Package org.htmlparser

Examples of org.htmlparser.Tag

342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
            NodeList links = nodelist.extractAllNodesThatMatch(filter);
            for (NodeIterator ni = links.elements(); ni.hasMoreNodes(); ) {
                Node node = ni.nextNode();
                if (node instanceof Tag) {
                    boolean got = false;
                    Tag tag = (Tag) node;
                    String src = tag.getAttribute("src");
                    if (src != null) {
                        processLink(base, src);
                        got = true;
                    }
                    String href = tag.getAttribute("href");
                    if (href != null) {
                        processLink(base, href);
                        got = true;
                    }
                    if (!got) {
View Full Code Here
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
            Node node = e.nextNode();
            // a url is always in a Tag.
            if (!(node instanceof Tag)) {
                continue;
            }
            Tag tag = (Tag) node;
            String tagname=tag.getTagName();
            String binUrlStr = null;

            // first we check to see if body tag has a
            // background set
            if (tag instanceof BodyTag) {
                binUrlStr = tag.getAttribute(ATT_BACKGROUND);
            } else if (tag instanceof BaseHrefTag) {
                BaseHrefTag baseHref = (BaseHrefTag) tag;
                String baseref = baseHref.getBaseUrl();
                try {
                    if (!baseref.equals(""))// Bugzilla 30713
                    {
                        baseUrl.url = ConversionUtils.makeRelativeURL(baseUrl.url, baseHref.getBaseUrl());
                    }
                } catch (MalformedURLException e1) {
                    throw new HTMLParseException(e1);
                }
            } else if (tag instanceof ImageTag) {
                ImageTag image = (ImageTag) tag;
                binUrlStr = image.getImageURL();
            } else if (tag instanceof AppletTag) {
                // look for applets

                // This will only work with an Applet .class file.
                // Ideally, this should be upgraded to work with Objects (IE)
                // and archives (.jar and .zip) files as well.
                AppletTag applet = (AppletTag) tag;
                binUrlStr = applet.getAppletClass();
            } else if (tag instanceof InputTag) {
                // we check the input tag type for image
                if (ATT_IS_IMAGE.equalsIgnoreCase(tag.getAttribute(ATT_TYPE))) {
                    // then we need to download the binary
                    binUrlStr = tag.getAttribute(ATT_SRC);
                }
            } else if (tag instanceof LinkTag) {
                LinkTag link = (LinkTag) tag;
                if (link.getChild(0) instanceof ImageTag) {
                    ImageTag img = (ImageTag) link.getChild(0);
                    binUrlStr = img.getImageURL();
                }
            } else if (tag instanceof ScriptTag) {
                binUrlStr = tag.getAttribute(ATT_SRC);
            } else if (tag instanceof FrameTag) {
                binUrlStr = tag.getAttribute(ATT_SRC);
            } else if (tagname.equalsIgnoreCase(TAG_EMBED)
                || tagname.equalsIgnoreCase(TAG_BGSOUND)){
                binUrlStr = tag.getAttribute(ATT_SRC);
            } else if (tagname.equalsIgnoreCase(TAG_LINK)) {
                // Putting the string first means it works even if the attribute is null
                if (STYLESHEET.equalsIgnoreCase(tag.getAttribute(ATT_REL))) {
                    binUrlStr = tag.getAttribute(ATT_HREF);
                }
            } else {
                binUrlStr = tag.getAttribute(ATT_BACKGROUND);
            }

            if (binUrlStr != null) {
                urls.addURL(binUrlStr, baseUrl.url);
            }

            // Now look for URLs in the STYLE attribute
            String styleTagStr = tag.getAttribute(ATT_STYLE);
            if(styleTagStr != null) {
                HtmlParsingUtils.extractStyleURLs(baseUrl.url, urls, styleTagStr);
            }

            // second, if the tag was a composite tag,
View Full Code Here
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
            Node node = e.nextNode();
            // a url is always in a Tag.
            if (!(node instanceof Tag)) {
                continue;
            }
            Tag tag = (Tag) node;

            // Only check form tags
            if (tag instanceof FormTag) {
                // Find the action / form url
                String action = tag.getAttribute("action");
                String acceptCharSet = tag.getAttribute("accept-charset");
                if(action != null && action.length() > 0) {
                    // We use the page encoding where the form resides, as the
                    // default encoding for the form
                    String formCharSet = pageEncoding;
                    // Check if we found an accept-charset attribute on the form
View Full Code Here
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
            Node node = e.nextNode();
            // a url is always in a Tag.
            if (!(node instanceof Tag)) {
                continue;
            }
            Tag tag = (Tag) node;

            // Only check form tags
            if (tag instanceof FormTag) {
                // Find the action / form url
                String action = tag.getAttribute("action");
                String acceptCharSet = tag.getAttribute("accept-charset");
                if(action != null && action.length() > 0) {
                    // We use the page encoding where the form resides, as the
                    // default encoding for the form
                    String formCharSet = pageEncoding;
                    // Check if we found an accept-charset attribute on the form
View Full Code Here
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
            Node node = e.nextNode();
            // a url is always in a Tag.
            if (!(node instanceof Tag)) {
                continue;
            }
            Tag tag = (Tag) node;
            String tagname=tag.getTagName();
            String binUrlStr = null;

            // first we check to see if body tag has a
            // background set
            if (tag instanceof BodyTag) {
                binUrlStr = tag.getAttribute(ATT_BACKGROUND);
            } else if (tag instanceof BaseHrefTag) {
                BaseHrefTag baseHref = (BaseHrefTag) tag;
                String baseref = baseHref.getBaseUrl().toString();
                try {
                    if (!baseref.equals(""))// Bugzilla 30713
                    {
                        baseUrl.url = new URL(baseUrl.url, baseHref.getBaseUrl());
                    }
                } catch (MalformedURLException e1) {
                    throw new HTMLParseException(e1);
                }
            } else if (tag instanceof ImageTag) {
                ImageTag image = (ImageTag) tag;
                binUrlStr = image.getImageURL();
            } else if (tag instanceof AppletTag) {
            // look for applets

            // This will only work with an Applet .class file.
            // Ideally, this should be upgraded to work with Objects (IE)
            // and archives (.jar and .zip) files as well.
                AppletTag applet = (AppletTag) tag;
                binUrlStr = applet.getAppletClass();
            } else if (tag instanceof InputTag) {
                // we check the input tag type for image
                if (ATT_IS_IMAGE.equalsIgnoreCase(tag.getAttribute(ATT_TYPE))) {
                    // then we need to download the binary
                    binUrlStr = tag.getAttribute(ATT_SRC);
                }
            } else if (tag instanceof LinkTag) {
                LinkTag link = (LinkTag) tag;
                if (link.getChild(0) instanceof ImageTag) {
                    ImageTag img = (ImageTag) link.getChild(0);
                    binUrlStr = img.getImageURL();
                }
            } else if (tag instanceof ScriptTag) {
                binUrlStr = tag.getAttribute(ATT_SRC);
            } else if (tag instanceof FrameTag) {
                binUrlStr = tag.getAttribute(ATT_SRC);
            } else if (tagname.equalsIgnoreCase(TAG_EMBED)
                || tagname.equalsIgnoreCase(TAG_BGSOUND)){
                binUrlStr = tag.getAttribute(ATT_SRC); 
            } else if (tagname.equalsIgnoreCase(TAG_LINK)) {
                // Putting the string first means it works even if the attribute is null
                if (STYLESHEET.equalsIgnoreCase(tag.getAttribute(ATT_REL))) {
                    binUrlStr = tag.getAttribute(ATT_HREF);
                }
            } else {
                binUrlStr = tag.getAttribute(ATT_BACKGROUND);
            }

            if (binUrlStr != null) {
                urls.addURL(binUrlStr, baseUrl.url);
            }

            // Now look for URLs in the STYLE attribute
            String styleTagStr = tag.getAttribute(ATT_STYLE);
            if(styleTagStr != null) {
              HtmlParsingUtils.extractStyleURLs(baseUrl.url, urls, styleTagStr);
            }

            // second, if the tag was a composite tag,
View Full Code Here
62
63
64
65
66
67
68
69
70
71
72
    int begin = getBeginOffset(tag);
    int end = begin;
    if (tagClosed) {
      end = getEndOffset(tag);
    } else {
      Tag endTag = tag.getEndTag();
      if (endTag != null) {
        end = getEndOffset(endTag);
      } else {
        end = getEndOffset(tag);
        tagStillOpen = true;
View Full Code Here
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
            Node node = e.nextNode();
            // a url is always in a Tag.
            if (!(node instanceof Tag)) {
                continue;
            }
            Tag tag = (Tag) node;
            String tagname=tag.getTagName();
            String binUrlStr = null;

            // first we check to see if body tag has a
            // background set
            if (tag instanceof BodyTag) {
                binUrlStr = tag.getAttribute(ATT_BACKGROUND);
            } else if (tag instanceof BaseHrefTag) {
                BaseHrefTag baseHref = (BaseHrefTag) tag;
                String baseref = baseHref.getBaseUrl();
                try {
                    if (!baseref.equals(""))// Bugzilla 30713
                    {
                        baseUrl.url = ConversionUtils.makeRelativeURL(baseUrl.url, baseref);
                    }
                } catch (MalformedURLException e1) {
                    throw new HTMLParseException(e1);
                }
            } else if (tag instanceof ImageTag) {
                ImageTag image = (ImageTag) tag;
                binUrlStr = image.getImageURL();
            } else if (tag instanceof AppletTag) {
                // look for applets

                // This will only work with an Applet .class file.
                // Ideally, this should be upgraded to work with Objects (IE)
                // and archives (.jar and .zip) files as well.
                AppletTag applet = (AppletTag) tag;
                binUrlStr = applet.getAppletClass();
            } else if (tag instanceof ObjectTag) {
                // look for Objects
                ObjectTag applet = (ObjectTag) tag;
                String data = applet.getAttribute(ATT_CODEBASE);
                if(!StringUtils.isEmpty(data)) {
                    binUrlStr = data;              
                }
               
                data = applet.getAttribute(ATT_DATA);
                if(!StringUtils.isEmpty(data)) {
                    binUrlStr = data;                   
                }
               
            } else if (tag instanceof InputTag) {
                // we check the input tag type for image
                if (ATT_IS_IMAGE.equalsIgnoreCase(tag.getAttribute(ATT_TYPE))) {
                    // then we need to download the binary
                    binUrlStr = tag.getAttribute(ATT_SRC);
                }
            } else if (tag instanceof ScriptTag) {
                binUrlStr = tag.getAttribute(ATT_SRC);
                // Bug 51750
            } else if (tag instanceof FrameTag || tagname.equalsIgnoreCase(TAG_IFRAME)) {
                binUrlStr = tag.getAttribute(ATT_SRC);
            } else if (tagname.equalsIgnoreCase(TAG_EMBED)
                || tagname.equalsIgnoreCase(TAG_BGSOUND)){
                binUrlStr = tag.getAttribute(ATT_SRC);
            } else if (tagname.equalsIgnoreCase(TAG_LINK)) {
                // Putting the string first means it works even if the attribute is null
                if (STYLESHEET.equalsIgnoreCase(tag.getAttribute(ATT_REL))) {
                    binUrlStr = tag.getAttribute(ATT_HREF);
                }
            } else {
                binUrlStr = tag.getAttribute(ATT_BACKGROUND);
            }

            if (binUrlStr != null) {
                urls.addURL(binUrlStr, baseUrl.url);
            }

            // Now look for URLs in the STYLE attribute
            String styleTagStr = tag.getAttribute(ATT_STYLE);
            if(styleTagStr != null) {
                HtmlParsingUtils.extractStyleURLs(baseUrl.url, urls, styleTagStr);
            }

            // second, if the tag was a composite tag,
View Full Code Here
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
     * @return <code>true</code> if the node has the attribute
     * (and value if that is being checked too), <code>false</code> otherwise.
     */
    public boolean accept (Node node)
    {
        Tag tag;
        Attribute attribute;
        boolean ret;

        ret = false;
        if (node instanceof Tag)
        {
            tag = (Tag)node;
            attribute = tag.getAttributeEx (mAttribute);
            ret = null != attribute;
            if (ret && (null != mValue))
                ret = mValue.equals (attribute.getValue ());
        }

View Full Code Here
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
    protected void doSAX (Node node)
        throws
            ParserException,
            SAXException
    {
        Tag tag;
        Tag end;

        if (node instanceof Remark)
        {
            String text = mParser.getLexer ().getPage ().getText (node.getStartPosition (), node.getEndPosition ());
            mContentHandler.ignorableWhitespace (text.toCharArray (), 0, text.length ());
        }
        else if (node instanceof Text)
        {
            String text = mParser.getLexer ().getPage ().getText (node.getStartPosition (), node.getEndPosition ());
            mContentHandler.characters (text.toCharArray (), 0, text.length ());
        }
        else if (node instanceof Tag)
        {
            tag = (Tag)node;
            if (mNameSpaces)
                mSupport.processName (tag.getTagName (), mParts, false);
            else
            {
                mParts[0] = "";
                mParts[1] = "";
            }
            if (mNameSpacePrefixes)
                mParts[2] = tag.getTagName ();
            else if (mNameSpaces)
                mParts[2] = "";
            else
                mParts[2] = tag.getTagName ();

            mContentHandler.startElement (
                mParts[0], // uri
                mParts[1], // local
                mParts[2], // raw
                new Attributes (tag, mSupport, mParts));
            NodeList children = tag.getChildren ();
            if (null != children)
                for (int i = 0; i < children.size (); i++)
                    doSAX (children.elementAt (i));
            end = tag.getEndTag ();
            if (null != end)
            {
                if (mNameSpaces)
                    mSupport.processName (end.getTagName (), mParts, false);
                else
                {
                    mParts[0] = "";
                    mParts[1] = "";
                }
                if (mNameSpacePrefixes)
                    mParts[2] = end.getTagName ();
                else if (mNameSpaces)
                    mParts[2] = "";
                else
                    mParts[2] = end.getTagName ();
                mContentHandler.endElement (
                    mParts[0], // uri
                    mParts[1], // local
                    mParts[2]); // raw
            }
View Full Code Here
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
     * @return The next node in the HTML stream, or null if there are no more nodes.
     * @exception ParserException If an unrecoverable error occurs.
     */
    public Node nextNode () throws ParserException
    {
        Tag tag;
        Scanner scanner;
        NodeList stack;
        Node ret;

        try
        {
            ret = mLexer.nextNode ();
            if (null != ret)
            {
                // kick off recursion for the top level node
                if (ret instanceof Tag)
                {
                    tag = (Tag)ret;
                    if (!tag.isEndTag ())
                    {
                        // now recurse if there is a scanner for this type of tag
                        scanner = tag.getThisScanner ();
                        if (null != scanner)
                        {
                            stack = new NodeList ();
                            ret = scanner.scan (tag, mLexer, stack);
                        }
View Full Code Here
TOP

Related Classes of org.htmlparser.Tag

  • com.almilli.htmlparser.CssClassFilter
  • com.almilli.htmlparser.HasAttributeRegexFilter
  • com.brewtab.ircbot.applets.TextsFromLastNightApplet
  • com.lanyuan.util.HttpClientUtils
  • fitnesse.fixtures.PageDriver$HasAttributePrefixFilter
  • fitnesse.testsystems.slim.HtmlTable
  • fitnesse.testsystems.slim.HtmlTable$Row
  • fitnesse.util.HtmlParserTools
  • name.abuchen.portfolio.online.DestatisCPIFeed$Visitor
  • org.apache.jmeter.protocol.http.parser.HtmlParserHTMLParser
    • 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.