feat: lite deep researcher implementation

src/crawler/readability_extractor.py

@@ -0,0 +1,12 @@
+from readabilipy import simple_json_from_html_string
+
+from .article import Article
+
+
+class ReadabilityExtractor:
+    def extract_article(self, html: str) -> Article:
+        article = simple_json_from_html_string(html, use_readability=True)
+        return Article(
+            title=article.get("title"),
+            html_content=article.get("content"),
+        )