fix: pass logger to WebScrapingStrategy and update score computation in PruningContentFilter

crawl4ai/async_webcrawler.py

@@ -472,7 +472,9 @@ class AsyncWebCrawler:
         try:
             _url = url if not kwargs.get("is_raw_html", False) else "Raw HTML"
             t1 = time.perf_counter()
-            scrapping_strategy = WebScrapingStrategy()
+            scrapping_strategy = WebScrapingStrategy(
+                logger=self.logger,
+            )
             # result = await scrapping_strategy.ascrap(
             result = scrapping_strategy.scrap(
                 url,

crawl4ai/content_filter_strategy.py

@@ -468,7 +468,7 @@ class PruningContentFilter(RelevantContentFilter):
             'link_text_len': link_text_len
         }
 
-        score = self._compute_composite_score(metrics)
+        score = self._compute_composite_score(metrics, text_len, tag_len, link_text_len)
 
         if self.threshold_type == 'fixed':
             should_remove = score < self.threshold