Spaces:

victor
/

dom-to-semantic-markdown

Running

App Files Files Community

victor HF staff commited on Jul 24

Commit

26240b0

•

0 Parent(s):

yo

Browse files

Files changed (7) hide show

.gitattributes +35 -0
Dockerfile +20 -0
README.md +10 -0
index.html +36 -0
package.json +21 -0
script.js +42 -0
server.js +32 -0

.gitattributes ADDED Viewed

	@@ -0,0 +1,35 @@

+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

Dockerfile ADDED Viewed

	@@ -0,0 +1,20 @@

+# Use an official Node.js runtime as the base image
+FROM node:14
+# Set the working directory in the container
+WORKDIR /usr/src/app
+# Copy package.json and package-lock.json to the working directory
+COPY package*.json ./
+# Install the application dependencies
+RUN npm install
+# Copy the rest of the application code to the working directory
+COPY . .
+# Expose the port that the app runs on
+EXPOSE 3000
+# Define the command to run the application
+CMD ["node", "server.js"]

README.md ADDED Viewed

	@@ -0,0 +1,10 @@

+---
+title: Dom To Semantic Markdown
+emoji: 📚
+colorFrom: gray
+colorTo: blue
+sdk: docker
+pinned: false
+---
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

index.html ADDED Viewed

	@@ -0,0 +1,36 @@

+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>DOM to Semantic Markdown Converter</title>
+    <script src="https://cdn.tailwindcss.com"></script>
+</head>
+<body>
+    <div class="w-dvh grid h-dvh grid-rows-[50px,1fr] overflow-hidden">
+        <div class="flex p-2 items-center gap-5 whitespace-nowrap">
+            <input type="url" id="url-input" placeholder="Enter URL" class="bg-gray-100 h-8 w-96 rounded-lg px-2" required>
+            <label>
+                <input type="checkbox" id="extract-main-content"> Extract main content
+            </label>
+            <label>
+                <input type="checkbox" id="refify-urls"> Refify URLs
+            </label>
+            <label>
+                <input type="checkbox" id="enable-table-column-tracking"> Enable table column tracking
+            </label>
+            <button type="submit" class="bg-black px-4 text-white h-8" form="converter-form">Convert to semantic markdown</button>
+        </div>
+        <div class="bg-gray-100 p-4 overflow-auto text-sm">
+            <pre id="markdown-output" class="whitespace-pre-wrap"></pre>
+        </div>
+    </div>
+    <form id="converter-form" class="hidden">
+        <input type="text" id="website-domain" placeholder="Website domain">
+    </form>
+    <script src="node_modules/dom-to-semantic-markdown/dist/browser/bundle.js"></script>
+    <script type="module" src="script.js"></script>
+</body>
+</html>

package.json ADDED Viewed

	@@ -0,0 +1,21 @@

+{
+  "name": "dom-to-semantic-markdown",
+  "version": "1.0.0",
+  "description": "--- title: Dom To Semantic Markdown emoji: 📚 colorFrom: gray colorTo: blue sdk: docker pinned: false ---",
+  "main": "server.js",
+  "scripts": {
+    "start": "node server.js",
+    "dev": "nodemon server.js",
+    "test": "echo \"Error: no test specified\" && exit 1"
+  },
+  "author": "",
+  "license": "ISC",
+  "dependencies": {
+    "dom-to-semantic-markdown": "^1.0.11",
+    "express": "^4.19.2",
+    "axios": "^0.21.1"
+  },
+  "devDependencies": {
+    "nodemon": "^2.0.22"
+  }
+}

script.js ADDED Viewed

	@@ -0,0 +1,42 @@

+const { convertHtmlToMarkdown } = htmlToSMD;
+document
+  .getElementById("converter-form")
+  .addEventListener("submit", async function (e) {
+    e.preventDefault();
+    const urlInput = document.getElementById("url-input").value;
+    const markdownOutput = document.getElementById("markdown-output");
+    const extractMainContent = document.getElementById(
+      "extract-main-content"
+    ).checked;
+    const refifyUrls = document.getElementById("refify-urls").checked;
+    const enableTableColumnTracking = document.getElementById(
+      "enable-table-column-tracking"
+    ).checked;
+    const websiteDomain = document.getElementById("website-domain").value;
+    const options = {
+      extractMainContent,
+      refifyUrls,
+      enableTableColumnTracking,
+      websiteDomain: websiteDomain || undefined,
+    };
+    try {
+      // Fetch HTML content from the server
+      const response = await fetch(
+        `/fetch-html?url=${encodeURIComponent(urlInput)}`
+      );
+      if (!response.ok) {
+        throw new Error("Failed to fetch HTML content");
+      }
+      const htmlContent = await response.text();
+      // Convert HTML to Markdown
+      const markdown = await convertHtmlToMarkdown(htmlContent, options);
+      markdownOutput.textContent = markdown;
+    } catch (error) {
+      markdownOutput.textContent = "Error: " + error.message;
+    }
+  });

server.js ADDED Viewed

	@@ -0,0 +1,32 @@

+const express = require("express");
+const path = require("path");
+const axios = require("axios");
+const app = express();
+const port = process.env.PORT || 3000;
+// Serve static files from the current directory
+app.use(express.static(__dirname));
+// Route to fetch HTML content from a given URL
+app.get("/fetch-html", async (req, res) => {
+  const url = req.query.url;
+  if (!url) {
+    return res.status(400).json({ error: "URL parameter is required" });
+  }
+  try {
+    const response = await axios.get(url);
+    res.send(response.data);
+  } catch (error) {
+    res.status(500).json({ error: "Failed to fetch HTML content" });
+  }
+});
+// Send index.html for any other routes
+app.get("*", (req, res) => {
+  res.sendFile(path.resolve(__dirname, "index.html"));
+});
+app.listen(port, () => {
+  console.log(`Server is running on port ${port}`);
+});