unprint 0.9.5 → 0.10.0

package/README.md

@@ -85,6 +85,16 @@ Return the contents of the element or attribute as a Number primitive.
 
 Return the HTML contents of an element (`.innerHTML`).
 
+#### Query the text
+`query.text([selector], [options])`
+
+Return the text contents of an element, skipping non-text children, as opposed to querying content.
+
+Options
+* `join`: Join text nodes into one string
+* `trim`: Remove excess whitespace
+* `filter`: Remove empty text nodes
+
 #### Query a URL
 `query.url([selector], [options])`
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "unprint",
-  "version": "0.9.5",
+  "version": "0.10.0",
   "description": "Simplify common web scraping tasks while staying in control of the data.",
   "main": "src/app.js",
   "scripts": {

package/src/app.js

@@ -193,11 +193,11 @@ const defaultNumberRegexp = /\d+(\.\d+)?/;
 
 function matchNumberString(numberString, options) {
 	if (numberString && options.match) {
-		return Number(numberString.match(options.match)?.[options.matchIndex]);
+		return Number(numberString.match(options.match)?.[options.matchIndex]) || null;
 	}
 
 	if (numberString) {
-		return Number(numberString);
+		return Number(numberString) || null;
 	}
 
 	return null;
@@ -249,6 +249,51 @@ function queryHtmls(context, selector, customOptions) {
 	return targets.map((target) => trim(target.innerHTML));
 }
 
+function extractText(target, customOptions) {
+	const options = {
+		filter: true,
+		trim: true,
+		join: true,
+		...customOptions,
+	};
+
+	const nodes = Array.from(target.childNodes)
+		.filter((node) => node.nodeName === '#text')
+		.map((node) => (options.trim ? trim(node.textContent) : node.textContent));
+
+	const filteredNodes = options.filter
+		? nodes.filter(Boolean)
+		: nodes;
+
+	if (options.join) {
+		const text = filteredNodes.join(typeof options.join === 'string' ? options.join : ' ');
+
+		if (options.trim) {
+			return text.trim();
+		}
+
+		return text;
+	}
+
+	return filteredNodes;
+}
+
+function queryText(context, selector, customOptions) {
+	const target = queryElement(context, selector, customOptions);
+
+	if (!target) {
+		return null;
+	}
+
+	return extractText(target, customOptions);
+}
+
+function queryTexts(context, selector, customOptions) {
+	const targets = queryElements(context, selector, customOptions);
+
+	return targets.map((target) => extractText(target, customOptions));
+}
+
 function prefixUrl(urlPath, originUrl, customOptions) {
 	if (!urlPath) {
 		return null;
@@ -626,6 +671,8 @@ const queryFns = {
 	sourceSets: querySourceSets,
 	srcSet: querySourceSet,
 	srcSets: querySourceSets,
+	text: queryText,
+	texts: queryTexts,
 	url: queryUrl,
 	urls: queryUrls,
 	video: queryVideo,

package/tests/index.html

@@ -46,5 +46,18 @@
 
 		<div class="dataset" data-hello="world" data-foo="bar">
 		<div class="dataset" data-hello="world" data-foo="bar">
+
+		<div class="text">
+			<span>this should not be extracted</span>
+			this is our juice
+			<span>this should not be extracted</span>
+			more juice
+		</div>
+
+		<div class="text">
+			<span>this should not be extracted</span>
+			this some more text
+			this is the final text
+		</div>
     </body>
 </html>

package/tests/init.js

@@ -28,6 +28,9 @@ async function initTest() {
 	console.log('items', res.context.query.contents('.item'));
 	console.log('link', res.context.query.url('#link'));
 	console.log('links', res.context.query.urls('.link'));
+	console.log('text', res.context.query.text('.text'));
+	console.log('texts', res.context.query.text('.text', { join: false }));
+	console.log('all texts', res.context.query.texts('.text'));
 	console.log('image', res.context.query.img('.image'));
 	console.log('images', res.context.query.imgs('.image'));
 	console.log('srcset', res.context.query.sourceSet('.srcset'));