Spaces:

rrg92
/

hf-community-highlights-parser

Running

App Files Files Community

rrg92 commited on Jul 4

Commit

2ede869

•

1 Parent(s): 3ae9e56

Add some description

Browse files

Files changed (1) hide show

index.html +230 -219

index.html CHANGED Viewed

@@ -1,220 +1,231 @@
-<html>
-	<head>
-		<script type="text/javascript">
-			let CURRENT_CONTENT;
-			let parser = new DOMParser()
-			function FormatDiscordMessage(html){
-				let dom = parser.parseFromString(html, "text/html");
-				CURRENT_CONTENT.dom = dom;
-				let allChilds = dom.querySelectorAll("body > *");
-				let FullContent = [];
-				let buffContent = []
-				let buffLinks = []
-				let authorName= [];
-				let edition;
-				let flushContent = function(){
-					console.log("line break found!");
-					let AllText = buffContent.join("").trim();
-					let links = buffLinks.join(",");
-					if(!links)
-						return;
-					FullContent.push({
-						 text: AllText
-						,links
-						,authors: authorName.join(",")
-						,edition
-					});
-					buffContent = []
-					buffLinks = [];
-					authorName = []
-				}
-				for(let c of allChilds){
-					let text;
-					if(c.tagName == "A")
-						buffLinks.push(c.href);
-					if(c.tagName.at(0) == 'H'){
-						let editionMatch = c.textContent.match(/#\d+/g);
-						if(editionMatch){
-							edition = parseInt( editionMatch[0].replace('#',''))
-						}
-						continue;
-					}
-					if(c.classList.contains("mention"))
-						authorName.push(c.textContent);
-					text = c.textContent;
-					if(text)
-						buffContent.push(text);
-					if(/\!?\s*\n+/.test(text)){
-						flushContent();
-					}
-				}
-				// last
-				if(buffContent){
-					flushContent();
-				}
-				return { dom, content: FullContent };
-			}
-			function ProcessPastedMessage(){
-				let res = FormatDiscordMessage(CURRENT_CONTENT.html)
-				CURRENT_CONTENT.result = res;
-				let out = document.querySelector("#result");
-				let xDoc = document.implementation.createDocument(null, "highlights");
-				let rootDoc = xDoc.querySelector("highlights");
-				let Stats = {
-					total: 0
-					,edition: null
-				};
-				Stats.edition = res.content[0].edition;
-				for(let [i,high] of res.content.entries()){
-					let xHigh = xDoc.createElement("highlight");
-					let xAutor 		= xDoc.createElement("author");
-					let xLinks 		= xDoc.createElement("links");
-					let xEdition 	= xDoc.createElement("edition");
-					let xText 		= xDoc.createElement("text");
-					xAutor.textContent 		= high.authors
-					xLinks.textContent 		= high.links
-					xEdition.textContent 	= high.edition
-					xText.textContent 		= high.text
-					xHigh.appendChild(xText);
-					xHigh.appendChild(xLinks);
-					xHigh.appendChild(xEdition);
-					xHigh.appendChild(xAutor);
-					rootDoc.appendChild(xHigh)
-					Stats.total++
-				}
-				document.querySelector("#stats").innerHTML = `Stats: total = ${Stats.total}, edition = ${Stats.edition}`
-				let serializer = new XMLSerializer();
-				out.innerHTML = serializer.serializeToString(xDoc);
-			}
-			function ProcessPasted(content){
-				navigator.clipboard.read(["text/html"])
-					.then( async (content) => {
-						console.log("content", content[0].types)
-						let contentTypes = content[0].types;
-						let plainText = await (await content[0].getType("text/plain")).text();
-						let html = null;
-						if(contentTypes.includes("text/html")){
-							htmlContent = await content[0].getType("text/html");
-							console.log("html:", htmlContent);
-							html = await htmlContent.text();
-							CURRENT_CONTENT = {
-								html:  await htmlContent.text()
-								,text: plainText
-							}
-						} else {
-							console.log("NotContainsHtml");
-						}
-						CURRENT_CONTENT = {
-							html
-							,text: plainText
-						}
-						setTimeout(ProcessPastedMessage, 100)
-					})
-				return false;
-			}
-			addEventListener("paste", ProcessPasted);
-		</script>
-		<style>
-			textarea {
-				width: 100%;
-			}
-			.container {
-				display: flex;
-				flex-direction: row;
-			}
-			.container > div {
-				width: 50%;
-				height: 70vh;
-				padding: 5px;
-			}
-			.container textarea {
-				height: 100%;
-			}
-		</style>
-	</head>
-	<body>
-		<div>
-			<p id="stats"></p>
-		</div>
-		<div class="container">
-			<div>
-				<p>Content</p>
-				<textarea></textarea>
-			</div>
-			<div>
-				<p>XML</p>
-				<textarea readonly id="result"></textarea>
-			</div>
-		</div>
-	</body>
 </html>

+<html>
+	<head>
+		<script type="text/javascript">
+			let CURRENT_CONTENT;
+			let parser = new DOMParser()
+			function FormatDiscordMessage(html){
+				let dom = parser.parseFromString(html, "text/html");
+				CURRENT_CONTENT.dom = dom;
+				let allChilds = dom.querySelectorAll("body > *");
+				let FullContent = [];
+				let buffContent = []
+				let buffLinks = []
+				let authorName= [];
+				let edition;
+				let flushContent = function(){
+					console.log("line break found!");
+					let AllText = buffContent.join("").trim();
+					let links = buffLinks.join(",");
+					if(!links)
+						return;
+					FullContent.push({
+						 text: AllText
+						,links
+						,authors: authorName.join(",")
+						,edition
+					});
+					buffContent = []
+					buffLinks = [];
+					authorName = []
+				}
+				for(let c of allChilds){
+					let text;
+					if(c.tagName == "A")
+						buffLinks.push(c.href);
+					if(c.tagName.at(0) == 'H'){
+						let editionMatch = c.textContent.match(/#\d+/g);
+						if(editionMatch){
+							edition = parseInt( editionMatch[0].replace('#',''))
+						}
+						continue;
+					}
+					if(c.classList.contains("mention"))
+						authorName.push(c.textContent);
+					text = c.textContent;
+					if(text)
+						buffContent.push(text);
+					if(/\!?\s*\n+/.test(text)){
+						flushContent();
+					}
+				}
+				// last
+				if(buffContent){
+					flushContent();
+				}
+				return { dom, content: FullContent };
+			}
+			function ProcessPastedMessage(){
+				let res = FormatDiscordMessage(CURRENT_CONTENT.html)
+				CURRENT_CONTENT.result = res;
+				let out = document.querySelector("#result");
+				let xDoc = document.implementation.createDocument(null, "highlights");
+				let rootDoc = xDoc.querySelector("highlights");
+				let Stats = {
+					total: 0
+					,edition: null
+				};
+				Stats.edition = res.content[0].edition;
+				for(let [i,high] of res.content.entries()){
+					let xHigh = xDoc.createElement("highlight");
+					let xAutor 		= xDoc.createElement("author");
+					let xLinks 		= xDoc.createElement("links");
+					let xEdition 	= xDoc.createElement("edition");
+					let xText 		= xDoc.createElement("text");
+					xAutor.textContent 		= high.authors
+					xLinks.textContent 		= high.links
+					xEdition.textContent 	= high.edition
+					xText.textContent 		= high.text
+					xHigh.appendChild(xText);
+					xHigh.appendChild(xLinks);
+					xHigh.appendChild(xEdition);
+					xHigh.appendChild(xAutor);
+					rootDoc.appendChild(xHigh)
+					Stats.total++
+				}
+				document.querySelector("#stats").innerHTML = `Stats: total = ${Stats.total}, edition = ${Stats.edition}`
+				let serializer = new XMLSerializer();
+				out.innerHTML = serializer.serializeToString(xDoc);
+			}
+			function ProcessPasted(content){
+				navigator.clipboard.read(["text/html"])
+					.then( async (content) => {
+						console.log("content", content[0].types)
+						let contentTypes = content[0].types;
+						let plainText = await (await content[0].getType("text/plain")).text();
+						let html = null;
+						if(contentTypes.includes("text/html")){
+							htmlContent = await content[0].getType("text/html");
+							console.log("html:", htmlContent);
+							html = await htmlContent.text();
+							CURRENT_CONTENT = {
+								html:  await htmlContent.text()
+								,text: plainText
+							}
+						} else {
+							console.log("NotContainsHtml");
+						}
+						CURRENT_CONTENT = {
+							html
+							,text: plainText
+						}
+						setTimeout(ProcessPastedMessage, 100)
+					})
+				return false;
+			}
+			addEventListener("paste", ProcessPasted);
+		</script>
+		<style>
+			textarea {
+				width: 100%;
+			}
+			.container {
+				display: flex;
+				flex-direction: row;
+			}
+			.container > div {
+				width: 50%;
+				height: 70vh;
+				padding: 5px;
+			}
+			.container textarea {
+				height: 100%;
+			}
+		</style>
+	</head>
+	<body>
+        <p>This is a simple parser of Community Highlights, posted weekly in Huging Face Discord</p>
+        <p>Community Highlights is a valuable information. While Hugging Face dont provide an official list (via some API), use that tool to parse and import anywhere</p>
+        <p>Use it to transform content into something best to be parsed (for example, to import in some database, or blog)</p>
+        <p>Instrunctions></p>
+        <ol>
+          <li>Open Discord in some Broswer (just opening in browser works)</li>
+          <li>Go to desired Community Highlights message. Select all message and Copy</li>
+          <li>Paste on Content Field</li>
+          <li>Then, a parsed data must be generate in side input, in XML format. That format is better to you import anyhwere</li>
+        </ol>
+        <p>TODO: JSON Support, API import</p>
+		<div>
+			<p id="stats"></p>
+		</div>
+		<div class="container">
+			<div>
+				<p>Content</p>
+				<textarea></textarea>
+			</div>
+			<div>
+				<p>XML</p>
+				<textarea readonly id="result"></textarea>
+			</div>
+		</div>
+	</body>
 </html>