Created
April 7, 2016 05:11
-
-
Save jmini/ae3265583c5d6f37bbdd2f8ef300d2f8 to your computer and use it in GitHub Desktop.
Check HTML links to local pages, using JSoup
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import java.io.File; | |
| import java.io.FileFilter; | |
| import java.io.FilenameFilter; | |
| import org.jsoup.Jsoup; | |
| import org.jsoup.nodes.Document; | |
| import org.jsoup.nodes.Element; | |
| import org.jsoup.select.Elements; | |
| import com.google.common.base.Charsets; | |
| import com.google.common.io.Files; | |
| /** | |
| * Check HTML links to local pages, using JSoup. | |
| */ | |
| public class CheckLink { | |
| private static final FileFilter DIRECTORY_FILEFILTER = new FileFilter() { | |
| @Override | |
| public boolean accept(File f) { | |
| return f.isDirectory(); | |
| } | |
| }; | |
| private static final FilenameFilter HTML_FILENAMEFILTER = new FilenameFilter() { | |
| @Override | |
| public boolean accept(File dir, String name) { | |
| return name.endsWith(".html"); | |
| } | |
| }; | |
| public static void main(String[] args) throws Exception { | |
| File root = new File("C:/Users/jbr/git/n4js"); | |
| handleFolder(root); | |
| } | |
| /** | |
| * @param f | |
| * @throws Exception | |
| */ | |
| private static void checkLinks(File file) throws Exception { | |
| String html = Files.toString(file, Charsets.UTF_8); | |
| Document doc = Jsoup.parse(html); | |
| Elements aElements = doc.getElementsByTag("a"); | |
| for (Element e : aElements) { | |
| String href = e.attr("href"); | |
| if (shouldFixLink(href)) { | |
| if (!href.startsWith("#")) { | |
| int i = href.lastIndexOf("#"); | |
| String path; | |
| if (i > 0) { | |
| path = href.substring(0, i); | |
| } | |
| else { | |
| path = href; | |
| } | |
| File otherFile = new File(file.getParentFile(), path); | |
| if (!otherFile.exists()) { | |
| System.out.println("In file " + file.getAbsolutePath() + " there is a link to '" + href + "' that can not be found"); | |
| } | |
| } | |
| } | |
| } | |
| System.out.println("Checked " + file.getAbsolutePath() + "."); | |
| } | |
| static boolean shouldFixLink(String href) { | |
| return href != null && !href.isEmpty() && !href.matches("(mailto\\:|[a-zA-Z]+\\://|//).+"); | |
| } | |
| /** | |
| * @param root | |
| * @throws Exception | |
| */ | |
| private static void handleFolder(File folder) throws Exception { | |
| File[] files = folder.listFiles(HTML_FILENAMEFILTER); | |
| for (File f : files) { | |
| checkLinks(f); | |
| } | |
| File[] folders = folder.listFiles(DIRECTORY_FILEFILTER); | |
| if (folders != null) { | |
| for (File f : folders) { | |
| handleFolder(f); | |
| } | |
| } | |
| } | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment