📄 extractorhtml.html
字号:
<A NAME="methods_inherited_from_class_java.lang.Object"><!-- --></A><TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY=""><TR BGCOLOR="#EEEEFF" CLASS="TableSubHeadingColor"><TH ALIGN="left"><B>Methods inherited from class java.lang.Object</B></TH></TR><TR BGCOLOR="white" CLASS="TableRowColor"><TD><CODE>clone, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait</CODE></TD></TR></TABLE> <P><!-- ============ FIELD DETAIL =========== --><A NAME="field_detail"><!-- --></A><TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY=""><TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor"><TH ALIGN="left" COLSPAN="1"><FONT SIZE="+2"><B>Field Detail</B></FONT></TH></TR></TABLE><A NAME="RELEVANT_TAG_EXTRACTOR"><!-- --></A><H3>RELEVANT_TAG_EXTRACTOR</H3><PRE>static final java.lang.String <B>RELEVANT_TAG_EXTRACTOR</B></PRE><DL><DL></DL></DL><HR><A NAME="MAX_ATTR_VAL_LENGTH"><!-- --></A><H3>MAX_ATTR_VAL_LENGTH</H3><PRE>static final int <B>MAX_ATTR_VAL_LENGTH</B></PRE><DL><DL></DL></DL><HR><A NAME="EACH_ATTRIBUTE_EXTRACTOR"><!-- --></A><H3>EACH_ATTRIBUTE_EXTRACTOR</H3><PRE>static final java.lang.String <B>EACH_ATTRIBUTE_EXTRACTOR</B></PRE><DL><DL></DL></DL><HR><A NAME="LIKELY_URI_PATH"><!-- --></A><H3>LIKELY_URI_PATH</H3><PRE>static final java.lang.String <B>LIKELY_URI_PATH</B></PRE><DL><DL><DT><B>See Also:</B><DD><A HREF="../../../../constant-values.html#org.archive.crawler.extractor.ExtractorHTML.LIKELY_URI_PATH">Constant Field Values</A></DL></DL><HR><A NAME="WHITESPACE"><!-- --></A><H3>WHITESPACE</H3><PRE>static final java.lang.String <B>WHITESPACE</B></PRE><DL><DL><DT><B>See Also:</B><DD><A HREF="../../../../constant-values.html#org.archive.crawler.extractor.ExtractorHTML.WHITESPACE">Constant Field Values</A></DL></DL><HR><A NAME="CLASSEXT"><!-- --></A><H3>CLASSEXT</H3><PRE>static final java.lang.String <B>CLASSEXT</B></PRE><DL><DL><DT><B>See Also:</B><DD><A HREF="../../../../constant-values.html#org.archive.crawler.extractor.ExtractorHTML.CLASSEXT">Constant Field Values</A></DL></DL><HR><A NAME="APPLET"><!-- --></A><H3>APPLET</H3><PRE>static final java.lang.String <B>APPLET</B></PRE><DL><DL><DT><B>See Also:</B><DD><A HREF="../../../../constant-values.html#org.archive.crawler.extractor.ExtractorHTML.APPLET">Constant Field Values</A></DL></DL><HR><A NAME="BASE"><!-- --></A><H3>BASE</H3><PRE>static final java.lang.String <B>BASE</B></PRE><DL><DL><DT><B>See Also:</B><DD><A HREF="../../../../constant-values.html#org.archive.crawler.extractor.ExtractorHTML.BASE">Constant Field Values</A></DL></DL><HR><A NAME="LINK"><!-- --></A><H3>LINK</H3><PRE>static final java.lang.String <B>LINK</B></PRE><DL><DL><DT><B>See Also:</B><DD><A HREF="../../../../constant-values.html#org.archive.crawler.extractor.ExtractorHTML.LINK">Constant Field Values</A></DL></DL><HR><A NAME="FRAME"><!-- --></A><H3>FRAME</H3><PRE>static final java.lang.String <B>FRAME</B></PRE><DL><DL><DT><B>See Also:</B><DD><A HREF="../../../../constant-values.html#org.archive.crawler.extractor.ExtractorHTML.FRAME">Constant Field Values</A></DL></DL><HR><A NAME="IFRAME"><!-- --></A><H3>IFRAME</H3><PRE>static final java.lang.String <B>IFRAME</B></PRE><DL><DL><DT><B>See Also:</B><DD><A HREF="../../../../constant-values.html#org.archive.crawler.extractor.ExtractorHTML.IFRAME">Constant Field Values</A></DL></DL><HR><A NAME="ATTR_TREAT_FRAMES_AS_EMBED_LINKS"><!-- --></A><H3>ATTR_TREAT_FRAMES_AS_EMBED_LINKS</H3><PRE>public static final java.lang.String <B>ATTR_TREAT_FRAMES_AS_EMBED_LINKS</B></PRE><DL><DL><DT><B>See Also:</B><DD><A HREF="../../../../constant-values.html#org.archive.crawler.extractor.ExtractorHTML.ATTR_TREAT_FRAMES_AS_EMBED_LINKS">Constant Field Values</A></DL></DL><HR><A NAME="ATTR_IGNORE_FORM_ACTION_URLS"><!-- --></A><H3>ATTR_IGNORE_FORM_ACTION_URLS</H3><PRE>public static final java.lang.String <B>ATTR_IGNORE_FORM_ACTION_URLS</B></PRE><DL><DL><DT><B>See Also:</B><DD><A HREF="../../../../constant-values.html#org.archive.crawler.extractor.ExtractorHTML.ATTR_IGNORE_FORM_ACTION_URLS">Constant Field Values</A></DL></DL><HR><A NAME="ATTR_OVERLY_EAGER_LINK_DETECTION"><!-- --></A><H3>ATTR_OVERLY_EAGER_LINK_DETECTION</H3><PRE>public static final java.lang.String <B>ATTR_OVERLY_EAGER_LINK_DETECTION</B></PRE><DL><DL><DT><B>See Also:</B><DD><A HREF="../../../../constant-values.html#org.archive.crawler.extractor.ExtractorHTML.ATTR_OVERLY_EAGER_LINK_DETECTION">Constant Field Values</A></DL></DL><HR><A NAME="ATTR_IGNORE_UNEXPECTED_HTML"><!-- --></A><H3>ATTR_IGNORE_UNEXPECTED_HTML</H3><PRE>public static final java.lang.String <B>ATTR_IGNORE_UNEXPECTED_HTML</B></PRE><DL><DL><DT><B>See Also:</B><DD><A HREF="../../../../constant-values.html#org.archive.crawler.extractor.ExtractorHTML.ATTR_IGNORE_UNEXPECTED_HTML">Constant Field Values</A></DL></DL><HR><A NAME="numberOfCURIsHandled"><!-- --></A><H3>numberOfCURIsHandled</H3><PRE>protected long <B>numberOfCURIsHandled</B></PRE><DL><DL></DL></DL><HR><A NAME="numberOfLinksExtracted"><!-- --></A><H3>numberOfLinksExtracted</H3><PRE>protected long <B>numberOfLinksExtracted</B></PRE><DL><DL></DL></DL><HR><A NAME="JAVASCRIPT_LIKELY_URI_EXTRACTOR"><!-- --></A><H3>JAVASCRIPT_LIKELY_URI_EXTRACTOR</H3><PRE>static final java.lang.String <B>JAVASCRIPT_LIKELY_URI_EXTRACTOR</B></PRE><DL><DL><DT><B>See Also:</B><DD><A HREF="../../../../constant-values.html#org.archive.crawler.extractor.ExtractorHTML.JAVASCRIPT_LIKELY_URI_EXTRACTOR">Constant Field Values</A></DL></DL><HR><A NAME="JAVASCRIPT"><!-- --></A><H3>JAVASCRIPT</H3><PRE>static final java.lang.String <B>JAVASCRIPT</B></PRE><DL><DL><DT><B>See Also:</B><DD><A HREF="../../../../constant-values.html#org.archive.crawler.extractor.ExtractorHTML.JAVASCRIPT">Constant Field Values</A></DL></DL><HR><A NAME="NON_HTML_PATH_EXTENSION"><!-- --></A><H3>NON_HTML_PATH_EXTENSION</H3><PRE>static final java.lang.String <B>NON_HTML_PATH_EXTENSION</B></PRE><DL><DL><DT><B>See Also:</B><DD><A HREF="../../../../constant-values.html#org.archive.crawler.extractor.ExtractorHTML.NON_HTML_PATH_EXTENSION">Constant Field Values</A></DL></DL><!-- ========= CONSTRUCTOR DETAIL ======== --><A NAME="constructor_detail"><!-- --></A><TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY=""><TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor"><TH ALIGN="left" COLSPAN="1"><FONT SIZE="+2"><B>Constructor Detail</B></FONT></TH></TR></TABLE><A NAME="ExtractorHTML(java.lang.String)"><!-- --></A><H3>ExtractorHTML</H3><PRE>public <B>ExtractorHTML</B>(java.lang.String name)</PRE><DL></DL><HR><A NAME="ExtractorHTML(java.lang.String, java.lang.String)"><!-- --></A><H3>ExtractorHTML</H3><PRE>public <B>ExtractorHTML</B>(java.lang.String name, java.lang.String description)</PRE><DL></DL><!-- ============ METHOD DETAIL ========== --><A NAME="method_detail"><!-- --></A><TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY=""><TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor"><TH ALIGN="left" COLSPAN="1"><FONT SIZE="+2"><B>Method Detail</B></FONT></TH></TR></TABLE><A NAME="processGeneralTag(org.archive.crawler.datamodel.CrawlURI, java.lang.CharSequence, java.lang.CharSequence)"><!-- --></A><H3>processGeneralTag</H3><PRE>protected void <B>processGeneralTag</B>(<A HREF="../../../../org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">CrawlURI</A> curi, java.lang.CharSequence element, java.lang.CharSequence cs)</PRE><DL><DD><DL></DL></DD><DD><DL></DL></DD>
⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -