📄 libxml2-htmlparser.html
字号:
<?xml version="1.0" encoding="UTF-8"?><html> <head> <meta http-equiv="Content-Type" content="text/html; charset=UTF-8"/> <title>HTMLparser: interface for an HTML 4.0 non-verifying parser</title> <meta name="generator" content="Libxml2 devhelp stylesheet"/> <link rel="start" href="index.html" title="libxml2 Reference Manual"/> <link rel="up" href="general.html" title="API"/> <link rel="stylesheet" href="style.css" type="text/css"/> <link rel="chapter" href="general.html" title="API"/> </head> <body bgcolor="white" text="black" link="#0000FF" vlink="#840084" alink="#0000FF"> <table class="navigation" width="100%" summary="Navigation header" cellpadding="2" cellspacing="2"> <tr valign="middle"> <td> <a accesskey="p" href="libxml2-DOCBparser.html"> <img src="left.png" width="24" height="24" border="0" alt="Prev"/> </a> </td> <td> <a accesskey="u" href="general.html"> <img src="up.png" width="24" height="24" border="0" alt="Up"/> </a> </td> <td> <a accesskey="h" href="index.html"> <img src="home.png" width="24" height="24" border="0" alt="Home"/> </a> </td> <td> <a accesskey="n" href="libxml2-HTMLtree.html"> <img src="right.png" width="24" height="24" border="0" alt="Next"/> </a> </td> <th width="100%" align="center">libxml2 Reference Manual</th> </tr> </table> <h2> <span class="refentrytitle">HTMLparser</span> </h2> <p>HTMLparser - interface for an HTML 4.0 non-verifying parser</p> <p>this module implements an HTML 4.0 non-verifying parser with API compatible with the XML parser ones. It should be able to parse "real world" HTML, even if severely broken from a specification point of view. </p> <p>Author(s): Daniel Veillard </p> <div class="refsynopsisdiv"> <h2>Synopsis</h2> <pre class="synopsis">#define <a href="#htmlDefaultSubelement">htmlDefaultSubelement</a>(elt);#define <a href="#htmlElementAllowedHereDesc">htmlElementAllowedHereDesc</a>(parent, elt);#define <a href="#htmlRequiredAttrs">htmlRequiredAttrs</a>(elt);typedef <a href="libxml2-parser.html#xmlParserNodeInfo">xmlParserNodeInfo</a> <a href="#htmlParserNodeInfo">htmlParserNodeInfo</a>;typedef <a href="libxml2-tree.html#xmlParserInput">xmlParserInput</a> <a href="#htmlParserInput">htmlParserInput</a>;typedef <a href="libxml2-tree.html#xmlParserCtxtPtr">xmlParserCtxtPtr</a> <a href="#htmlParserCtxtPtr">htmlParserCtxtPtr</a>;typedef struct _htmlEntityDesc <a href="#htmlEntityDesc">htmlEntityDesc</a>;typedef <a href="libxml2-tree.html#xmlDocPtr">xmlDocPtr</a> <a href="#htmlDocPtr">htmlDocPtr</a>;typedef <a href="libxml2-tree.html#xmlSAXHandlerPtr">xmlSAXHandlerPtr</a> <a href="#htmlSAXHandlerPtr">htmlSAXHandlerPtr</a>;typedef enum <a href="#htmlStatus">htmlStatus</a>;typedef <a href="libxml2-tree.html#xmlNodePtr">xmlNodePtr</a> <a href="#htmlNodePtr">htmlNodePtr</a>;typedef <a href="libxml2-HTMLparser.html#htmlElemDesc">htmlElemDesc</a> * <a href="#htmlElemDescPtr">htmlElemDescPtr</a>;typedef struct _htmlElemDesc <a href="#htmlElemDesc">htmlElemDesc</a>;typedef <a href="libxml2-tree.html#xmlSAXHandler">xmlSAXHandler</a> <a href="#htmlSAXHandler">htmlSAXHandler</a>;typedef <a href="libxml2-tree.html#xmlParserInputPtr">xmlParserInputPtr</a> <a href="#htmlParserInputPtr">htmlParserInputPtr</a>;typedef enum <a href="#htmlParserOption">htmlParserOption</a>;typedef <a href="libxml2-HTMLparser.html#htmlEntityDesc">htmlEntityDesc</a> * <a href="#htmlEntityDescPtr">htmlEntityDescPtr</a>;typedef <a href="libxml2-tree.html#xmlParserCtxt">xmlParserCtxt</a> <a href="#htmlParserCtxt">htmlParserCtxt</a>;int <a href="#htmlIsScriptAttribute">htmlIsScriptAttribute</a> (const <a href="libxml2-xmlstring.html#xmlChar">xmlChar</a> * name);int <a href="#htmlHandleOmittedElem">htmlHandleOmittedElem</a> (int val);<a href="libxml2-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> <a href="#htmlReadFd">htmlReadFd</a> (int fd, <br/> const char * URL, <br/> const char * encoding, <br/> int options);<a href="libxml2-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> <a href="#htmlReadIO">htmlReadIO</a> (<a href="libxml2-xmlIO.html#xmlInputReadCallback">xmlInputReadCallback</a> ioread, <br/> <a href="libxml2-xmlIO.html#xmlInputCloseCallback">xmlInputCloseCallback</a> ioclose, <br/> void * ioctx, <br/> const char * URL, <br/> const char * encoding, <br/> int options);<a href="libxml2-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> <a href="#htmlParseFile">htmlParseFile</a> (const char * filename, <br/> const char * encoding);<a href="libxml2-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> <a href="#htmlCtxtReadDoc">htmlCtxtReadDoc</a> (<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt, <br/> const <a href="libxml2-xmlstring.html#xmlChar">xmlChar</a> * cur, <br/> const char * URL, <br/> const char * encoding, <br/> int options);int <a href="#htmlAutoCloseTag">htmlAutoCloseTag</a> (<a href="libxml2-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> doc, <br/> const <a href="libxml2-xmlstring.html#xmlChar">xmlChar</a> * name, <br/> <a href="libxml2-HTMLparser.html#htmlNodePtr">htmlNodePtr</a> elem);int <a href="#htmlParseChunk">htmlParseChunk</a> (<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt, <br/> const char * chunk, <br/> int size, <br/> int terminate);const <a href="libxml2-HTMLparser.html#htmlElemDesc">htmlElemDesc</a> * <a href="#htmlTagLookup">htmlTagLookup</a> (const <a href="libxml2-xmlstring.html#xmlChar">xmlChar</a> * tag);<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> <a href="#htmlCreateMemoryParserCtxt">htmlCreateMemoryParserCtxt</a> (const char * buffer, <br/> int size);void <a href="#htmlCtxtReset">htmlCtxtReset</a> (<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt);int <a href="#htmlElementAllowedHere">htmlElementAllowedHere</a> (const <a href="libxml2-HTMLparser.html#htmlElemDesc">htmlElemDesc</a> * parent, <br/> const <a href="libxml2-xmlstring.html#xmlChar">xmlChar</a> * elt);<a href="libxml2-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> <a href="#htmlCtxtReadIO">htmlCtxtReadIO</a> (<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt, <br/> <a href="libxml2-xmlIO.html#xmlInputReadCallback">xmlInputReadCallback</a> ioread, <br/> <a href="libxml2-xmlIO.html#xmlInputCloseCallback">xmlInputCloseCallback</a> ioclose, <br/> void * ioctx, <br/> const char * URL, <br/> const char * encoding, <br/> int options);<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> <a href="#htmlCreatePushParserCtxt">htmlCreatePushParserCtxt</a> (<a href="libxml2-HTMLparser.html#htmlSAXHandlerPtr">htmlSAXHandlerPtr</a> sax, <br/> void * user_data, <br/> const char * chunk, <br/> int size, <br/> const char * filename, <br/> <a href="libxml2-encoding.html#xmlCharEncoding">xmlCharEncoding</a> enc);<a href="libxml2-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> <a href="#htmlReadMemory">htmlReadMemory</a> (const char * buffer, <br/> int size, <br/> const char * URL, <br/> const char * encoding, <br/> int options);int <a href="#htmlIsAutoClosed">htmlIsAutoClosed</a> (<a href="libxml2-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> doc, <br/> <a href="libxml2-HTMLparser.html#htmlNodePtr">htmlNodePtr</a> elem);int <a href="#htmlParseCharRef">htmlParseCharRef</a> (<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt);<a href="libxml2-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> <a href="#htmlReadDoc">htmlReadDoc</a> (const <a href="libxml2-xmlstring.html#xmlChar">xmlChar</a> * cur, <br/> const char * URL, <br/> const char * encoding, <br/> int options);int <a href="#htmlEncodeEntities">htmlEncodeEntities</a> (unsigned char * out, <br/> int * outlen, <br/> const unsigned char * in, <br/> int * inlen, <br/> int quoteChar);<a href="libxml2-HTMLparser.html#htmlStatus">htmlStatus</a> <a href="#htmlNodeStatus">htmlNodeStatus</a> (const <a href="libxml2-HTMLparser.html#htmlNodePtr">htmlNodePtr</a> node, <br/> int legacy);<a href="libxml2-HTMLparser.html#htmlStatus">htmlStatus</a> <a href="#htmlAttrAllowed">htmlAttrAllowed</a> (const <a href="libxml2-HTMLparser.html#htmlElemDesc">htmlElemDesc</a> * elt, <br/> const <a href="libxml2-xmlstring.html#xmlChar">xmlChar</a> * attr, <br/> int legacy);<a href="libxml2-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> <a href="#htmlSAXParseFile">htmlSAXParseFile</a> (const char * filename, <br/> const char * encoding, <br/> <a href="libxml2-HTMLparser.html#htmlSAXHandlerPtr">htmlSAXHandlerPtr</a> sax, <br/> void * userData);const <a href="libxml2-HTMLparser.html#htmlEntityDesc">htmlEntityDesc</a> * <a href="#htmlParseEntityRef">htmlParseEntityRef</a> (<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt, <br/> const <a href="libxml2-xmlstring.html#xmlChar">xmlChar</a> ** str);<a href="libxml2-HTMLparser.html#htmlStatus">htmlStatus</a> <a href="#htmlElementStatusHere">htmlElementStatusHere</a> (const <a href="libxml2-HTMLparser.html#htmlElemDesc">htmlElemDesc</a> * parent, <br/> const <a href="libxml2-HTMLparser.html#htmlElemDesc">htmlElemDesc</a> * elt);const <a href="libxml2-HTMLparser.html#htmlEntityDesc">htmlEntityDesc</a> * <a href="#htmlEntityValueLookup">htmlEntityValueLookup</a> (unsigned int value);void <a href="#htmlParseElement">htmlParseElement</a> (<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt);int <a href="#UTF8ToHtml">UTF8ToHtml</a> (unsigned char * out, <br/> int * outlen, <br/> const unsigned char * in, <br/> int * inlen);const <a href="libxml2-HTMLparser.html#htmlEntityDesc">htmlEntityDesc</a> * <a href="#htmlEntityLookup">htmlEntityLookup</a> (const <a href="libxml2-xmlstring.html#xmlChar">xmlChar</a> * name);void <a href="#htmlFreeParserCtxt">htmlFreeParserCtxt</a> (<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt);<a href="libxml2-HTMLparser.html#htmlDocPtr">htmlDocPtr</a> <a href="#htmlCtxtReadMemory">htmlCtxtReadMemory</a> (<a href="libxml2-HTMLparser.html#htmlParserCtxtPtr">htmlParserCtxtPtr</a> ctxt, <br/> const char * buffer, <br/> int size, <br/> const char * URL, <br/> const char * encoding, <br/> int options);⌨️ 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 + -