Java Parser类代码示例

import org.jsoup.parser.Parser; //导入依赖的package包/类
public void action(JSONObject data) throws EventException {
	final JSONObject article = data.optJSONObject(Article.ARTICLE);

	String content = article.optString(Article.ARTICLE_CONTENT);

	final Document doc = Jsoup.parse(content, StringUtils.EMPTY, Parser.htmlParser());
	doc.outputSettings().prettyPrint(false);

	final StringBuilder listBuilder = new StringBuilder();

	listBuilder.append("<link rel=\"stylesheet\" type=\"text/css\" href=\"" + Latkes.getStaticServePath()
			+ "/plugins/list/style.css\" />");

	final Elements hs = doc.select("h1, h2, h3, h4, h5");

	listBuilder.append("<ul class='b3-solo-list'>");
	for (int i = 0; i < hs.size(); i++) {
		final Element element = hs.get(i);
		final String tagName = element.tagName().toLowerCase();
		final String text = element.text();
		final String id = "b3_solo_" + tagName + "_" + i;

		element.before("<span id='" + id + "'></span>");

		listBuilder.append("<li class='b3-solo-list-").append(tagName).append("'><a href='#").append(id)
				.append("'>").append(text).append("</a></li>");
	}
	listBuilder.append("</ul>");

	final Element body = doc.getElementsByTag("body").get(0);

	content = listBuilder.toString() + body.html();

	article.put(Article.ARTICLE_CONTENT, content);
}
 

import org.jsoup.parser.Parser; //导入依赖的package包/类
/**
 * Fetches captions/transcript for a given video
 * @param videoID to fetch
 * @param lang this captions should be in
 * @throws IOException
 */
public void getAndSaveTranscript(String videoID, String lang) throws IOException {

    lang = LanguageCode.convertIso2toIso1(lang);

    String url = captionEndPoint+"lang="+lang+"&v="+videoID;
    GetMethod get = new GetMethod(url);
    this.client.executeMethod(get);
    String xmlData = get.getResponseBodyAsString();

    //parse XML
    Document doc = Jsoup.parse(xmlData, "", Parser.xmlParser());
    String allCaps = "";
    for (Element e : doc.select("text")) {
        allCaps += e.text();
    }

    FileSaver file = new FileSaver(allCaps, lang, "youtube_caps", url, videoID);
    file.save(logDb);

}
 

import org.jsoup.parser.Parser; //导入依赖的package包/类
/**
 * Checks if a given video has captions in our target language. As identified by the user who entered them
 * @param videoID to check
 * @param lang target
 * @return true if there are captions in lang
 * @throws IOException
 */
public boolean videoHasCaptionsInLanguage(String videoID, String lang) throws IOException {
    //visit captions index
    GetMethod get = new GetMethod(captionsIndex+videoID);
    this.client.executeMethod(get);
    String xmlData = get.getResponseBodyAsString();

    //parse XML
    Document doc = Jsoup.parse(xmlData, "", Parser.xmlParser());

    //iterate over all captions
    for (Element e : doc.select("track")) {
        String langCode = e.attr("lang_code");
        String fixedLangCode = LanguageCode.convertIso1toIso2(langCode);
        if(fixedLangCode.equals(lang))
            return true;
    }

    return false;
}
 

import org.jsoup.parser.Parser; //导入依赖的package包/类
/**
 * Parse a given HTML template and return the a result object containing the expressions
 * and a transformed HTML.
 * @param htmlTemplate The HTML template to process, as a String
 * @param context Context of the Component we are currently processing
 * @return A {@link TemplateParserResult} containing the processed template and expressions
 */
public TemplateParserResult parseHtmlTemplate(String htmlTemplate,
    TemplateParserContext context)
{
    this.context = context;
    Parser parser = Parser.htmlParser();
    parser.settings(new ParseSettings(true, true)); // tag, attribute preserve case
    Document doc = parser.parseInput(htmlTemplate, "");

    result = new TemplateParserResult();
    processImports(doc);
    processNode(doc);

    result.setProcessedTemplate(doc.body().html());
    return result;
}
 

import org.jsoup.parser.Parser; //导入依赖的package包/类
@Override
protected ArrayList<News> doInBackground(Void ...voids) {
    final ArrayList<News> newsList = new ArrayList<News>();
    try {
        final String endpoint = BASE_URL + NEWS_ENDPOINT;
        final Document doc = Jsoup.connect(endpoint).parser(Parser.xmlParser()).get();
        final Elements elements = doc.select("item");
        for (final Element element : elements) {
            final News news = new News();
            news.title = element.select("title").text();
            news.description = element.select("description").text();
            news.thumbnail = element.select("media|thumbnail").text();
            news.pubDate = element.select("pubDate").text();
            news.link = element.select("link").text();
            newsList.add(news);
        }
    } catch (IOException e){
        Log.e(TAG, "FetchNews error", e);
    }
    return newsList;
}
 

import org.jsoup.parser.Parser; //导入依赖的package包/类
public String removeHtmlTags(String markup) {
    
    String clean = preMatcher.matcher(markup).replaceAll(" ");
    clean = sourceMatcher.matcher(clean).replaceAll(" ");
    clean = syntaxMatcher.matcher(clean).replaceAll(" ");
    clean = commentMatcher.matcher(clean).replaceAll(" ");
    clean = monoTagMatcher.matcher(clean).replaceAll(" ");
    clean = fakeTagMatcher.matcher(clean).replaceAll(" ");
    
    try {
        Document document = Jsoup.parse(clean, "", Parser.xmlParser());
        document.select("math, gallery, ref, br, ins, s, del, tt, blockqoute, table").html(" ");
        clean = document.text();
    } catch(Exception e) {
        e.printStackTrace();
    }
    
    return clean;
}
 

import org.jsoup.parser.Parser; //导入依赖的package包/类
private AudioTrack loadTrack(String videoId) {
  checkLoggedIn();

  try (HttpInterface httpInterface = getHttpInterface()) {
    try (CloseableHttpResponse response = httpInterface.execute(new HttpGet("http://ext.nicovideo.jp/api/getthumbinfo/" + videoId))) {
      int statusCode = response.getStatusLine().getStatusCode();
      if (statusCode != 200) {
        throw new IOException("Unexpected response code from video info: " + statusCode);
      }

      Document document = Jsoup.parse(response.getEntity().getContent(), StandardCharsets.UTF_8.name(), "", Parser.xmlParser());
      return extractTrackFromXml(videoId, document);
    }
  } catch (IOException e) {
    throw new FriendlyException("Error occurred when extracting video info.", SUSPICIOUS, e);
  }
}
 

import org.jsoup.parser.Parser; //导入依赖的package包/类
@Override public List<String> getAllClasses() throws IOException, JSONException, CredentialInvalidException {
    String baseurl = data.getString(PARAM_BASEURL) + "/";

    for (int i = -4; i < MAX_DAYS; i++) {
        LocalDate date = LocalDate.now().plusDays(i);
        String dateStr = DateTimeFormat.forPattern("yyyyMMdd").print(date);
        String url = baseurl + "mobdaten/PlanKl" + dateStr + ".xml?_=" + System.currentTimeMillis();
        try {
            String xml = httpGet(url, "UTF-8");
            Document doc = Jsoup.parse(xml, url, Parser.xmlParser());

            List<String> classes = new ArrayList<>();
            for (Element klasse:doc.select("Klassen > Kl")) {
                classes.add(klasse.select("Kurz").first().text());
            }
            return classes;
        } catch (HttpResponseException e) {
            if (e.getStatusCode() != 404 && e.getStatusCode() != 300) throw e;
        }
    }
    return new ArrayList<>();
}
 

import org.jsoup.parser.Parser; //导入依赖的package包/类
@Test
public void wrongMetaCharsetFallback() {
    try {
        final byte[] input = "<html><head><meta charset=iso-8></head><body></body></html>".getBytes("UTF-8");
        final ByteBuffer inBuffer = ByteBuffer.wrap(input);
        
        Document doc = DataUtil.parseByteData(inBuffer, null, "http://example.com", Parser.htmlParser());
        
        final String expected = "<html>\n" +
                                " <head>\n" +
                                "  <meta charset=\"iso-8\">\n" +
                                " </head>\n" +
                                " <body></body>\n" +
                                "</html>";
        
        assertEquals(expected, doc.toString());
    } catch( UnsupportedEncodingException ex ) {
        fail(ex.getMessage());
    }
}
 

import org.jsoup.parser.Parser; //导入依赖的package包/类
public static void normalXmlParse(){
    String json = CrawlerPack.getFromRemote(url);
    String xml = CrawlerPack.jsonToXml(json);

    // 原始 json 轉為 xml 的結果
    System.out.println( "原始XML" ) ;
    System.out.println( xml );

    Document jsoupDoc = Jsoup.parse(xml, "", Parser.xmlParser());
    jsoupDoc.charset(StandardCharsets.UTF_8);

    // 發生了什麼事？
    System.out.println( "轉換後XML" ) ;
    System.out.println(jsoupDoc.toString());


}
 

import org.jsoup.parser.Parser; //导入依赖的package包/类
@Override
protected String doInBackground(String... strings) {
    Document opmlDocument = null;
    try {
        if (mUrl != null) {
            opmlDocument = Jsoup.connect(mUrl).parser(Parser.xmlParser()).get();
        } else {
            opmlDocument = Jsoup.parse(mFile, "UTF-8");
        }
    } catch (IOException e) {
        e.printStackTrace();
        return e.getMessage();
    }
    if (opmlDocument != null) {
        mOpmlItems = opmlDocument.select("outline");
    }
    return "success";
}
 

import org.jsoup.parser.Parser; //导入依赖的package包/类
public static Document getDocument(String filepath) {
	Document doc = null;
	InputStream is = null;
	try {
		is = new FileInputStream(filepath);
	} catch (FileNotFoundException e1) {
		// TODO Auto-generated catch block
		System.out.println("FileUtils: no such XML file path exists");
		e1.printStackTrace();
		return null;
	}
	try {
		doc = Jsoup.parse(is, "UTF-8", "", Parser.xmlParser());
	} catch (Exception e) {
		System.out.println("Parse file to XML Document error!");
		e.printStackTrace();
	}
	return doc;
}
 

import org.jsoup.parser.Parser; //导入依赖的package包/类
private static String getBranchRegex(String jobXml) {
    try {
        String branchRegex = Jsoup.parse(jobXml, "", Parser.xmlParser())
                .getElementsByTag("gerritProjects").get(0)
                .getElementsByTag(GERRITPROJECT_TAG).get(0)
                .getElementsByTag("branches").get(0)
                .getElementsByTag(BRANCH_TAG).get(0)
                .getElementsByTag("pattern").get(0).html();

        // Remove "^" and "$" at the beginning and the end, respectively
        branchRegex = branchRegex.substring(1, branchRegex.length() - 1);

        // Remove sections of regex that we add post-user-input
        branchRegex = branchRegex.replace("(?!refs/meta/)", "");
        branchRegex = branchRegex.replace("(?!refs/)", "refs/heads/");

        return branchRegex;
    } catch (IndexOutOfBoundsException e) {
        return null;
    }
}
 

import org.jsoup.parser.Parser; //导入依赖的package包/类
private String parse(String str) {
    Document document = Jsoup.parse(str, "", Parser.xmlParser());
    String result = "";
    switch (outType) {
        case TYPE_TEXT:
            result = document.text();
            break;
        case TYPE_HTML:
            result = document.html();
            break;
        default:
            result = document.text();
            break;
    }
    return result;
}
 

import org.jsoup.parser.Parser; //导入依赖的package包/类
/**
 * Read information about user. Here you can read other important info.
 * @throws Exception 
 */
private void getUserInfo() throws Exception {
    //https://www.box.net/api/1.0/rest?action=get_auth_token&api_key=vkf3k5dh0tg1ibvcikjcp8sx0f89d14u&ticket=

    //https://www.box.net/api/1.0/rest?action=get_auth_token&api_key=vkf3k5dh0tg1ibvcikjcp8sx0f89d14u&ticket=xybt9orxzo1xrr5vk4r0axne804y1tpk

    NULogger.getLogger().log(Level.INFO, "{0} Getting auth token value............", getClass());
    httpGet = new NUHttpGet("https://www.box.net/api/1.0/rest?action=get_auth_token&api_key=vkf3k5dh0tg1ibvcikjcp8sx0f89d14u&ticket=" + ticket);
    httpResponse = httpclient.execute(httpGet, httpContext);
    responseString = EntityUtils.toString(httpResponse.getEntity());
    //NULogger.getLogger().log(Level.INFO, "{0}Response : {1}", new Object[]{getClass(), stringResponse});
    
    doc = Jsoup.parse(responseString, "", Parser.xmlParser());
    String auth_token = doc.select("response auth_token").text();

    NULogger.getLogger().log(Level.INFO, "{0} Auth_token : {1}", new Object[]{getClass(), auth_token});
    properties().setEncryptedProperty(KEY_AUTH_TOKEN, auth_token);
}