Process subtractive_selectors first

Currently, if a filter rule is more selective than the subtractive selector, the subtractive selector will not be executed because the information by which to do the subtraction is already discarded. This fixes that by removing elements first and then applying filter selections.
dgtlmoon · Sep 27, 2022 · cb4c7dd · cb4c7dd
1 parent 3ebb2ab
commit cb4c7dd
Showing 1 changed file with 5 additions and 5 deletions.
diff --git a/changedetectionio/fetch_site_status.py b/changedetectionio/fetch_site_status.py
@@ -157,17 +157,17 @@ def run(self, uuid):
                 stripped_text_from_html = html_content
             else:
                 # Then we assume HTML
+                if has_subtractive_selectors:
+                    html_content = html_tools.element_removal(subtractive_selectors, html_content)
+
                 if has_filter_rule:
                     # For HTML/XML we offer xpath as an option, just start a regular xPath "/.."
                     if css_filter_rule[0] == '/' or css_filter_rule.startswith('xpath:'):
                         html_content = html_tools.xpath_filter(xpath_filter=css_filter_rule.replace('xpath:', ''),
-                                                               html_content=fetcher.content)
+                                                               html_content=html_content)
                     else:
                         # CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text
-                        html_content = html_tools.css_filter(css_filter=css_filter_rule, html_content=fetcher.content)
-
-                if has_subtractive_selectors:
-                    html_content = html_tools.element_removal(subtractive_selectors, html_content)
+                        html_content = html_tools.css_filter(css_filter=css_filter_rule, html_content=html_content)
 
                 if not is_source:
                     # extract text