* Update HtmlUnitAndJUnitTest.java

* Update HtmlUnitWebScraping.java

* Update HtmlUnitAndSpringTest.java

* Create message.html

* Update HtmlUnitAndJUnitTest.java

* Delete HtmlUnitAndSpringIntegrationTest.java

* Delete HtmlUnitTest.java
This commit is contained in:
Juan García Heredero
2016-11-28 18:43:10 +01:00
committed by Grzegorz Piwowarek
parent 678e47dc1a
commit 977333c9a3
6 changed files with 131 additions and 115 deletions

View File

@@ -5,36 +5,38 @@ import java.util.List;
import com.gargoylesoftware.htmlunit.WebClient;
import com.gargoylesoftware.htmlunit.html.HtmlAnchor;
import com.gargoylesoftware.htmlunit.html.HtmlHeading1;
import com.gargoylesoftware.htmlunit.html.HtmlHeading2;
import com.gargoylesoftware.htmlunit.html.HtmlPage;
public class HtmlUnitWebScraping {
public static void main(final String[] args) throws Exception {
try (final WebClient webClient = new WebClient()) {
private WebClient webClient;
webClient.getOptions().setCssEnabled(false);
webClient.getOptions().setJavaScriptEnabled(false);
@Before
public void init() throws Exception {
webClient = new WebClient();
}
final HtmlPage page = webClient.getPage("http://www.baeldung.com/full_archive");
final HtmlAnchor latestPostLink = (HtmlAnchor) page.getByXPath("(//ul[@class='car-monthlisting']/li)[1]/a").get(0);
@After
public void close() throws Exception {
webClient.close();
}
System.out.println("Entering: " + latestPostLink.getHrefAttribute());
@Test
public void givenBaeldungArchive_whenRetrievingArticle_thenHasH1()
throws Exception {
webClient.getOptions().setCssEnabled(false);
webClient.getOptions().setJavaScriptEnabled(false);
final HtmlPage postPage = latestPostLink.click();
String url = "http://www.baeldung.com/full_archive";
HtmlPage page = webClient.getPage(url);
String xpath = "(//ul[@class='car-monthlisting']/li)[1]/a";
HtmlAnchor latestPostLink
= (HtmlAnchor) page.getByXPath(xpath).get(0);
HtmlPage postPage = latestPostLink.click();
final HtmlHeading1 heading1 = (HtmlHeading1) postPage.getByXPath("//h1").get(0);
System.out.println("Title: " + heading1.getTextContent());
final List<HtmlHeading2> headings2 = (List<HtmlHeading2>) postPage.getByXPath("//h2");
final StringBuilder sb = new StringBuilder(heading1.getTextContent());
for (final HtmlHeading2 h2 : headings2) {
sb.append("\n").append(h2.getTextContent());
}
System.out.println(sb.toString());
}
}
List<HtmlHeading1> h1
= (List<HtmlHeading1>) postPage.getByXPath("//h1");
Assert.assertTrue(h1.size() > 0);
}
}