Fix "raw://" URL parsing logic

Closes https://github.com/unclecode/crawl4ai/issues/686
2025-02-15 15:34:59 +00:00
parent dde14eba7d
commit 27af4cc27b
2 changed files with 27 additions and 2 deletions
--- a/crawl4ai/async_crawler_strategy.py
+++ b/crawl4ai/async_crawler_strategy.py
@@ -1231,9 +1231,9 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
                get_delayed_content=None,
            )

-        elif url.startswith("raw:") or url.startswith("raw://"):
+        elif url.startswith("raw:"):
            # Process raw HTML content
-            raw_html = url[4:] if url[:4] == "raw:" else url[7:]
+            raw_html = url[6:] if url.startswith("raw://") else url[4:]
            html = raw_html
            if config.screenshot:
                screenshot_data = await self._generate_screenshot_from_html(html)