Package org.htmlcleaner

Examples of org.htmlcleaner.HtmlCleaner.clean()

868
869
870
871
872
873
874
875
876
877
878
    final ArrayList<String> list = new ArrayList<String>();

    HtmlCleaner cleaner = new HtmlCleaner();
    //CleanerProperties props = cleaner.getProperties();    
    //props.setXXX(...);
    TagNode node = cleaner.clean(rawPage);

    TagNode[] myNodes;

    if (depth==1 || depth==2) {
      // <a href=
View Full Code Here
88
89
90
91
92
93
94
95
96
97
98
        }

        String headContentsStr = headContents.toString();
        HtmlCleaner cleaner = new HtmlCleaner();
        // parse the string HTML
        TagNode pageData = cleaner.clean(headContentsStr);

    // read in the declared namespaces
    boolean hasOGspec = false;
    TagNode headElement = pageData.findElementByName("head", true);
    if (headElement.hasAttribute("prefix"))
View Full Code Here
240
241
242
243
244
245
246
247
248
249
250
    }

    // Try to convert html to xhtml
    HtmlCleaner cleaner = new HtmlCleaner();
    CleanerProperties xhtmlProperties = cleaner.getProperties();
    TagNode xhtmlNode = cleaner.clean(html);
    if (xhtmlNode == null) {
      logger.warn("Error creating well-formed document from page {}", resource);
      return;
    }
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. 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.