fix:Make JsonCssExtractionStrategy.generate_schema resilient to markdown tags generated by LLMs https://github.com/unclecode/crawl4ai/issues/1663

.github/workflows/docker-release.yml

@@ -11,25 +11,6 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-      - name: Free up disk space
-        run: |
-          echo "=== Disk space before cleanup ==="
-          df -h
-
-          # Remove unnecessary tools and libraries (frees ~25GB)
-          sudo rm -rf /usr/share/dotnet
-          sudo rm -rf /usr/local/lib/android
-          sudo rm -rf /opt/ghc
-          sudo rm -rf /opt/hostedtoolcache/CodeQL
-          sudo rm -rf /usr/local/share/boost
-          sudo rm -rf /usr/share/swift
-
-          # Clean apt cache
-          sudo apt-get clean
-
-          echo "=== Disk space after cleanup ==="
-          df -h
-
       - name: Checkout code
         uses: actions/checkout@v4
 

crawl4ai/extraction_strategy.py

@@ -1378,9 +1378,10 @@ In this scenario, use your best judgment to generate the schema. You need to exa
                 base_url=llm_config.base_url,
                 extra_args=kwargs
             )
-            
+              # Simply strip the markdown formatting
+            raw_json = response.choices[0].message.content.replace('```json\n', '').replace('\n```', '')
             # Extract and return schema
-            return json.loads(response.choices[0].message.content)
+            return json.loads(raw_json)
             
         except Exception as e:
             raise Exception(f"Failed to generate schema: {str(e)}")