unprint 0.4.3 → 0.6.0

package/README.md

@@ -43,11 +43,73 @@ query.element('h1#title'); // HTMLHeadingElement
 #### Selector
 The selector can be a CSS selector, an XPath selector starting with `//`, or an array of either or both acting as fallbacks. If the selector is falsy, the input element will be used.
 
+#### Querying multiple elements
+Most methods can be used in plural, returning an array of results, i.e. `query.elements()`, `query.dates()`.
+
 #### Query an element
 * `query.element([selector], [options])`
 
 Returns the element node directly.
 
+#### Query an attribute
+`query.attribute(selector, attribute, [options])` or `query.attr()`
+
+Return the contents of an attribute. Alias for `query.element([selector], { attribute: [attribute] })`.
+
+#### Query existence
+`query.exists(selector, [options])`
+
+Return the presence of an element as a boolean.
+
+#### Query count
+`query.count(selector, [options])`
+
+Return the number of elements that match the selector.
+
+#### Query the content
+`query.content([selector], [options])`
+
+Return the text contents of an element (`.textContent`).
+
+#### Query the HTML
+`query.content([selector], [options])`
+
+Return the HTML contents of an element (`.innerHTML`).
+
+#### Query a URL
+`query.url([selector], [options])`
+
+Options
+* `origin`: The hostname to prefix when it is not included in the URL (`/path`).
+* `protocol`: The protocol to use when it is not included in the URL (`:www.example.com`, default `http`).
+
+Returns the `href` from an anchor element (or any other specified target) as a string.
+
+#### Query an image
+`query.image([selector], [options])` or `query.img()`
+
+Options:
+* All options supported by `query.url()`.
+
+Returns the `src` from an image element (or any other specified target) as a string.
+
+#### Query a source set
+`query.sourceSet([selector], [options])` or `query.srcSet()`
+
+Options:
+* `includeDescriptor`: Produce an array of `{ descriptor, url }` instead of URL strings.
+* All options supported by `query.url()`.
+
+Returns an array of media URLs from the `srcset` of an media element as strings sorted by their descriptor from large to small.
+
+#### Query a video
+`query.video([selector], [options])`
+
+Options:
+* All options supported by `query.url()`.
+
+Returns the `src` from an video source element (or any other specified target) as a string.
+
 #### Query a date
 `query.date(selector, format, [options])`
 
@@ -55,13 +117,23 @@ Arguments
 * `format` (string, array): The input format as a string or array of strings described by the [Moment.js docs](https://momentjs.com/docs/#/displaying/format/).
 
 Options
-* `match (RegExp): The text to extract before attempting to parse it as a date. The default expression will attempt to extract any of 01-01-1970, 1970-01-01, 01/01/1970 or January 1, 1970 with optional 00:00[:00] time.
+* `match` (RegExp): The text to extract before attempting to parse it as a date. The default expression will attempt to extract any of 01-01-1970, 1970-01-01, 01/01/1970 or January 1, 1970 with optional 00:00[:00] time.
 * `timezone` (string): The name of the input timezone, defaults to 'UTC'.
 
 Returns a Date object.
 
-#### Querying multiple elements
-Most methods can be used in plural, returning an array of results, i.e. `query.elements()`, `query.dates()`.
+#### Query a duration
+`query.duration(selector, format, [options])` or `query.dur`
+
+Options
+* `match` (RegExp): The text to extract before attempting to parse it as a duration. The default expression will attempt to extract `(hh:)mm:ss` and `PT##H##M##S`.
+
+Returns the duration in seconds as a number.
+
+#### Query JSON
+`query.json([selector], [options])`
+
+Returns the parsed JSON content of an element as an object.
 
 ### HTTP request
 * `unprint.get(url, [options])`

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "unprint",
-  "version": "0.4.3",
+  "version": "0.6.0",
   "description": "Simplify common web scraping tasks while staying in control of the data.",
   "main": "src/app.js",
   "scripts": {

package/src/app.js

@@ -295,6 +295,50 @@ function queryImages(context, selector = 'img', customOptions) {
 	return imageUrls.map((imageUrl) => prefixUrl(imageUrl, options.origin, options));
 }
 
+function querySourceSet(context, selector, attr = 'srcset', customOptions = {}) {
+	const srcset = queryAttribute(context, selector, attr, customOptions);
+
+	if (!srcset) {
+		return null;
+	}
+
+	const sources = srcset
+		.split(/\s*,\s*/)
+		.map((source) => {
+			const [link, descriptor] = source.split(' ');
+
+			if (link) {
+				return {
+					descriptor: descriptor || 'fallback',
+					url: prefixUrl(link, customOptions.origin, customOptions.protocol),
+				};
+			}
+
+			return null;
+		})
+		.filter(Boolean)
+		.sort((sourceA, sourceB) => {
+			if (sourceB.descriptor === 'fallback' || parseInt(sourceA.descriptor, 10) > parseInt(sourceB.descriptor, 10)) {
+				return -1;
+			}
+
+			if (parseInt(sourceA.descriptor, 10) < parseInt(sourceB.descriptor, 10)) {
+				return 1;
+			}
+
+			return 0;
+		});
+
+	if (customOptions.includeDescriptor) {
+		return sources.map((source) => ({
+			descriptor: source.descriptor,
+			url: prefixUrl(source.url),
+		}));
+	}
+
+	return sources.map((source) => prefixUrl(source.url));
+}
+
 function queryVideo(context, selector = 'source', customOptions) {
 	const options = {
 		...context.options,
@@ -391,6 +435,48 @@ function queryDates(context, selector, format, customOptions) {
 	}));
 }
 
+function extractDuration(durationString, match) {
+	const durationMatch = durationString.match(match || /(\d+:)?\d+:\d+/);
+
+	if (durationMatch) {
+		const segments = ['00'].concat(durationMatch[0].split(/[:hm]/)).slice(-3);
+
+		return moment.duration(segments.join(':')).asSeconds();
+	}
+
+	return null;
+}
+function extractTimestamp(durationString) {
+	const timestampMatch = durationString.match(/(\d+H)?\s*(\d+M)?\s*\d+S?/i);
+
+	if (timestampMatch) {
+		const hours = timestampMatch[0].match(/(\d+)H/i)?.[1] || 0;
+		const minutes = timestampMatch[0].match(/(\d+)M/i)?.[1] || 0;
+		const seconds = timestampMatch[0].match(/(\d+)(S|$)/i)?.[1] || 0;
+
+		return (Number(hours) * 3600) + (Number(minutes) * 60) + Number(seconds);
+	}
+
+	return null;
+}
+
+function queryDuration(context, selector, customOptions) {
+	const options = { ...customOptions };
+	const durationString = queryContent(context, selector, customOptions);
+
+	if (!durationString) {
+		return null;
+	}
+
+	if (options.match) {
+		return extractDuration(durationString, options.match);
+	}
+
+	return extractDuration(durationString)
+		|| extractTimestamp(durationString)
+		|| null;
+}
+
 const queryFns = {
 	element: queryElement,
 	elements: queryElements,
@@ -415,6 +501,10 @@ const queryFns = {
 	jsons: queryJsons,
 	date: queryDate,
 	dates: queryDates,
+	duration: queryDuration,
+	dur: queryDuration,
+	sourceSet: querySourceSet,
+	srcSet: querySourceSet,
 	url: queryUrl,
 	video: queryVideo,
 	videos: queryVideos,
@@ -592,6 +682,7 @@ module.exports = {
 	init,
 	initAll,
 	extractDate,
+	extractDuration,
 	options: configure,
 	query: initQueryFns(queryFns),
 };

package/tests/index.html

@@ -21,10 +21,15 @@
 		<div id="date">Date: 22-07-2022 02:00</div>
 		<div id="date2">Date: 13-05-2022 18:00</div>
 
+		<div id="duration">01:15:33</div>
+		<div id="timestamp">PT1H34M18S</div>
+
 		<img class="image" src="https://i.redd.it/vn9h981hlx281.png">
 		<img class="image" src="https://i.redd.it/1s22dsrqy0181.jpg">
 		<img class="image" src="https://i.redd.it/e91oo4ueyeb71.jpg">
 
+		<img class="srcset" srcset="https://i.redd.it/e91oo4ueyeb71.jpg 240w, https://i.redd.it/vn9h981hlx281.png 480w, https://i.redd.it/e91oo4ueyeb71.jpg 640w">
+
 		<video id="video"><source src="https://i.imgur.com/eDQmLys.mp4"></video>
 
 		<script id="json" type="application/js">{"foo": "bar", "lorem": "ipsum", "hello": "world"}</script>

package/tests/init.js

@@ -18,11 +18,14 @@ async function initTest() {
 
 	console.log('title', res.context.query.content('//*[contains(text(), "Test")]'));
 	console.log('date', res.context.query.date('#date', 'DD-MM-YYYY HH:mm'));
+	console.log('duration', res.context.query.duration('#duration'));
+	console.log('timestamp', res.context.query.duration('#timestamp'));
 	console.log('data', res.context.query.json('#json'));
 	console.log('items', res.context.query.contents('.item'));
 	console.log('link', res.context.query.url('#link'));
 	console.log('image', res.context.query.img('.image'));
 	console.log('images', res.context.query.imgs('.image'));
+	console.log('srcset', res.context.query.sourceSet('.srcset'));
 	console.log('path', res.context.query.url('#path'));
 	console.log('relative path', res.context.query.url('#relativePath'));
 	console.log('exists', res.context.query.exists('#title'));