git clone https://github.com/bpweatherill/WebSearchAndCrawl.git
cd WebSearchAndCrawl

python -m venv venv
source venv/bin/activate  # Linux/Mac
# OR
venv\Scripts\activate   # Windows

pip install -r requirements.txt

playwright install firefox

# Server
MCP_PORT=8808
MCP_HOST=0.0.0.0

# Crawler
MAX_DEPTH=9
MAX_THREADS=5
RATE_LIMIT=5
REQUEST_TIMEOUT=10
MAX_MEMORY_MB=1024

# Firefox
FIREFOX_PROFILE=my_profile  # Optional: Specific Firefox profile
DEFAULT_SEARCH_ENGINE=google

# Directories
INDEX_DIR=./index
DOWNLOADS_DIR=./downloads
CHECKPOINTS_DIR=./checkpoints

python -m server.main

{
  "url": "https://www.nasa.gov",
  "whitelist_domains": "nasa.gov",
  "max_depth": 3,
  "use_token": false,
  "firefox_profile": "my_profile"
}

{
  "excerpt": "NASA's Perseverance Rover lands on Mars...",
  "full_text": "Full article text here...",
  "url": "https://www.nasa.gov/mars2020",
  "timestamp": "2024-05-20T12:00:00Z",
  "domain": "nasa.gov"
}

{
  "domain": "nasa.gov",
  "regex": ".*Mars.*",
  "max_results": 10
}

[
  {
    "url": "https://www.nasa.gov/mars2020",
    "excerpt": "NASA's Perseverance Rover lands on Mars...",
    "timestamp": "2024-05-20T12:00:00Z"
  }
]

{
  "domain": "nasa.gov",
  "regex": ".*\\.pdf$",
  "output_dir": "./downloads/nasa.gov"
}

{
  "filename": "./downloads/nasa.gov/mars_rover.pdf",
  "url": "https://www.nasa.gov/pdf/mars_rover.pdf",
  "parsed_text": "Extracted text from PDF..."
}

{
  "query": "NASA Mars missions",
  "search_engine": "google",
  "use_token": false,
  "firefox_profile": "my_profile"
}

{
  "title": "Mars 2020 Mission - NASA",
  "url": "https://www.nasa.gov/mars2020",
  "snippet": "Learn about the Perseverance Rover..."
}

curl -X POST http://localhost:8808/crawl_website \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://www.nasa.gov",
    "whitelist_domains": "nasa.gov",
    "max_depth": 2,
    "use_token": false
  }'

curl -X POST http://localhost:8808/search_index \
  -H "Content-Type: application/json" \
  -d '{
    "domain": "nasa.gov",
    "regex": ".*Mars.*",
    "max_results": 5
  }'

curl -X POST http://localhost:8808/download_documents \
  -H "Content-Type: application/json" \
  -d '{
    "domain": "nasa.gov",
    "regex": ".*\\.pdf$"
  }'

curl -X POST http://localhost:8808/get_search_results \
  -H "Content-Type: application/json" \
  -d '{
    "query": "NASA Mars missions",
    "search_engine": "google"
  }'

WebSearchAndCrawl/
│
├── server/                          # Core server logic
│   ├── __init__.py
│   ├── main.py                       # FastAPI app + MCP tools
│   ├── config.py                     # Configuration settings
│   ├── schemas.py                    # Pydantic request/response models
│   │
│   ├── firefox/                      # Firefox browser automation
│   │   ├── __init__.py
│   │   ├── controller.py              # Playwright Firefox management
│   │   └── token_manager.py           # Session token handling
│   │
│   ├── crawler/                     # Web crawling logic
│   │   ├── __init__.py
│   │   ├── crawler.py                # Main crawling logic
│   │   └── rate_limiter.py            # Thread/rate limiting
│   │
│   ├── indexer/                     # Indexing and search
│   │   ├── __init__.py
│   │   ├── indexer.py                 # JSON index management
│   │   └── search_engine.py           # Regex search
│   │
│   ├── downloader/                  # Document downloading and parsing
│   │   ├── __init__.py
│   │   ├── downloader.py              # Download logic
│   │   └── parsers/                  # File type parsers
│   │       ├── __init__.py
│   │       ├── pdf_parser.py
│   │       ├── docx_parser.py
│   │       └── xlsx_parser.py
│   │
│   └── streamer.py                   # Chunked JSON streaming
│
├── tests/                           # Unit and integration tests
│   ├── __init__.py
│   ├── test_firefox.py
│   └── test_crawler.py
│
├── index/                           # Index files (auto-generated)
│   ├── nasa.gov.json
│   └── ...
│
├── downloads/                       # Downloaded documents (auto-generated)
│   ├── nasa.gov/
│   │   ├── document1.pdf
│   │   └── ...
│   └── ...
│
├── checkpoints/                     # Crawl checkpoints (auto-generated)
│   └── ...
│
├── requirements.txt                 # Python dependencies
├── .env.example                     # Example environment variables
└── README.md                        # This file