_string("%.2f", value, grouping=True)
-
     return formatted_value
 
+@app.template_filter('regex_search')
+def _jinja2_filter_regex_search(value, pattern):
+    import re
+    return re.search(pattern, str(value)) is not None
+
 @app.template_global('is_checking_now')
 def _watch_is_checking_now(watch_obj, format="%Y-%m-%d %H:%M:%S"):
     return worker_pool.is_watch_running(watch_obj['uuid'])

changedetectionio/processors/restock_diff/__init__.py

@@ -31,6 +31,7 @@ def parse_currency(self, raw_value: str) -> Union[float, None]:
 
         if standardized_value:
             # Convert to float
+            # @todo locale needs to be the locale of the webpage
             return float(parse_decimal(standardized_value, locale='en'))
 
         return None

changedetectionio/processors/restock_diff/pure_python_extractor.py

@@ -283,4 +283,7 @@ def query_price_availability(extracted_data):
     if not result.get('availability') and 'availability' in microdata:
         result['availability'] = microdata['availability']
 
+    # result['price'] could be float or str here, depending on the website, for example it might contain "1,00" commas, etc.
+    # using something like babel you need to know the locale of the website and even then it can be problematic
+    # we dont really do anything with the price data so far.. so just accept it the way it comes.
     return result

changedetectionio/tests/test_restock_itemprop.py

@@ -467,3 +467,38 @@ def test_special_prop_examples(client, live_server, measure_memory_usage, datast
             assert b'155.55' in res.data
 
     delete_all_watches(client)
+
+
+def test_itemprop_as_str(client, live_server, measure_memory_usage, datastore_path):
+
+    test_return_data = f"""<html>
+       <body>
+     Some initial text<br>
+     <p>Which is across multiple lines</p>
+<span itemprop="offers" itemscope itemtype="http://schema.org/Offer">
+<meta content="767.55" itemprop="price"/>
+<meta content="EUR" itemprop="priceCurrency"/>
+<meta content="InStock" itemprop="availability"/>
+<meta content="https://www.123-test.dk" itemprop="url"/>
+</span>
+     </body>
+     </html>
+    """
+
+    with open(os.path.join(datastore_path, "endpoint-content.txt"), "w") as f:
+        f.write(test_return_data)
+
+
+    test_url = url_for('test_endpoint', _external=True)
+
+    client.post(
+        url_for("ui.ui_views.form_quick_watch_add"),
+        data={"url": test_url, "tags": 'restock tests', 'processor': 'restock_diff'},
+        follow_redirects=True
+    )
+
+    client.get(url_for("ui.form_watch_checknow"))
+    wait_for_all_checks(client)
+
+    res = client.get(url_for("watchlist.index"))
+    assert b'767.55' in res.data