Design LlamaIndex Data Connectors

Using LlamaIndex, design and implement a data ingestion pipeline that can pull data from a simulated legal document repository (e.g., local PDF files for filings), a news API (simulated with local JSON files), and a public company website (simulated via web scraping of a local HTML file).

Your task is to use `SimpleDirectoryReader`, `WebPageReader`, or custom `BaseReader` implementations to load these documents, and then create a `VectorStoreIndex` using `PineconeVectorStore` for efficient retrieval. Provide Python code snippets for initializing LlamaIndex, defining your readers, and setting up the index.