FastMCP Documentation & Web Scraping Server

import os import requests import zipfile import io from minsearch import Index ZIP_URL = "https://github.com/jlowin/fastmcp/archive/refs/heads/main.zip" ZIP_NAME = "fastmcp-main.zip" def ensure_zip(): if os.path.exists(ZIP_NAME): print(f"Zip already exists: {ZIP_NAME}") return print(f"Downloading {ZIP_URL} -> {ZIP_NAME}") resp = requests.get(ZIP_URL, stream=True, timeout=60) resp.raise_for_status() with open(ZIP_NAME, "wb") as f: for chunk in resp.iter_content(1024 * 64): if chunk: f.write(chunk) def iter_md_files_from_zip(zip_path): with zipfile.ZipFile(zip_path, "r") as z: for name in z.namelist(): lower = name.lower() if lower.endswith(".md") or lower.endswith(".mdx"): # read file data = z.read(name) text = data.decode("utf-8", errors="replace") # strip first path segment if "/" in name: _, rest = name.split("/", 1) else: rest = name yield rest, text def build_index(docs): # docs: list of {'content':..., 'filename':...} idx = Index(text_fields=["content"], keyword_fields=["filename"]) idx.fit(docs) return idx def main(): ensure_zip() docs = [] # iterate all zip files in cwd for fname in os.listdir('.'): if fname.lower().endswith('.zip'): for filename, text in iter_md_files_from_zip(fname): docs.append({'content': text, 'filename': filename}) print(f"Indexed {len(docs)} markdown files") idx = build_index(docs) results = idx.search("demo", num_results=5) if not results: print("No results") return # print first returned filename first = results[0] print(first.get('filename')) if __name__ == '__main__': main()