Merge branch 'master' into bael-16656

jsoup/README.md

@@ -0,0 +1,10 @@
+## jsoup
+
+This module contains articles about jsoup.
+
+### Relevant Articles: 
+- [Parsing HTML in Java with Jsoup](https://www.baeldung.com/java-with-jsoup)
+
+### Build the Project
+
+mvn clean install

jsoup/pom.xml

@@ -0,0 +1,27 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+    xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
+    <modelVersion>4.0.0</modelVersion>
+    <artifactId>jsoup</artifactId>
+    <name>jsoup</name>
+    <packaging>jar</packaging>
+
+    <parent>
+        <groupId>com.baeldung</groupId>
+        <artifactId>parent-modules</artifactId>
+        <version>1.0.0-SNAPSHOT</version>
+    </parent>
+
+    <dependencies>
+        <dependency>
+            <groupId>org.jsoup</groupId>
+            <artifactId>jsoup</artifactId>
+            <version>${jsoup.version}</version>
+        </dependency>
+    </dependencies>
+
+    <properties>
+        <jsoup.version>1.10.2</jsoup.version>
+    </properties>
+
+</project>

jsoup/src/test/java/com/baeldung/jsoup/JsoupParserIntegrationTest.java

@@ -0,0 +1,122 @@
+package com.baeldung.jsoup;
+
+import org.jsoup.HttpStatusException;
+import org.jsoup.Jsoup;
+import org.jsoup.nodes.Document;
+import org.jsoup.nodes.Element;
+import org.jsoup.parser.Tag;
+import org.jsoup.select.Elements;
+import org.junit.Before;
+import org.junit.Test;
+
+import java.io.IOException;
+
+import static org.junit.Assert.assertEquals;
+import static org.junit.Assert.assertTrue;
+
+public class JsoupParserIntegrationTest {
+
+    private Document doc;
+
+    @Before
+    public void setUp() throws IOException {
+        doc = Jsoup.connect("https://spring.io/blog")
+            .get();
+    }
+
+    @Test
+    public void loadDocument404() throws IOException {
+        try {
+            doc = Jsoup.connect("https://spring.io/will-not-be-found")
+                .get();
+        } catch (HttpStatusException ex) {
+            assertEquals(404, ex.getStatusCode());
+        }
+    }
+
+    @Test
+    public void loadDocumentCustomized() throws IOException {
+        doc = Jsoup.connect("https://spring.io/blog")
+            .userAgent("Mozilla")
+            .timeout(5000)
+            .cookie("cookiename", "val234")
+            .cookie("anothercookie", "ilovejsoup")
+            .referrer("http://google.com")
+            .header("headersecurity", "xyz123")
+            .get();
+    }
+
+    @Test
+    public void examplesSelectors() {
+        Elements links = doc.select("a");
+        Elements logo = doc.select(".spring-logo--container");
+        Elements pagination = doc.select("#pagination_control");
+        Elements divsDescendant = doc.select("header div");
+        Elements divsDirect = doc.select("header > div");
+
+        Element pag = doc.getElementById("pagination_control");
+        Elements desktopOnly = doc.getElementsByClass("desktopOnly");
+
+        Elements sections = doc.select("section");
+        Element firstSection = sections.first();
+        Elements sectionParagraphs = firstSection.select(".paragraph");
+    }
+
+    @Test
+    public void examplesTraversing() {
+        Elements sections = doc.select("section");
+
+        Element firstSection = sections.first();
+        Element lastSection = sections.last();
+        Element secondSection = sections.get(2);
+        Elements allParents = firstSection.parents();
+        Element parent = firstSection.parent();
+        Elements children = firstSection.children();
+        Elements siblings = firstSection.siblingElements();
+
+        sections.forEach(el -> System.out.println("section: " + el));
+    }
+
+    @Test
+    public void examplesExtracting() {
+        Element firstArticle = doc.select("article")
+            .first();
+        Element timeElement = firstArticle.select("time")
+            .first();
+        String dateTimeOfFirstArticle = timeElement.attr("datetime");
+        Element sectionDiv = firstArticle.select("section div")
+            .first();
+        String sectionDivText = sectionDiv.text();
+        String articleHtml = firstArticle.html();
+        String outerHtml = firstArticle.outerHtml();
+    }
+
+    @Test
+    public void examplesModifying() {
+        Element firstArticle = doc.select("article")
+            .first();
+        Element timeElement = firstArticle.select("time")
+            .first();
+        Element sectionDiv = firstArticle.select("section div")
+            .first();
+
+        String dateTimeOfFirstArticle = timeElement.attr("datetime");
+        timeElement.attr("datetime", "2016-12-16 15:19:54.3");
+        sectionDiv.text("foo bar");
+        firstArticle.select("h2")
+            .html("<div><span></span></div>");
+
+        Element link = new Element(Tag.valueOf("a"), "").text("Checkout this amazing website!")
+            .attr("href", "http://baeldung.com")
+            .attr("target", "_blank");
+        firstArticle.appendChild(link);
+
+        doc.select("li.navbar-link")
+            .remove();
+        firstArticle.select("img")
+            .remove();
+
+        assertTrue(doc.html()
+            .contains("http://baeldung.com"));
+    }
+}