Add hosted Defuddle URL conversion to the app

README.md

@@ -9,8 +9,9 @@ It focuses on fast multi-file conversion to Markdown with a modern Fluent-style
 
 ## Features
 
-- Queue-based file workflow with drag and drop.
-- Batch conversion with start, pause/resume, cancel, and progress feedback.
+- Queue-based file workflow with drag and drop.
+- Paste website URLs and convert article content to Markdown with the hosted Defuddle API.
+- Batch conversion with start, pause/resume, cancel, and progress feedback.
 - Results view with per-file selection and Markdown preview.
 - Preview modes: rendered Markdown view and raw Markdown view.
 - Save modes: export as one combined file or separate files.
@@ -23,10 +24,10 @@ It focuses on fast multi-file conversion to Markdown with a modern Fluent-style
 
 Download prebuilt binaries from [Releases](https://github.com/imadreamerboy/markitdown-gui/releases), or run from source.
 
-### Prerequisites
-
-- Python `3.10+`
-- `uv` (recommended)
+### Prerequisites
+
+- Python `3.10+`
+- `uv` (recommended)
 
 Install dependencies:
 
@@ -40,14 +41,23 @@ Alternative:
 pip install -e .[dev]
 ```
 
-### OCR Notes
+### OCR Notes
 
 - OCR is optional and disabled by default.
 - Local OCR requires a system `tesseract` binary. Install it from the [official Tesseract project](https://github.com/tesseract-ocr/tesseract). If it is not on your `PATH`, set the executable path in Settings.
 - Azure OCR requires an Azure Document Intelligence endpoint in Settings.
 - Azure Document Intelligence pricing includes [500 free pages per month](https://azure.microsoft.com/en-us/products/ai-foundry/tools/document-intelligence#Pricing) at the time of writing.
 - For API-key auth, set `AZURE_OCR_API_KEY`.
-- If `AZURE_OCR_API_KEY` is not set, Azure OCR falls back to Azure identity credentials supported by `DefaultAzureCredential`.
+- If `AZURE_OCR_API_KEY` is not set, Azure OCR falls back to Azure identity credentials supported by `DefaultAzureCredential`.
+
+### Website URL Notes
+
+- Website conversion uses the hosted [Defuddle](https://defuddle.md/) API.
+- The app sends the pasted `http://` or `https://` URL to `https://defuddle.md/<url>` and stores the returned Markdown in the normal results view.
+- Defuddle responses typically include YAML frontmatter metadata at the top when available.
+- According to the [Defuddle Terms](https://defuddle.md/terms), unauthenticated requests are limited to `1,000` requests per month per IP address as of March 14, 2026.
+- Because requests are sent directly from the desktop app, that free-tier limit applies to the user's own network IP.
+- Website conversion requires an internet connection and depends on the external Defuddle service being available.
 
 ## Run the App
 

markitdowngui/core/conversion.py

@@ -1,22 +1,30 @@
 from __future__ import annotations
 
-from dataclasses import dataclass
-from itertools import islice
-import os
-from pathlib import Path
-
-from PySide6.QtCore import QThread, Signal
-
-IMAGE_EXTENSIONS = {".bmp", ".gif", ".jpeg", ".jpg", ".png", ".tiff", ".webp"}
-DOCINTEL_IMAGE_EXTENSIONS = {".bmp", ".jpeg", ".jpg", ".png", ".tiff"}
-PDF_EXTENSION = ".pdf"
-PDF_RENDER_SCALE = 3.0
-LOCAL_OCR_TIMEOUT_SECONDS = 60
-AZURE_OCR_API_KEY_ENV_VAR = "AZURE_OCR_API_KEY"
-CONVERSION_ERROR_PREFIX = "Error converting "
-BACKEND_AZURE = "azure"
-BACKEND_LOCAL = "local"
-BACKEND_NATIVE = "native"
+from dataclasses import dataclass
+from itertools import islice
+import os
+from pathlib import Path
+from urllib.parse import quote
+
+import requests
+
+from PySide6.QtCore import QThread, Signal
+
+from markitdowngui.core.input_sources import is_web_url
+
+IMAGE_EXTENSIONS = {".bmp", ".gif", ".jpeg", ".jpg", ".png", ".tiff", ".webp"}
+DOCINTEL_IMAGE_EXTENSIONS = {".bmp", ".jpeg", ".jpg", ".png", ".tiff"}
+PDF_EXTENSION = ".pdf"
+PDF_RENDER_SCALE = 3.0
+LOCAL_OCR_TIMEOUT_SECONDS = 60
+DEFUDDLE_REQUEST_TIMEOUT_SECONDS = 30
+DEFUDDLE_API_BASE_URL = "https://defuddle.md/"
+AZURE_OCR_API_KEY_ENV_VAR = "AZURE_OCR_API_KEY"
+CONVERSION_ERROR_PREFIX = "Error converting "
+BACKEND_AZURE = "azure"
+BACKEND_DEFUDDLE = "defuddle"
+BACKEND_LOCAL = "local"
+BACKEND_NATIVE = "native"
 
 
 @dataclass(frozen=True)
@@ -144,13 +152,20 @@ def test_azure_ocr_connection(options: ConversionOptions) -> str:
     return "api_key"
 
 
-def convert_file_with_details(
-    file_path: str,
-    options: ConversionOptions | None = None,
-) -> ConversionOutcome:
-    """Convert a single file to Markdown text and report which backend produced it."""
-    effective_options = options or ConversionOptions()
-    extension = Path(file_path).suffix.lower()
+def convert_file_with_details(
+    file_path: str,
+    options: ConversionOptions | None = None,
+) -> ConversionOutcome:
+    """Convert a single file to Markdown text and report which backend produced it."""
+    effective_options = options or ConversionOptions()
+
+    if is_web_url(file_path):
+        return ConversionOutcome(
+            markdown=_convert_url_with_defuddle(file_path),
+            backend=BACKEND_DEFUDDLE,
+        )
+
+    extension = Path(file_path).suffix.lower()
 
     if not effective_options.ocr_enabled:
         return ConversionOutcome(
@@ -259,10 +274,10 @@ def _convert_pdf_with_ocr_fallback(
     )
 
 
-def _convert_with_markitdown(
-    file_path: str,
-    options: ConversionOptions,
-    *,
+def _convert_with_markitdown(
+    file_path: str,
+    options: ConversionOptions,
+    *,
     use_docintel: bool = False,
 ) -> str:
     # Delay heavy imports until conversion is requested.
@@ -274,8 +289,42 @@ def _convert_with_markitdown(
         kwargs["docintel_credential"], _auth_method = _build_docintel_credential()
 
     md = MarkItDown(**kwargs)
-    result = md.convert(file_path)
-    return result.text_content or ""
+    result = md.convert(file_path)
+    return result.text_content or ""
+
+
+def _convert_url_with_defuddle(url: str) -> str:
+    request_url = _build_defuddle_request_url(url)
+
+    try:
+        response = requests.get(
+            request_url,
+            timeout=DEFUDDLE_REQUEST_TIMEOUT_SECONDS,
+        )
+    except requests.Timeout as exc:
+        raise RuntimeError(
+            "Website conversion timed out while waiting for the Defuddle service."
+        ) from exc
+    except requests.RequestException as exc:
+        raise RuntimeError(
+            f"Website conversion failed to reach the Defuddle service: {exc}"
+        ) from exc
+
+    if response.status_code == 429:
+        raise RuntimeError(
+            "Defuddle rate limit reached. The free tier allows up to 1,000 requests per month per IP."
+        )
+
+    if not response.ok:
+        message = response.text.strip()
+        raise RuntimeError(message or "Defuddle failed to convert the URL.")
+
+    return response.text.strip()
+
+
+def _build_defuddle_request_url(url: str) -> str:
+    encoded_url = quote(url.strip(), safe="")
+    return f"{DEFUDDLE_API_BASE_URL}{encoded_url}"
 
 
 def _convert_image_with_local_ocr(file_path: str, options: ConversionOptions) -> str:

markitdowngui/core/input_sources.py

@@ -0,0 +1,50 @@
+from __future__ import annotations
+
+import re
+from pathlib import Path, PureWindowsPath
+from urllib.parse import unquote, urlparse
+
+WEB_URL_SCHEMES = {"http", "https"}
+UNSAFE_FILENAME_CHARS = re.compile(r"[^A-Za-z0-9._-]+")
+
+
+def is_web_url(value: str) -> bool:
+    candidate = value.strip()
+    if not candidate:
+        return False
+    if any(ch.isspace() or ord(ch) < 32 for ch in candidate):
+        return False
+
+    parsed = urlparse(candidate)
+    return parsed.scheme.lower() in WEB_URL_SCHEMES and bool(parsed.netloc)
+
+
+def _source_path(source: str) -> Path | PureWindowsPath:
+    candidate = source.strip()
+    if "\\" in candidate:
+        return PureWindowsPath(candidate)
+    return Path(candidate)
+
+
+def source_display_name(source: str) -> str:
+    return source.strip() if is_web_url(source) else _source_path(source).name or source
+
+
+def source_output_stem(source: str) -> str:
+    if not is_web_url(source):
+        return _source_path(source).stem or "converted"
+
+    parsed = urlparse(source.strip())
+    path_parts = [part for part in parsed.path.split("/") if part]
+    slug = unquote(path_parts[-1]) if path_parts else ""
+    query = parsed.query.split("&", 1)[0] if parsed.query else ""
+
+    segments = [parsed.netloc]
+    if slug:
+        segments.append(slug)
+    elif query:
+        segments.append(query)
+
+    candidate = "-".join(segments)
+    sanitized = UNSAFE_FILENAME_CHARS.sub("-", candidate).strip("._-")
+    return sanitized or "website"

markitdowngui/ui/components/url_input_bar.py

@@ -0,0 +1,41 @@
+from __future__ import annotations
+
+from PySide6.QtCore import Signal
+from PySide6.QtWidgets import QHBoxLayout, QWidget
+from qfluentwidgets import LineEdit, PushButton
+
+
+class UrlInputBar(QWidget):
+    url_submitted = Signal(str)
+
+    def __init__(self, translate, parent=None):
+        super().__init__(parent=parent)
+        self.translate = translate
+
+        layout = QHBoxLayout(self)
+        layout.setContentsMargins(0, 0, 0, 0)
+        layout.setSpacing(8)
+
+        self.url_edit = LineEdit(self)
+        self.url_edit.returnPressed.connect(self.submit_url)
+
+        self.submit_button = PushButton(self)
+        self.submit_button.clicked.connect(self.submit_url)
+
+        layout.addWidget(self.url_edit, 1)
+        layout.addWidget(self.submit_button)
+
+        self.retranslate_ui(translate)
+
+    def submit_url(self) -> None:
+        value = self.url_edit.text().strip()
+        if value:
+            self.url_submitted.emit(value)
+
+    def clear(self) -> None:
+        self.url_edit.clear()
+
+    def retranslate_ui(self, translate) -> None:
+        self.translate = translate
+        self.url_edit.setPlaceholderText(self.translate("home_url_placeholder"))
+        self.submit_button.setText(self.translate("home_add_url_button"))

markitdowngui/ui/help_interface.py

@@ -76,13 +76,19 @@ def _build_ui(self) -> None:
 
         repo_btn = HyperlinkButton()
         repo_btn.setText(self.translate("help_open_repository"))
-        repo_btn.setIcon(FIF.GITHUB)
-        repo_btn.setUrl(QUrl("https://github.com/imadreamerboy/markitdown-gui"))
-        layout.addWidget(repo_btn, 0, Qt.AlignmentFlag.AlignLeft)
-
-        azure_pricing_btn = HyperlinkButton()
-        azure_pricing_btn.setText(self.translate("help_open_azure_ocr_pricing"))
-        azure_pricing_btn.setIcon(FIF.LINK)
+        repo_btn.setIcon(FIF.GITHUB)
+        repo_btn.setUrl(QUrl("https://github.com/imadreamerboy/markitdown-gui"))
+        layout.addWidget(repo_btn, 0, Qt.AlignmentFlag.AlignLeft)
+
+        defuddle_docs_btn = HyperlinkButton()
+        defuddle_docs_btn.setText(self.translate("help_open_defuddle_docs"))
+        defuddle_docs_btn.setIcon(FIF.LINK)
+        defuddle_docs_btn.setUrl(QUrl("https://defuddle.md/docs"))
+        layout.addWidget(defuddle_docs_btn, 0, Qt.AlignmentFlag.AlignLeft)
+
+        azure_pricing_btn = HyperlinkButton()
+        azure_pricing_btn.setText(self.translate("help_open_azure_ocr_pricing"))
+        azure_pricing_btn.setIcon(FIF.LINK)
         azure_pricing_btn.setUrl(
             QUrl(
                 "https://azure.microsoft.com/en-us/products/ai-foundry/tools/document-intelligence#Pricing"
@@ -96,8 +102,22 @@ def _build_ui(self) -> None:
         tesseract_btn.setUrl(QUrl("https://github.com/tesseract-ocr/tesseract"))
         layout.addWidget(tesseract_btn, 0, Qt.AlignmentFlag.AlignLeft)
 
-        layout.addWidget(TitleLabel(self.translate("help_faq_title")))
-
+        layout.addWidget(TitleLabel(self.translate("help_faq_title")))
+
+        layout.addWidget(
+            self._build_faq_card(
+                FIF.GLOBE,
+                "help_faq_defuddle_question",
+                "help_faq_defuddle_answer",
+            )
+        )
+        layout.addWidget(
+            self._build_faq_card(
+                FIF.GLOBE,
+                "help_faq_defuddle_limits_question",
+                "help_faq_defuddle_limits_answer",
+            )
+        )
         layout.addWidget(
             self._build_faq_card(
                 FIF.FOLDER,