:zap: [Enhance] ignore classes pattern, especially for 163.com

documents/webpage_content_extractor.py

@@ -34,7 +34,8 @@ class WebpageContentExtractor:
 
     def remove_elements_from_html(self, html_str):
         soup = BeautifulSoup(html_str, "html.parser")
-        ignore_classes_pattern = f'{"|".join(IGNORE_CLASSES)}'
+        ignore_classes_with_parentheses = [f"({word})" for word in IGNORE_CLASSES]
+        ignore_classes_pattern = f'{"|".join(ignore_classes_with_parentheses)}'
         removed_element_counts = 0
         for element in soup.find_all():
             class_str = ""

networks/network_configs.py

@@ -8,7 +8,10 @@ IGNORE_CLASSES = [
     # "menu",
     "offcanvas",
     "navbar",
-    "post_side",
+    # 163.com
+    "post_(top)|(side)|(recommends)|(crumb)|(statement)|(next)|(jubao)",
+    "ntes-.*nav",
+    "nav-bottom",
 ]
 
 IGNORE_HOSTS = [