Created
October 4, 2018 14:22
-
-
Save nicolausYes/37189184a3ff8deae6c4af52bdb7fa04 to your computer and use it in GitHub Desktop.
Parse genres/subgenres from ITunes
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
final StringBuilder builder = new StringBuilder(); | |
final String pattern = "([\\d])\\w+"; | |
Pattern compiledPattern = Pattern.compile(pattern); | |
try { | |
Document doc = Jsoup.connect("https://itunes.apple.com/us/genre/podcasts/id26?mt=2").get(); | |
Elements links = doc.select("a.top-level-genre[href],.top-level-subgenres a[href]"); | |
for (Element link : links) { | |
String url = link.attr("href"); | |
String text = link.text(); | |
String id = ""; | |
String enumName = text.replace(" ", "_") | |
.replace("-", "_") | |
.replace("&", "and") | |
.toUpperCase();; | |
String result = ""; | |
if (link.hasClass("top-level-genre")) | |
result += "\n"; | |
Matcher m = compiledPattern.matcher(url); | |
if (m.find()) | |
id = m.group(0); | |
result += String.format(Locale.ENGLISH, "%s(%s, \"%s\"),\n", | |
enumName, id, text); | |
builder.append(result); | |
} | |
} catch (IOException e) { | |
builder.append("Error : ").append(e.getMessage()).append("\n"); | |
} | |
Log.d("TAG", builder.toString()); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment