app.py

# File: main/app.py
# Purpose: One Space that offers five tools/tabs:
#   1) Fetch — extract relevant page content (title, metadata, clean text, hyperlinks)
#   2) DDG (Concise) — ultra-succinct DuckDuckGo search that emits JSONL with short keys to minimize tokens
#   3) Websearch — structured DuckDuckGo search via LangChain tool (JSON)
#   4) Unstructured DDG — raw DuckDuckGo list[dict] rendered into a Textbox
#   5) Generate Sitemap — LIMITED: grouped internal/external links with an optional per-domain cap (and a .md download)

from __future__ import annotations

import re
import json
from typing import List, Dict, Literal, Tuple

import gradio as gr
import requests
from bs4 import BeautifulSoup
from readability import Document
from urllib.parse import urljoin, urldefrag, urlparse
from langchain_community.tools import DuckDuckGoSearchResults
from duckduckgo_search import DDGS


# ==============================
# Fetch: HTTP + extraction utils
# ==============================

def _http_get(url: str) -> requests.Response:
    """
    Download the page politely with a short timeout and realistic headers.
    (Layman's terms: grab the web page like a normal browser would, but quickly.)
    """
    headers = {
        "User-Agent": "Mozilla/5.0 (compatible; WebMCP/1.0; +https://example.com)",
        "Accept-Language": "en-US,en;q=0.9",
        "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
    }
    return requests.get(url, headers=headers, timeout=15)


def _normalize_whitespace(text: str) -> str:
    """
    Squeeze extra spaces and blank lines to keep things compact.
    (Layman's terms: tidy up the text so it’s not full of weird spacing.)
    """
    text = re.sub(r"[ \t\u00A0]+", " ", text)
    text = re.sub(r"\n\s*\n\s*\n+", "\n\n", text.strip())
    return text.strip()


def _truncate(text: str, max_chars: int) -> Tuple[str, bool]:
    """
    Cut text if it gets too long; return the text and whether we trimmed.
    (Layman's terms: shorten long text and tell us if we had to cut it.)
    """
    if max_chars is None or max_chars <= 0 or len(text) <= max_chars:
        return text, False
    return text[:max_chars].rstrip() + " …", True


def _shorten(text: str, limit: int) -> str:
    """
    Hard cap a string with an ellipsis to keep tokens small.
    (Layman's terms: force a string to a max length with an ellipsis.)
    """
    if limit <= 0 or len(text) <= limit:
        return text
    return text[: max(0, limit - 1)].rstrip() + "…"


def _domain_of(url: str) -> str:
    """
    Show a friendly site name like "example.com".
    (Layman's terms: pull the website's domain.)
    """
    try:
        return urlparse(url).netloc or ""
    except Exception:
        return ""


def _meta(soup: BeautifulSoup, name: str) -> str | None:
    tag = soup.find("meta", attrs={"name": name})
    return tag.get("content") if tag and tag.has_attr("content") else None


def _og(soup: BeautifulSoup, prop: str) -> str | None:
    tag = soup.find("meta", attrs={"property": prop})
    return tag.get("content") if tag and tag.has_attr("content") else None


def _extract_metadata(soup: BeautifulSoup, final_url: str) -> Dict[str, str]:
    """
    Pull the useful bits: title, description, site name, canonical URL, language, etc.
    (Layman's terms: gather page basics like title/description/address.)
    """
    meta: Dict[str, str] = {}

    # Title preference: <title> > og:title > twitter:title
    title_candidates = [
        (soup.title.string if soup.title and soup.title.string else None),
        _og(soup, "og:title"),
        _meta(soup, "twitter:title"),
    ]
    meta["title"] = next((t.strip() for t in title_candidates if t and t.strip()), "")

    # Description preference: description > og:description > twitter:description
    desc_candidates = [
        _meta(soup, "description"),
        _og(soup, "og:description"),
        _meta(soup, "twitter:description"),
    ]
    meta["description"] = next((d.strip() for d in desc_candidates if d and d.strip()), "")

    # Canonical link (helps dedupe)
    link_canonical = soup.find("link", rel=lambda v: v and "canonical" in v)
    meta["canonical"] = (link_canonical.get("href") or "").strip() if link_canonical else ""

    # Site name + language info if present
    meta["site_name"] = (_og(soup, "og:site_name") or "").strip()
    html_tag = soup.find("html")
    meta["lang"] = (html_tag.get("lang") or "").strip() if html_tag else ""

    # Final URL + domain
    meta["fetched_url"] = final_url
    meta["domain"] = _domain_of(final_url)

    return meta


def _extract_main_text(html: str) -> Tuple[str, BeautifulSoup]:
    """
    Use Readability to isolate the main article and turn it into clean text.
    Returns (clean_text, soup_of_readable_html).
    (Layman's terms: find the real article text and clean it.)
    """
    # Simplified article HTML from Readability
    doc = Document(html)
    readable_html = doc.summary(html_partial=True)

    # Parse simplified HTML
    s = BeautifulSoup(readable_html, "lxml")

    # Remove noisy tags
    for sel in ["script", "style", "noscript", "iframe", "svg"]:
        for tag in s.select(sel):
            tag.decompose()

    # Keep paragraphs, list items, and subheadings for structure without bloat
    text_parts: List[str] = []
    for p in s.find_all(["p", "li", "h2", "h3", "h4", "blockquote"]):
        chunk = p.get_text(" ", strip=True)
        if chunk:
            text_parts.append(chunk)

    clean_text = _normalize_whitespace("\n\n".join(text_parts))
    return clean_text, s


def _extract_links(readable_soup: BeautifulSoup, base_url: str, max_links: int) -> List[Tuple[str, str]]:
    """
    Collect clean, unique, absolute links from the readable section only.
    (Layman's terms: pull a tidy list of links from the article body.)
    """
    seen = set()
    links: List[Tuple[str, str]] = []

    for a in readable_soup.find_all("a", href=True):
        href = a.get("href").strip()
        # Skip junk links we can't use
        if not href or href.startswith("#") or href.startswith("mailto:") or href.startswith("javascript:"):
            continue

        # Resolve relative URLs, strip fragments (#…)
        absolute = urljoin(base_url, href)
        absolute, _ = urldefrag(absolute)

        if absolute in seen:
            continue
        seen.add(absolute)

        text = a.get_text(" ", strip=True)
        if len(text) > 120:
            text = text[:117] + "…"

        links.append((text or absolute, absolute))

        if len(links) >= max_links > 0:
            break

    return links


def _format_markdown(
    meta: Dict[str, str],
    body: str,
    body_truncated: bool,
    links: List[Tuple[str, str]],
    include_text: bool,
    include_metadata: bool,
    include_links: bool,
    verbosity: str,
) -> str:
    """
    Assemble a compact Markdown summary with optional sections.
    (Layman's terms: build the final markdown output with options.)
    """
    lines: List[str] = []

    # Title header
    title = meta.get("title") or meta.get("domain") or "Untitled"
    lines.append(f"# {title}")

    # Metadata section (only show what exists)
    if include_metadata:
        md: List[str] = []
        if meta.get("description"):
            md.append(f"- **Description:** {meta['description']}")
        if meta.get("site_name"):
            md.append(f"- **Site:** {meta['site_name']}")
        if meta.get("canonical"):
            md.append(f"- **Canonical:** {meta['canonical']}")
        if meta.get("lang"):
            md.append(f"- **Language:** {meta['lang']}")
        if meta.get("fetched_url"):
            md.append(f"- **Fetched From:** {meta['fetched_url']}")
        if md:
            lines.append("## Metadata")
            lines.extend(md)

    # Body text
    if include_text and body:
        if verbosity == "Brief":
            brief, was_more = _truncate(body, 800)
            lines.append("## Text")
            lines.append(brief)
            if was_more or body_truncated:
                lines.append("\n> (Trimmed for brevity)")
        else:
            lines.append("## Text")
            lines.append(body)
            if body_truncated:
                lines.append("\n> (Trimmed for brevity)")

    # Links section
    if include_links and links:
        lines.append(f"## Links ({len(links)})")
        for text, url in links:
            lines.append(f"- [{text}]({url})")

    return "\n\n".join(lines).strip()


def Fetch_Webpage(  # <-- MCP tool #1 (Fetch)
    url: str,
    verbosity: str = "Standard",
    include_metadata: bool = True,
    include_text: bool = True,
    include_links: bool = True,
    max_chars: int = 3000,
    max_links: int = 20,
) -> str:
    """
    Fetch a web page and return a compact Markdown summary that includes title, key
    metadata, readable main text, and outbound links.

    (Layman's terms: summarize a page with clean text + useful details.)
    """
    if not url or not url.strip():
        return "Please enter a valid URL."

    try:
        resp = _http_get(url)
        resp.raise_for_status()
    except requests.exceptions.RequestException as e:
        return f"An error occurred: {e}"

    final_url = str(resp.url)
    ctype = resp.headers.get("Content-Type", "")
    if "html" not in ctype.lower():
        return f"Unsupported content type for extraction: {ctype or 'unknown'}"

    # Decode to text
    resp.encoding = resp.encoding or resp.apparent_encoding
    html = resp.text

    # Full-page soup for metadata
    full_soup = BeautifulSoup(html, "lxml")
    meta = _extract_metadata(full_soup, final_url)

    # Readable content
    body_text, readable_soup = _extract_main_text(html)
    if not body_text:
        # Fallback to "whole-page text" if Readability found nothing
        fallback_text = full_soup.get_text(" ", strip=True)
        body_text = _normalize_whitespace(fallback_text)

    # Verbosity presets (we keep the smaller of preset vs. user cap)
    preset_caps = {"Brief": 1200, "Standard": 3000, "Full": 999_999}
    target_cap = preset_caps.get(verbosity, 3000)
    cap = min(max_chars if max_chars > 0 else target_cap, target_cap)
    body_text, truncated = _truncate(body_text, cap) if include_text else ("", False)

    # Extract links from the simplified content only
    links = _extract_links(readable_soup, final_url, max_links=max_links if include_links else 0)

    # Final compact Markdown
    md = _format_markdown(
        meta=meta,
        body=body_text,
        body_truncated=truncated,
        links=links,
        include_text=include_text,
        include_metadata=include_metadata,
        include_links=include_links,
        verbosity=verbosity,
    )
    return md or "No content could be extracted."


# ==========================
# Websearch: DuckDuckGo tool
# ==========================

def Search_Structured(  # <-- MCP tool #3 (Structured DDG)
    input_query: str,
    max_results: int = 5,
) -> List[Dict[Literal["snippet", "title", "link"], str]]:
    """
    Run a DuckDuckGo search and return structured results as a list of dictionaries.
    (Layman's terms: search DDG and get clean JSON objects.)
    """
    if not input_query or not input_query.strip():
        return []

    # Create the search tool (LangChain community wrapper)
    search = DuckDuckGoSearchResults(output_format="list", num_results=max_results)

    # Run the search and return results as a list of dicts
    results = search.invoke(input_query)
    return results


# ========================================
# Unstructured DDG: raw list into Textbox
# ========================================

def Search_Raw(  # <-- MCP tool #4 (Unstructured DDG)
    query: str,
) -> list[dict]:
    """
    Run a DuckDuckGo search using the native `duckduckgo_search` client and return the
    raw Python list of dictionaries from the library.
    (Layman's terms: search DDG and show exactly what the library returns.)
    """
    if not query or not query.strip():
        return []
    with DDGS() as ddgs:
        results = ddgs.text(query, max_results=5)
    return results


# ============================================
# Concise DDG: ultra-succinct JSONL for tokens
# ============================================

def Search_Concise(  # <-- MCP tool #2 (Concise DDG)
    query: str,
    max_results: int = 5,
    include_snippets: bool = False,
    max_snippet_chars: int = 80,
    dedupe_domains: bool = True,
    title_chars: int = 80,
) -> str:
    """
    Run a DuckDuckGo search and return ultra-compact JSONL lines with short keys to
    minimize tokens.

    (Layman's terms: the tiniest useful search output possible.)
    """
    if not query or not query.strip():
        return ""

    try:
        with DDGS() as ddgs:
            raw = ddgs.text(query, max_results=max_results)
    except Exception as e:
        return json.dumps({"error": str(e)[:120]}, ensure_ascii=False, separators=(",", ":"))

    seen_domains = set()
    lines: List[str] = []

    for r in raw or []:
        title = _shorten((r.get("title") or "").strip(), title_chars)
        url = (r.get("href") or r.get("link") or "").strip()
        body = (r.get("body") or r.get("snippet") or "").strip()

        if not url:
            continue

        if dedupe_domains:
            dom = _domain_of(url)
            if dom in seen_domains:
                continue
            seen_domains.add(dom)

        obj = {"t": title or _domain_of(url), "u": url}

        if include_snippets and body:
            obj["s"] = _shorten(body, max_snippet_chars)

        # Emit most compact JSON possible (no spaces)
        lines.append(json.dumps(obj, ensure_ascii=False, separators=(",", ":")))

    # Join as JSONL (each result on its own line)
    return "\n".join(lines)


# ============================================
# Generate Sitemap (new MCP tool #5)
# ============================================

def Generate_Sitemap(
    url: str,
    max_links_per_domain: int = 0,
) -> str:
    """
    Generate a grouped sitemap (Markdown) of anchor links on a page, with an optional
    per-domain cap.

    Args:
        url (str): The starting page URL (http/https). If the scheme is omitted,
            https is assumed.
        max_links_per_domain (int): Limit the number of links shown per domain.
            Use 0 to show all links.

    Returns:
        str: Markdown text containing grouped links under "Internal Links" and
        per-domain "External Links (domain)" sections. If an error occurs or no
        links are found, a short message is returned.
    """
    # --- Basic validation & normalization ---
    if not url or not url.strip():
        return "Please enter a valid URL."

    # If the user forgot the scheme, assume https
    if not url.lower().startswith(("http://", "https://")):
        url = "https://" + url.strip()

    # --- Fetch the page safely ---
    try:
        resp = _http_get(url)
        resp.raise_for_status()
    except requests.exceptions.RequestException as e:
        return f"Error fetching URL: {str(e)}"

    base_url = str(resp.url)  # follow redirects and use the final URL
    content_type = resp.headers.get("Content-Type", "")
    if "html" not in content_type.lower():
        return "The provided URL does not appear to be an HTML page."

    # --- Parse and collect links ---
    soup = BeautifulSoup(resp.content, "lxml")  # fast, lenient HTML parsing
    anchors = soup.find_all("a", href=True)

    seen_urls: set[str] = set()
    items: List[Dict[str, str]] = []

    for a in anchors:
        href = (a.get("href") or "").strip()
        if not href:
            continue

        # Skip non-navigational/unsupported schemes
        if href.startswith(("#", "javascript:", "mailto:", "tel:")):
            continue

        # Resolve relative links and strip fragments
        absolute = urljoin(base_url, href)
        absolute, _ = urldefrag(absolute)

        # Deduplicate and skip self
        if absolute in seen_urls or absolute == base_url:
            continue
        seen_urls.add(absolute)

        # Use link text if available; otherwise the URL itself
        text = (a.get_text(" ", strip=True) or href).strip()
        if len(text) > 100:
            text = text[:100] + "..."

        items.append({"text": text, "url": absolute})

    if not items:
        return "No links found on this page."

    # --- Group by Internal vs External domains ---
    base_netloc = urlparse(base_url).netloc
    domain_groups: Dict[str, List[Dict[str, str]]] = {}

    for it in items:
        netloc = urlparse(it["url"]).netloc
        key = "Internal Links" if netloc == base_netloc else f"External Links ({netloc})"
        domain_groups.setdefault(key, []).append(it)

    # --- Build Markdown with optional per-domain limit ---
    total_links = len(items)
    md_lines: List[str] = []
    md_lines.append("# Sitemap")
    md_lines.append(f"Base URL: {base_url}")
    md_lines.append(f"Found {total_links} links:\n")

    # Show Internal first, then external groups sorted by name
    keys_sorted = ["Internal Links"] + sorted([k for k in domain_groups if k != "Internal Links"])

    for group_key in keys_sorted:
        if group_key not in domain_groups:
            continue

        group_links = domain_groups[group_key]
        md_lines.append(f"## {group_key}\n")

        if max_links_per_domain and max_links_per_domain > 0:
            links_to_show = group_links[:max_links_per_domain]
            remaining = max(0, len(group_links) - max_links_per_domain)
        else:
            links_to_show = group_links
            remaining = 0

        for link in links_to_show:
            md_lines.append(f"- [{link['text']}]({link['url']})")

        if remaining > 0:
            md_lines.append(f"- ... and {remaining} more links")

        md_lines.append("")  # blank line after each group

    sitemap_md = "\n".join(md_lines).strip()
    return sitemap_md


# ======================
# UI: five-tab interface
# ======================

# --- Fetch tab (compact controllable extraction) ---
fetch_interface = gr.Interface(
    fn=Fetch_Webpage,  # connect the function to the UI
    inputs=[
        gr.Textbox(label="URL", placeholder="https://example.com/article"),
        gr.Dropdown(label="Verbosity", choices=["Brief", "Standard", "Full"], value="Standard"),
        gr.Checkbox(value=True, label="Include Metadata"),
        gr.Checkbox(value=True, label="Include Main Text"),
        gr.Checkbox(value=True, label="Include Links"),
        gr.Slider(400, 12000, value=3000, step=100, label="Max Characters (body text)"),
        gr.Slider(0, 100, value=20, step=1, label="Max Links"),
    ],
    outputs=gr.Markdown(label="Extracted Summary"),
    title="Fetch Webpage",
    description="Extract title, key metadata, readable text, and links. No noisy HTML.",
    api_description=(
        "Fetch a web page and return a compact Markdown summary with title, key "
        "metadata, readable body text, and outbound links. Parameters let you "
        "control verbosity, whether to include metadata/text/links, and limits "
        "for characters and number of links."
    ),
    allow_flagging="never",
    theme="Nymbo/Nymbo_Theme",
)

# --- Concise DDG tab (JSONL with short keys, minimal tokens) ---
concise_interface = gr.Interface(
    fn=Search_Concise,
    inputs=[
        gr.Textbox(label="Query", placeholder="topic OR site:example.com"),
        gr.Slider(minimum=1, maximum=20, value=5, step=1, label="Max results"),
        gr.Checkbox(value=False, label="Include snippets (adds tokens)"),
        gr.Slider(minimum=20, maximum=200, value=80, step=5, label="Max snippet chars"),
        gr.Checkbox(value=True, label="Dedupe by domain"),
        gr.Slider(minimum=20, maximum=120, value=80, step=5, label="Max title chars"),
    ],
    outputs=gr.Textbox(label="Results (JSONL)", interactive=False),
    title="DuckDuckGo Search (Concise)",
    description="Emits JSONL with short keys (t,u[,s]). Defaults avoid snippets and duplicate domains.",
    api_description=(
        "Run a DuckDuckGo search and return newline-delimited JSON with short keys: "
        "t=title, u=url, optional s=snippet. Options control result count, "
        "snippet inclusion and length, domain deduping, and title length."
    ),
    allow_flagging="never",
    theme="Nymbo/Nymbo_Theme",
    submit_btn="Search",
)

# --- Websearch tab (structured DDG via LangChain) ---
websearch_interface = gr.Interface(
    fn=Search_Structured,  # connect the function to the UI
    inputs=[
        gr.Textbox(value="", label="Search query", placeholder="site:example.com interesting topic"),
        gr.Slider(minimum=1, maximum=20, value=5, step=1, label="Max results"),
    ],
    outputs=gr.JSON(label="Search results"),
    title="DuckDuckGo Search (Structured)",
    description="Search the web using DuckDuckGo; returns snippet, title, and link.",
    api_description=(
        "Run a DuckDuckGo web search and return a list of objects with keys: "
        "snippet, title, and link. Configure the number of results."
    ),
    allow_flagging="never",
    theme="Nymbo/Nymbo_Theme",
)

# --- Unstructured DDG tab (matches your separate app’s output) ---
unstructured_interface = gr.Interface(
    fn=Search_Raw,
    inputs=gr.Textbox(label="Enter Search Query"),
    outputs=gr.Textbox(label="Results", interactive=False),
    title="DuckDuckGo Search (Raw)",
    description="Returns the raw list of results (list[dict]) shown as text.",
    api_description=(
        "Run DuckDuckGo via the native client and return the raw list[dict] as "
        "provided by duckduckgo_search (fields like title, href/link, body/snippet)."
    ),
    allow_flagging="never",
    theme="Nymbo/Nymbo_Theme",
    submit_btn="Search",
)

# --- Generate Sitemap tab (LIMITED, grouped + optional per-domain cap) ---
sitemap_interface = gr.Interface(
    fn=Generate_Sitemap,
    inputs=[
        gr.Textbox(
            label="Website URL",
            placeholder="https://example.com or example.com"
        ),
        gr.Slider(
            minimum=0,
            maximum=1000,
            value=0,
            step=1,
            label="Max links per domain (0 = show all)"
        ),
    ],
    outputs=gr.Markdown(label="Sitemap (Markdown)"),
    title="Generate Sitemap",
    description="Group links by Internal/External domains; optionally limit links per domain.",
    api_description=(
        "Scan a page and build a grouped sitemap of anchor links. Links are grouped as "
        "Internal or External (per domain). Set a per-domain cap; 0 shows all."
    ),
    allow_flagging="never",
    theme="Nymbo/Nymbo_Theme",
    submit_btn="Generate",
)

# --- Combine all into a single app with tabs ---
demo = gr.TabbedInterface(
    interface_list=[fetch_interface, concise_interface, websearch_interface, unstructured_interface, sitemap_interface],
    tab_names=[
        "Fetch Webpage",
        "DuckDuckGo Search (Concise)",
        "DuckDuckGo Search (Structured)",
        "DuckDuckGo Search (Raw)",
        "Generate Sitemap",
    ],
    title="Web MCP — Fetch, Search, and Sitemaps with customizable output modes.",
    theme="Nymbo/Nymbo_Theme",
)

# Launch the UI and expose all functions as MCP tools in one server
if __name__ == "__main__":
    demo.launch(mcp_server=True)