diff options
Diffstat (limited to 'ext/tidy/examples')
-rw-r--r-- | ext/tidy/examples/cleanhtml.php | 40 | ||||
-rw-r--r-- | ext/tidy/examples/dumpit.php | 94 | ||||
-rw-r--r-- | ext/tidy/examples/urlgrab.php | 63 |
3 files changed, 197 insertions, 0 deletions
diff --git a/ext/tidy/examples/cleanhtml.php b/ext/tidy/examples/cleanhtml.php new file mode 100644 index 0000000000..c949a0cfc2 --- /dev/null +++ b/ext/tidy/examples/cleanhtml.php @@ -0,0 +1,40 @@ +<?php + + /* + * cleanhtml.php + * + * A simple script to clean and repair HTML,XHTML,PHP,ASP,etc. documents + * if no file is provided, it reads from standard input. + * + * By: John Coggeshall <john@php.net> + * + * Usage: php cleanhtml.php [filename] + * + */ + + $tidy = tidy_create(); + + if(!isset($_SERVER['argv'][1])) { + $data = file_get_contents("php://stdin"); + tidy_parse_string($tidy, $data); + } else { + tidy_parse_file($tidy, $_SERVER['argv'][1]); + } + + tidy_clean_repair($tidy); + + if(tidy_warning_count($tidy) || + tidy_error_count($tidy)) { + + echo "\n\nThe following errors or warnings occured:\n"; + echo tidy_get_error_buffer($tidy); + echo "\n"; + } + + echo tidy_get_output($tidy); + +?> + + + +
\ No newline at end of file diff --git a/ext/tidy/examples/dumpit.php b/ext/tidy/examples/dumpit.php new file mode 100644 index 0000000000..46d307d704 --- /dev/null +++ b/ext/tidy/examples/dumpit.php @@ -0,0 +1,94 @@ +<?php + /* + * dumpit.php + * + * a command-line script which dumps the given HTML, PHP, ASP, XHTML, etc. + * file as it is represented in the document model. + * + * By: John Coggeshall <john@php.net> + * + * Usage; php dumpit.php <filename> + */ + + + $tidy = tidy_create(); + tidy_parse_file($tidy, $_SERVER['argv'][1]); + + /* Optionally you can do this here if you want to fix up the document */ + + /* tidy_clean_repair($tidy); */ + + $tree = tidy_get_root($tidy); + dump_tree($tree); + echo "\n"; + + function node_type($type) { + + switch($type) { + + case TIDY_NODETYPE_ROOT: return "Root Node"; + case TIDY_NODETYPE_DOCTYPE: return "DocType Node"; + case TIDY_NODETYPE_COMMENT: return "Comment Node"; + case TIDY_NODETYPE_PROCINS: return "ProcIns Node"; + case TIDY_NODETYPE_TEXT: return "Text Node"; + case TIDY_NODETYPE_START: return "Start Node"; + case TIDY_NODETYPE_END: return "End Node"; + case TIDY_NODETYPE_STARTEND: return "Start/End Node"; + case TIDY_NODETYPE_CDATA: return "CDATA Node"; + case TIDY_NODETYPE_SECTION: return "Section Node"; + case TIDY_NODETYPE_ASP: return "ASP Source Code Node"; + case TIDY_NODETYPE_PHP: return "PHP Source Code Node"; + case TIDY_NODETYPE_JSTE: return "JSTE Source Code"; + case TIDY_NODETYPE_XMLDECL: return "XML Declaration Node"; + default: return "Unknown Node"; + } + } + + function do_leaf($string, $indent) { + for($i = 0; $i < $indent; $i++) { + echo " "; + } + echo $string; + } + + function dump_tree($node, $indent = 0) { + if($node) { + /* Put something there if the node name is empty */ + $nodename = trim(strtoupper($node->name)); + $nodename = (empty($nodename)) ? "[EMPTY]" : $nodename; + + /* Generate the Node, and a pretty name for it */ + do_leaf(" + $nodename (".node_type($node->type).")\n", $indent); + + /* Check to see if this node is a text node. Text nodes are + generated by start/end tags and contain the text in between. + i.e. <B>foo</B> will create a text node with $node->value + equal to 'foo' */ + if($node->type == TIDY_NODETYPE_TEXT) { + do_leaf(" |\n", $indent); + do_leaf(" +---- Value: '{$node->value}'\n", $indent); + } + + /* Any attributes on this node? */ + if(count($node->attribs)) { + do_leaf(" |\n", $indent); + do_leaf(" +---- Attributes\n", $indent); + + /* Cycle through the attributes and display them and their values. */ + foreach($node->attribs as $attrib) { + do_leaf(" +--{$attrib->name}\n", $indent); + do_leaf(" | +-- Value: {$attrib->value}\n", $indent); + } + } + + /* Recurse along the children to generate the remaining nodes */ + if($node->has_children()) { + foreach($node->children as $child) { + dump_tree($child, $indent + 3); + } + } + } + } + + +?>
\ No newline at end of file diff --git a/ext/tidy/examples/urlgrab.php b/ext/tidy/examples/urlgrab.php new file mode 100644 index 0000000000..63a2875a79 --- /dev/null +++ b/ext/tidy/examples/urlgrab.php @@ -0,0 +1,63 @@ +<?php + + /* + * urlgrab.php + * + * A simple command-line utility to extract all of the URLS contained + * within <A HREF> tags from a document. + * + * By: John Coggeshall <john@php.net> + * + * Usage: php urlgrab.php <file> + * + */ + + /* Create a Tidy Resource */ + $tidy = tidy_create(); + + /* Parse the document */ + tidy_parse_file($tidy, $_SERVER['argv'][1]); + + /* Fix up the document */ + tidy_clean_repair($tidy); + + /* Get an object representing everything from the <HTML> tag in */ + $html = tidy_get_html($tidy); + + /* Traverse the document tree */ + print_r(get_links($html)); + + function get_links($node) { + $urls = array(); + + /* Check to see if we are on an <A> tag or not */ + if($node->id == TIDY_TAG_A) { + /* If we are, find the HREF attribute */ + $attrib = $node->get_attr_type(TIDY_ATTR_HREF); + if($attrib) { + /* Add the value of the HREF attrib to $urls */ + $urls[] = $attrib->value; + } + + } + + /* Are there any children? */ + if($node->has_children()) { + + /* Traverse down each child recursively */ + foreach($node->children as $child) { + + /* Append the results from recursion to $urls */ + foreach(get_links($child) as $url) { + + $urls[] = $url; + + } + + } + } + + return $urls; + } + +?>
\ No newline at end of file |