1 <?xml version="1.0" encoding="ascii"?>
2 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
3 "DTD/xhtml1-transitional.dtd">
4 <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
6 <title>lxml.html.html5parser</title>
7 <link rel="stylesheet" href="epydoc.css" type="text/css" />
8 <script type="text/javascript" src="epydoc.js"></script>
11 <body bgcolor="white" text="black" link="blue" vlink="#204080"
13 <!-- ==================== NAVIGATION BAR ==================== -->
14 <table class="navbar" border="0" width="100%" cellpadding="0"
15 bgcolor="#a0c0ff" cellspacing="0">
18 <th> <a
19 href="lxml-module.html">Home</a> </th>
22 <th> <a
23 href="module-tree.html">Trees</a> </th>
26 <th> <a
27 href="identifier-index.html">Indices</a> </th>
30 <th> <a
31 href="help.html">Help</a> </th>
33 <!-- Project homepage -->
34 <th class="navbar" align="right" width="100%">
35 <table border="0" cellpadding="0" cellspacing="0">
36 <tr><th class="navbar" align="center"
37 ><a class="navbar" target="_top" href="/">lxml API</a></th>
41 <table width="100%" cellpadding="0" cellspacing="0">
44 <span class="breadcrumbs">
45 <a href="lxml-module.html">Package lxml</a> ::
46 <a href="lxml.html-module.html">Package html</a> ::
47 Module html5parser
51 <table cellpadding="0" cellspacing="0">
52 <!-- hide/show private -->
53 <tr><td align="right"><span class="options">[<a href="javascript:void(0);" class="privatelink"
54 onclick="toggle_private();">hide private</a>]</span></td></tr>
55 <tr><td align="right"><span class="options"
56 >[<a href="frames.html" target="_top">frames</a
57 >] | <a href="lxml.html.html5parser-module.html"
58 target="_top">no frames</a>]</span></td></tr>
63 <!-- ==================== MODULE DESCRIPTION ==================== -->
64 <h1 class="epydoc">Module html5parser</h1><p class="nomargin-top"><span class="codelink"><a href="lxml.html.html5parser-pysrc.html">source code</a></span></p>
65 An interface to html5lib that mimics the lxml.html interface.
67 <!-- ==================== CLASSES ==================== -->
68 <a name="section-Classes"></a>
69 <table class="summary" border="1" cellpadding="3"
70 cellspacing="0" width="100%" bgcolor="white">
71 <tr bgcolor="#70b0f0" class="table-header">
72 <td colspan="2" class="table-header">
73 <table border="0" cellpadding="0" cellspacing="0" width="100%">
75 <td align="left"><span class="table-header">Classes</span></td>
76 <td align="right" valign="top"
77 ><span class="options">[<a href="#section-Classes"
78 class="privatelink" onclick="toggle_private();"
79 >hide private</a>]</span></td>
85 <td width="15%" align="right" valign="top" class="summary">
86 <span class="summary-type"> </span>
87 </td><td class="summary">
88 <a href="lxml.html.html5parser.HTMLParser-class.html" class="summary-name">HTMLParser</a><br />
89 An html5lib HTML parser with lxml as tree.
93 <td width="15%" align="right" valign="top" class="summary">
94 <span class="summary-type"> </span>
95 </td><td class="summary">
96 <a href="lxml.html.html5parser.XHTMLParser-class.html" class="summary-name">XHTMLParser</a><br />
97 An html5lib XHTML Parser with lxml as tree.
101 <!-- ==================== FUNCTIONS ==================== -->
102 <a name="section-Functions"></a>
103 <table class="summary" border="1" cellpadding="3"
104 cellspacing="0" width="100%" bgcolor="white">
105 <tr bgcolor="#70b0f0" class="table-header">
106 <td colspan="2" class="table-header">
107 <table border="0" cellpadding="0" cellspacing="0" width="100%">
109 <td align="left"><span class="table-header">Functions</span></td>
110 <td align="right" valign="top"
111 ><span class="options">[<a href="#section-Functions"
112 class="privatelink" onclick="toggle_private();"
113 >hide private</a>]</span></td>
119 <td width="15%" align="right" valign="top" class="summary">
120 <span class="summary-type"> </span>
121 </td><td class="summary">
122 <table width="100%" cellpadding="0" cellspacing="0" border="0">
124 <td><span class="summary-sig"><a name="_find_tag"></a><span class="summary-sig-name">_find_tag</span>(<span class="summary-sig-arg">tree</span>,
125 <span class="summary-sig-arg">tag</span>)</span></td>
126 <td align="right" valign="top">
127 <span class="codelink"><a href="lxml.html.html5parser-pysrc.html#_find_tag">source code</a></span>
136 <td width="15%" align="right" valign="top" class="summary">
137 <span class="summary-type"> </span>
138 </td><td class="summary">
139 <table width="100%" cellpadding="0" cellspacing="0" border="0">
141 <td><span class="summary-sig"><a name="document_fromstring"></a><span class="summary-sig-name">document_fromstring</span>(<span class="summary-sig-arg">html</span>,
142 <span class="summary-sig-arg">guess_charset</span>=<span class="summary-sig-default">True</span>,
143 <span class="summary-sig-arg">parser</span>=<span class="summary-sig-default">None</span>)</span><br />
144 Parse a whole document into a string.</td>
145 <td align="right" valign="top">
146 <span class="codelink"><a href="lxml.html.html5parser-pysrc.html#document_fromstring">source code</a></span>
155 <td width="15%" align="right" valign="top" class="summary">
156 <span class="summary-type"> </span>
157 </td><td class="summary">
158 <table width="100%" cellpadding="0" cellspacing="0" border="0">
160 <td><span class="summary-sig"><a href="lxml.html.html5parser-module.html#fragments_fromstring" class="summary-sig-name">fragments_fromstring</a>(<span class="summary-sig-arg">html</span>,
161 <span class="summary-sig-arg">no_leading_text</span>=<span class="summary-sig-default">False</span>,
162 <span class="summary-sig-arg">guess_charset</span>=<span class="summary-sig-default">False</span>,
163 <span class="summary-sig-arg">parser</span>=<span class="summary-sig-default">None</span>)</span><br />
164 Parses several HTML elements, returning a list of elements.</td>
165 <td align="right" valign="top">
166 <span class="codelink"><a href="lxml.html.html5parser-pysrc.html#fragments_fromstring">source code</a></span>
175 <td width="15%" align="right" valign="top" class="summary">
176 <span class="summary-type"> </span>
177 </td><td class="summary">
178 <table width="100%" cellpadding="0" cellspacing="0" border="0">
180 <td><span class="summary-sig"><a href="lxml.html.html5parser-module.html#fragment_fromstring" class="summary-sig-name">fragment_fromstring</a>(<span class="summary-sig-arg">html</span>,
181 <span class="summary-sig-arg">create_parent</span>=<span class="summary-sig-default">False</span>,
182 <span class="summary-sig-arg">guess_charset</span>=<span class="summary-sig-default">False</span>,
183 <span class="summary-sig-arg">parser</span>=<span class="summary-sig-default">None</span>)</span><br />
184 Parses a single HTML element; it is an error if there is more than
185 one element, or if anything but whitespace precedes or follows the
187 <td align="right" valign="top">
188 <span class="codelink"><a href="lxml.html.html5parser-pysrc.html#fragment_fromstring">source code</a></span>
197 <td width="15%" align="right" valign="top" class="summary">
198 <span class="summary-type"> </span>
199 </td><td class="summary">
200 <table width="100%" cellpadding="0" cellspacing="0" border="0">
202 <td><span class="summary-sig"><a href="lxml.html.html5parser-module.html#fromstring" class="summary-sig-name">fromstring</a>(<span class="summary-sig-arg">html</span>,
203 <span class="summary-sig-arg">guess_charset</span>=<span class="summary-sig-default">True</span>,
204 <span class="summary-sig-arg">parser</span>=<span class="summary-sig-default">None</span>)</span><br />
205 Parse the html, returning a single element/document.</td>
206 <td align="right" valign="top">
207 <span class="codelink"><a href="lxml.html.html5parser-pysrc.html#fromstring">source code</a></span>
216 <td width="15%" align="right" valign="top" class="summary">
217 <span class="summary-type"> </span>
218 </td><td class="summary">
219 <table width="100%" cellpadding="0" cellspacing="0" border="0">
221 <td><span class="summary-sig"><a name="parse"></a><span class="summary-sig-name">parse</span>(<span class="summary-sig-arg">filename_url_or_file</span>,
222 <span class="summary-sig-arg">guess_charset</span>=<span class="summary-sig-default">True</span>,
223 <span class="summary-sig-arg">parser</span>=<span class="summary-sig-default">None</span>)</span><br />
224 Parse a filename, URL, or file-like object into an HTML document
225 tree. Note: this returns a tree, not an element. Use
226 <tt class="rst-docutils literal"><span class="pre">parse(...).getroot()</span></tt> to get the document root.</td>
227 <td align="right" valign="top">
228 <span class="codelink"><a href="lxml.html.html5parser-pysrc.html#parse">source code</a></span>
237 <!-- ==================== VARIABLES ==================== -->
238 <a name="section-Variables"></a>
239 <table class="summary" border="1" cellpadding="3"
240 cellspacing="0" width="100%" bgcolor="white">
241 <tr bgcolor="#70b0f0" class="table-header">
242 <td colspan="2" class="table-header">
243 <table border="0" cellpadding="0" cellspacing="0" width="100%">
245 <td align="left"><span class="table-header">Variables</span></td>
246 <td align="right" valign="top"
247 ><span class="options">[<a href="#section-Variables"
248 class="privatelink" onclick="toggle_private();"
249 >hide private</a>]</span></td>
255 <td width="15%" align="right" valign="top" class="summary">
256 <span class="summary-type"> </span>
257 </td><td class="summary">
258 <a name="xhtml_parser"></a><span class="summary-name">xhtml_parser</span> = <code title="XHTMLParser()">XHTMLParser()</code>
262 <td width="15%" align="right" valign="top" class="summary">
263 <span class="summary-type"> </span>
264 </td><td class="summary">
265 <a name="html_parser"></a><span class="summary-name">html_parser</span> = <code title="HTMLParser()">HTMLParser()</code>
269 <td width="15%" align="right" valign="top" class="summary">
270 <span class="summary-type"> </span>
271 </td><td class="summary">
272 <a name="__package__"></a><span class="summary-name">__package__</span> = <code title="'lxml.html'"><code class="variable-quote">'</code><code class="variable-string">lxml.html</code><code class="variable-quote">'</code></code>
276 <!-- ==================== FUNCTION DETAILS ==================== -->
277 <a name="section-FunctionDetails"></a>
278 <table class="details" border="1" cellpadding="3"
279 cellspacing="0" width="100%" bgcolor="white">
280 <tr bgcolor="#70b0f0" class="table-header">
281 <td colspan="2" class="table-header">
282 <table border="0" cellpadding="0" cellspacing="0" width="100%">
284 <td align="left"><span class="table-header">Function Details</span></td>
285 <td align="right" valign="top"
286 ><span class="options">[<a href="#section-FunctionDetails"
287 class="privatelink" onclick="toggle_private();"
288 >hide private</a>]</span></td>
294 <a name="fragments_fromstring"></a>
296 <table class="details" border="1" cellpadding="3"
297 cellspacing="0" width="100%" bgcolor="white">
299 <table width="100%" cellpadding="0" cellspacing="0" border="0">
300 <tr valign="top"><td>
301 <h3 class="epydoc"><span class="sig"><span class="sig-name">fragments_fromstring</span>(<span class="sig-arg">html</span>,
302 <span class="sig-arg">no_leading_text</span>=<span class="sig-default">False</span>,
303 <span class="sig-arg">guess_charset</span>=<span class="sig-default">False</span>,
304 <span class="sig-arg">parser</span>=<span class="sig-default">None</span>)</span>
306 </td><td align="right" valign="top"
307 ><span class="codelink"><a href="lxml.html.html5parser-pysrc.html#fragments_fromstring">source code</a></span>
311 <p>Parses several HTML elements, returning a list of elements.</p>
312 <p>The first item in the list may be a string. If no_leading_text is true,
313 then it will be an error if there is leading text, and it will always be
314 a list of only elements.</p>
315 <p>If <code class="link">guess_charset</code> is <code class="link">True</code> and the text was not unicode but a
316 bytestring, the <code class="link">chardet</code> library will perform charset guessing on the
322 <a name="fragment_fromstring"></a>
324 <table class="details" border="1" cellpadding="3"
325 cellspacing="0" width="100%" bgcolor="white">
327 <table width="100%" cellpadding="0" cellspacing="0" border="0">
328 <tr valign="top"><td>
329 <h3 class="epydoc"><span class="sig"><span class="sig-name">fragment_fromstring</span>(<span class="sig-arg">html</span>,
330 <span class="sig-arg">create_parent</span>=<span class="sig-default">False</span>,
331 <span class="sig-arg">guess_charset</span>=<span class="sig-default">False</span>,
332 <span class="sig-arg">parser</span>=<span class="sig-default">None</span>)</span>
334 </td><td align="right" valign="top"
335 ><span class="codelink"><a href="lxml.html.html5parser-pysrc.html#fragment_fromstring">source code</a></span>
339 <p>Parses a single HTML element; it is an error if there is more than
340 one element, or if anything but whitespace precedes or follows the
342 <p>If create_parent is true (or is a tag name) then a parent node
343 will be created to encapsulate the HTML in a single element. In
344 this case, leading or trailing text is allowed.</p>
349 <a name="fromstring"></a>
351 <table class="details" border="1" cellpadding="3"
352 cellspacing="0" width="100%" bgcolor="white">
354 <table width="100%" cellpadding="0" cellspacing="0" border="0">
355 <tr valign="top"><td>
356 <h3 class="epydoc"><span class="sig"><span class="sig-name">fromstring</span>(<span class="sig-arg">html</span>,
357 <span class="sig-arg">guess_charset</span>=<span class="sig-default">True</span>,
358 <span class="sig-arg">parser</span>=<span class="sig-default">None</span>)</span>
360 </td><td align="right" valign="top"
361 ><span class="codelink"><a href="lxml.html.html5parser-pysrc.html#fromstring">source code</a></span>
365 <p>Parse the html, returning a single element/document.</p>
366 <p>This tries to minimally parse the chunk of text, without knowing if it
367 is a fragment or a document.</p>
368 <p>base_url will set the document's base_url attribute (and the tree's docinfo.URL)</p>
374 <!-- ==================== NAVIGATION BAR ==================== -->
375 <table class="navbar" border="0" width="100%" cellpadding="0"
376 bgcolor="#a0c0ff" cellspacing="0">
379 <th> <a
380 href="lxml-module.html">Home</a> </th>
383 <th> <a
384 href="module-tree.html">Trees</a> </th>
387 <th> <a
388 href="identifier-index.html">Indices</a> </th>
391 <th> <a
392 href="help.html">Help</a> </th>
394 <!-- Project homepage -->
395 <th class="navbar" align="right" width="100%">
396 <table border="0" cellpadding="0" cellspacing="0">
397 <tr><th class="navbar" align="center"
398 ><a class="navbar" target="_top" href="/">lxml API</a></th>
402 <table border="0" cellpadding="0" cellspacing="0" width="100%%">
404 <td align="left" class="footer">
405 Generated by Epydoc 3.0.1 on Tue Jul 31 10:14:17 2012
407 <td align="right" class="footer">
408 <a target="mainFrame" href="http://epydoc.sourceforge.net"
409 >http://epydoc.sourceforge.net</a>
414 <script type="text/javascript">
416 // Private objects are initially displayed (because if
417 // javascript is turned off then we want them to be
418 // visible); but by default, we want to hide them. So hide
419 // them unless we have a cookie that says to show them.