Crate hanzo_extract 

Hanzo Extract

Content extraction with built-in sanitization via hanzo-guard.

This crate provides utilities for extracting text content from various sources (web pages, PDFs, etc.) and sanitizing the output for safe use with LLMs.

Features

• Web Extraction: Fetch and extract clean text from web pages
• PDF Extraction: Extract text from PDF documents
• Sanitization: Automatic PII redaction and injection detection via hanzo-guard

Example

use hanzo_extract::{WebExtractor, ExtractorConfig};

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let extractor = WebExtractor::new(ExtractorConfig::default());
    let result = extractor.extract("https://example.com").await?;
    println!("Extracted: {}", result.text);
    Ok(())
}

Architecture

┌─────────────┐     ┌──────────────┐     ┌─────────────────┐
│   Source    │ ──► │  Extractor   │ ──► │  Hanzo Guard    │
│ (URL/PDF)   │     │ (Text Parse) │     │ (Sanitization)  │
└─────────────┘     └──────────────┘     └─────────────────┘
                                                  │
                                                  ▼
                                         ┌─────────────────┐
                                         │  Clean Output   │
                                         │ (LLM-Ready)     │
                                         └─────────────────┘

Re-exports

pub use config::ExtractorConfig;

pub use error::ExtractError;

pub use error::Result;

pub use result::ExtractResult;

pub use web::WebExtractor;

pub use pdf::PdfExtractor;

Modules

config

Extractor configuration

error

Error types for content extraction

pdf

PDF document content extraction

result

Extraction result types

sanitize

Content sanitization using hanzo-guard

web

Web page content extraction

Traits

Extractor

Common trait for all extractors