Package org.jsoup.nodes

Examples of org.jsoup.nodes.Document

66
67
68
69
70
71
72
73
74
75
        // dumpResponse( response );

        List<String> expectedLinks = Arrays.asList( ".indexer/", "commons-lang/", "net/", "org/" );

        Document document = Jsoup.parse( response.getContentAsString() );
        Elements elements = document.getElementsByTag( "a" );

        assertLinks( expectedLinks, elements );
    }
View Full Code Here
82
83
84
85
86
87
88
89
90
91
        WebResponse response = getServletUnitClient().getResponse( request );
        assertEquals( "Response", HttpServletResponse.SC_OK, response.getStatusCode() );

        List<String> expectedLinks = Arrays.asList( "../", "apache/", "codehaus/" );

        Document document = Jsoup.parse( response.getContentAsString() );
        Elements elements = document.getElementsByTag( "a" );

        assertLinks( expectedLinks, elements );
    }
View Full Code Here
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
        }

        String startPath = StringUtils.substringBefore( path, "/" );

        // replace all links !!
        Document document = Jsoup.parse( is, "UTF-8", "" );

        Element body = document.body().child( 0 );

        Elements links = body.select( "a[href]" );

        for ( Element link : links ) {
            link.attr( "href", "#" + startPath + "/" + link.attr( "href" ) );
        }

        Elements codes = body.select( "code" );

        for ( Element code : codes ) {
            code.attr( "class", code.attr( "class" ) + " nice-code" );
        }

        //default generated enunciate use h1/h2/h3 which is quite big so transform to h3/h4/h5

        Elements headers = body.select( "h1" );

        for ( Element header : headers ) {
            header.tagName( "h3" );
        }

        headers = body.select( "h2" );

        for ( Element header : headers ) {
            header.tagName( "h4" );
        }

        headers = body.select( "h3" );

        for ( Element header : headers ) {
            header.tagName( "h5" );
        }

        Document res = new Document( "" );
        res.appendChild( body.select( "div[id=main]" ).first() );

        resp.getOutputStream().write( res.outerHtml().getBytes() );

    }
View Full Code Here
329
330
331
332
333
334
335
336
337
338
339
340
341
                while((text = input.readLine()) != null) 
                    buffer.append(text +"\n");
                code = buffer.toString();
               
//              将html中table提取出来，html头部等信息都不要
                Document doc = Jsoup.parse(code);
            StringBuffer sb = new StringBuffer();
            Elements elements = doc.select("table");
            for(int i=0;i<elements.size();i++){
              Element element = elements.get(i);
              sb.append(element.toString());
            }
           
View Full Code Here
88
89
90
91
92
93
94
95
96
97
98
99
 
  public OperResult renderXLSV2(String id,String html,String time,String title,String mode,Map parameterMap){
//    System.out.println(html);
    OperResult result = new OperResult();
    if(html!=null){
      Document doc = Jsoup.parseBodyFragment(html);
      Elements tables = doc.select("table");
      Workbook book = HTMLAdjustMent4J.convertHTML2Excel(tables);
      if(book!=null){
        result.setSucceed();
        result.setData(book);
//        result.setInfoMSG("报表");
View Full Code Here
165
166
167
168
169
170
171
172
173
174
175
176
  }
 
  public OperResult renderXLS(String id,String html,Map parameterMap) {
    OperResult result = new OperResult();
    if(html!=null){
      Document doc = Jsoup.parseBodyFragment(html);
      Elements tables = doc.select("table");
      List<Workbook> books = new ArrayList<Workbook>();
      for(int i=0;i<tables.size();i++){
        Element table = tables.get(i);
        Workbook book = HTMLAdjustMent4J.convertHTML2Excel(table.toString());
        if(book!=null){
View Full Code Here
46
47
48
49
50
51
52
53
54
55
56
        System.out.println(t.toStringTree());

    }
   
    private static void testHTMLExcelBridge(String content) throws Exception, ExcelException{
      Document doc = Jsoup.parseBodyFragment(content);
      Elements sheets = doc.select("table");
      HTMLExcelBridge heb = new HTMLExcelBridge(sheets);
      heb.reEvaluateAll();
      System.out.println(sheets.toString());
    }
View Full Code Here
153
154
155
156
157
158
159
160
161
162
    return null;
  }
 
  public HTMLTableManipulator(String code){
    if(code!=null){
      Document document = Jsoup.parseBodyFragment(code);
      tables = document.select("table");
     
    }
  }
View Full Code Here
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
    OperResult result = new OperResult();
    InputStream in = null;
    try {
      in = new FileInputStream(file1);
      Workbook book = WorkbookFactory.create(in);
      Document doc = Jsoup.parse("");
      Element body = doc.body();
      for(int i=0;i<book.getNumberOfSheets();i++){
        Sheet sheet = book.getSheetAt(i);
        if(!ExcelUtility.isEmptySheet(sheet)){
          Element table = body.appendElement("table");
          table.attr("title",sheet.getSheetName());
          ExcelUtility.convertSheet2HTMLTable(sheet, table);
        }
      }
      result.setSucceed();
      result.setData(doc.select("table").toString());
    } catch (Exception e) {
      // TODO Auto-generated catch block
      e.printStackTrace();
      result.setFailed(e.getMessage());
    } finally{
View Full Code Here
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
    
  }
 
  public static Workbook convertHTML2Excel(String tables){
    if(tables!=null){
      Document doc = Jsoup.parse(tables);
      doc.head().append("<META HTTP-EQUIV=\"CONTENT-TYPE\" CONTENT=\"text/html; charset=utf-8\">");
      try {
//        byte[] html = doc.toString().getBytes("utf-8");
        ByteArrayOutputStream bos = new ByteArrayOutputStream();
//        DocumentConverter.convert(doc.toString().getBytes("utf-8"), "html", bos, "xls");
        Workbook wb = WorkbookFactory.create(new ByteArrayInputStream(bos.toByteArray()));
        Elements tableElements = doc.select("table");
        for(int i=0;i<tableElements.size();i++){
          Element table = tableElements.get(i);
          if(table.hasAttr("title")){
            if(wb.getNumberOfSheets()>i){
              wb.setSheetName(i, table.attr("title"));
View Full Code Here
TOP

Related Classes of org.jsoup.nodes.Document

  • at.newmedialab.ldpath.model.functions.CssSelectFunction
  • br.com.objectos.way.bvmf.bdr.BdrWgetGuice
  • br.com.objectos.way.bvmf.bdr.BdrWgetGuice$Get
  • br.com.objectos.way.bvmf.bdr.TesteDeBdrParser
  • br.com.objectos.way.bvmf.fi.fii.FiiWgetGuice
  • br.com.objectos.way.bvmf.fi.fii.FiiWgetGuice$Get
  • by.dreamer.App
  • cn.edu.hfut.dmic.webcollector.parser.ParseUtils
  • com.astamuse.asta4d.Component
  • com.astamuse.asta4d.Page
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.