org.jsoup.nodes.Document.outerHtml()方法的使用及代码示例

x33g5p2x  于2022-01-18 转载在 其他  
字(7.6k)|赞(0)|评价(0)|浏览(314)

本文整理了Java中org.jsoup.nodes.Document.outerHtml()方法的一些代码示例，展示了Document.outerHtml()的具体用法。这些代码示例主要来源于Github/Stackoverflow/Maven等平台，是从一些精选项目中提取出来的代码，具有较强的参考意义，能在一定程度帮忙到你。Document.outerHtml()方法的具体详情如下：
包路径：org.jsoup.nodes.Document
类名称：Document
方法名：outerHtml

Document.outerHtml介绍

暂无

代码示例

代码示例来源：origin: RipMeApp/ripme

public static String getVideoURLAtPage(String url) throws IOException {
    Document doc = Http.url(url)
              .userAgent(USER_AGENT)
              .get();
    String html = doc.outerHtml();
    String videoURL = null;
    for (String quality : new String[] {"1080", "720", "480", "240"}) {
      quality = "url" + quality + "\\\":\\\"";
      if (html.contains(quality)) {
        videoURL = html.substring(html.indexOf(quality) + quality.length());
        videoURL = videoURL.substring(0, videoURL.indexOf("\""));
        videoURL = videoURL.replace("\\", "");
        break;
      }
    }
    if (videoURL == null) {
      throw new IOException("Could not find video URL at " + url);
    }
    return videoURL;
  }
}

代码示例来源：origin: RipMeApp/ripme

@Override
  public void run() {
    try {
      if (isStopped() && !isThisATest()) {
        return;
      }
      String u = this.url.toExternalForm();
      Document doc = Http.url(u)
                .referrer(u)
                .get();
      Pattern p = Pattern.compile("^.*__fileurl = '([^']+)';.*$", Pattern.DOTALL);
      Matcher m = p.matcher(doc.outerHtml());
      if (m.matches()) {
        String file = m.group(1);
        String prefix = "";
        if (Utils.getConfigBoolean("download.save_order", true)) {
          prefix = String.format("%03d_", index);
        }
        addURLToDownload(new URL(file), prefix);
      } else {
        LOGGER.warn("[!] could not find '__fileurl' at " + url);
      }
    } catch (IOException e) {
      LOGGER.error("[!] Exception while loading/parsing " + this.url, e);
    }
  }
}

代码示例来源：origin: tomoya92/pybbs

return parse.outerHtml();

代码示例来源：origin: rakam-io/rakam

parse.head().prepend("<script src=\"/static/components/jquery/dist/jquery.min.js\"></script>");
byte[] bytes = parse.outerHtml().getBytes(charset);
DefaultFullHttpResponse copy = new DefaultFullHttpResponse(
    resp.getProtocolVersion(), resp.getStatus(), Unpooled.wrappedBuffer(bytes));

代码示例来源：origin: com.vaadin/vaadin-server

return document.outerHtml();
} else {
  StringBuilder sb = new StringBuilder();

代码示例来源：origin: wuman/JReadability

/**
 * Get the combined outer HTML of all matched elements.
 * 
 * @return
 */
public final String outerHtml() {
  return mDocument.outerHtml();
}

代码示例来源：origin: org.symphonyoss.symphony/symphony-client

@SuppressWarnings("unused")
public String getOuterHtml() {
  return originalDoc.outerHtml();
}

代码示例来源：origin: symphonyoss/symphony-java-client

@SuppressWarnings("unused")
public String getOuterHtml() {
  return originalDoc.outerHtml();
}

代码示例来源：origin: stackoverflow.com

import org.apache.commons.io.FileUtils;

public void downloadPage() throws Exception {
    final Response response = Jsoup.connect("http://www.example.net").execute();
    final Document doc = response.parse();

    final File f = new File("filename.html");
    FileUtils.writeStringToFile(f, doc.outerHtml(), "UTF-8");
  }

代码示例来源：origin: com.cognifide.aet/jobs

private String formatCodeAllFormatted(String code) {
 Document doc = Jsoup.parse(code);
 return removeEmptyLines(doc.outerHtml());
}

代码示例来源：origin: Cognifide/aet

private String formatCodeAllFormatted(String code) {
 Document doc = Jsoup.parse(code);
 return removeEmptyLines(doc.outerHtml());
}

代码示例来源：origin: stackoverflow.com

Document doc = Jsoup.parse(html);

doc.outputSettings().indentAmount(4).outline(true);

String result = doc.outerHtml();

代码示例来源：origin: fr.sii.ogham/ogham-core

@Override
public ContentWithImages inline(String htmlContent, List<ImageResource> images) {
  Document doc = Jsoup.parse(htmlContent);
  for (ImageResource image : images) {
    Elements imgs = getImagesToInline(doc, image);
    for (Element img : imgs) {
      img.attr(SRC_ATTR, MessageFormat.format(BASE64_URI, image.getMimetype(), Base64Utils.encodeToString(image.getContent())));
      img.attr(INLINED_ATTR, true);
    }
  }
  return new ContentWithImages(doc.outerHtml(), new ArrayList<Attachment>(0));
}

代码示例来源：origin: OpenNMS/opennms

/**
 * Pre-process HTML.
 *
 * @param request the request
 * @param is the input stream
 * @return the updated input stream
 * @throws IOException Signals that an I/O exception has occurred.
 */
protected InputStream preProcessHtml(Request request, InputStream is) throws IOException {
  if (request == null || is == null || !Boolean.parseBoolean(request.getParameter("pre-parse-html"))) {
    return is;
  }
  try {
    org.jsoup.nodes.Document doc = Jsoup.parse(is, "ISO-8859-9", "/");
    doc.outputSettings().escapeMode(EscapeMode.xhtml);
    return new ByteArrayInputStream(doc.outerHtml().getBytes());
  } finally {
    IOUtils.closeQuietly(is);
  }
}

代码示例来源：origin: USPTO/PatentPublicData

@Override
public String getPlainText(String rawText, FreetextConfig textConfig) {
  Document jsoupDoc = Jsoup.parse(rawText, "", Parser.xmlParser());
  for (Element paragraph : jsoupDoc.select("PARA")) {
    int level = paragraph.attr("LVL") != null ? Integer.valueOf(paragraph.attr("LVL")) : 0;
    StringBuilder stb = new StringBuilder();
    for (int i = 0; i <= level; i++) {
      stb.append("&nbsp;");
    }
    paragraph.prepend(stb.toString());
  }
  String simpleHtml = getSimpleHtml(jsoupDoc.outerHtml());
  Document simpleDoc = Jsoup.parse(simpleHtml, "", Parser.xmlParser());
  HtmlToPlainText htmlConvert = new HtmlToPlainText(textConfig);
  return htmlConvert.getPlainText(simpleDoc);
}

代码示例来源：origin: USPTO/PatentPublicData

@Override
public String getPlainText(String rawText, FreetextConfig textConfig) {
  Document jsoupDoc = Jsoup.parse(rawText, "", Parser.xmlParser());
  for (int j = 0; j < 4; j++) {
    for (Element paragraph : jsoupDoc.select("PA" + j)) {
      int level = j;
      StringBuilder stb = new StringBuilder();
      for (int i = 0; i <= level; i++) {
        stb.append("&nbsp;");
      }
      paragraph.prepend(stb.toString());
    }
  }
  String simpleHtml = getSimpleHtml(jsoupDoc.outerHtml());
  Document simpleDoc = Jsoup.parse(simpleHtml, "", Parser.xmlParser());
  HtmlToPlainText htmlConvert = new HtmlToPlainText(textConfig);
  return htmlConvert.getPlainText(simpleDoc);
}

代码示例来源：origin: fr.sii.ogham/ogham-core

@Override
public String inline(String htmlContent, List<ExternalCss> cssContents) {
  Document doc = Jsoup.parse(htmlContent);
  internStyles(doc, cssContents);
  String stylesheet = fetchStyles(doc);
  extractStyles(doc, stylesheet);
  applyStyles(doc);
  return doc.outerHtml();
}

代码示例来源：origin: astamuse/asta4d

public String output() {
  // body only attr on body
  if (renderedDocument.body().hasAttr(ExtNodeConstants.ATTR_BODY_ONLY_WITH_NS)) {
    return renderedDocument.body().html();
  }
  // body only meta
  Elements bodyonlyMeta = renderedDocument.head().select(SelectorUtil.attr("meta", ExtNodeConstants.ATTR_BODY_ONLY_WITH_NS, null));
  if (bodyonlyMeta.size() > 0) {
    return renderedDocument.body().html();
  }
  // full page
  return renderedDocument.outerHtml();
}

代码示例来源：origin: com.vaadin/flow-server

@Override
public boolean synchronizedHandleRequest(VaadinSession session,
    VaadinRequest request, VaadinResponse response) throws IOException {
  // Find UI class
  Class<? extends UI> uiClass = getUIClass(request);
  BootstrapContext context = createAndInitUI(uiClass, request, response,
      session);
  ServletHelper.setResponseNoCacheHeaders(response::setHeader,
      response::setDateHeader);
  Document document = getBootstrapPage(context);
  writeBootstrapPage(response, document.outerHtml());
  return true;
}

代码示例来源：origin: jenkinsci/email-ext-plugin

/**
 * Takes an input string representing an html document and processes it with
 * the Css Inliner.
 *
 * @param input the html document
 * @return the processed html document
 */
public String process(String input) {
  Document doc = Jsoup.parse(input);
  // check if the user wants to inline the data
  Elements elements = doc.getElementsByAttributeValue(DATA_INLINE_ATTR, "true");
  if (elements.isEmpty()) {
    return input;
  }
  extractStyles(doc);
  applyStyles(doc);
  inlineImages(doc);
  doc.outputSettings(doc.outputSettings().syntax(Document.OutputSettings.Syntax.xml).prettyPrint(false).escapeMode(Entities.EscapeMode.extended));
  return StringEscapeUtils.unescapeHtml(doc.outerHtml());
}

内容来源于网络，如有侵权，请联系作者删除！

Document

相关文章

    查看更多

    热门标签

    更多
    JavaquerypythonNode开发语言requestUtil数据库Table后端算法LoggerMessageElementParser

    最新文章

    更多
    • 蜀ICP备13028337号-1 大数据知识库 https://www.saoniuhuo.com © All rights reserved
    • 本站内容来源互联网,如果侵犯您的权益请联系我们删除, 联系方式：448109455@qq.com