diff options
author | Jonas John <jonas@jonasjohn.de> | 2012-02-09 13:42:59 +0400 |
---|---|---|
committer | Jonas John <jonas@jonasjohn.de> | 2012-02-09 13:42:59 +0400 |
commit | a44eee9e97a7851596e26de2c9e53fa569df7389 (patch) | |
tree | 27904364de31aad4ddfab8bc006261fc6a382382 |
Initial commit (version 0.5 of May 2006)
-rwxr-xr-x | examples/demo_01.php | 46 | ||||
-rwxr-xr-x | examples/demo_02.php | 38 | ||||
-rwxr-xr-x | examples/demo_03.php | 37 | ||||
-rwxr-xr-x | examples/demo_04.php | 36 | ||||
-rwxr-xr-x | examples/demo_05.php | 38 | ||||
-rwxr-xr-x | examples/demo_06.php | 40 | ||||
-rwxr-xr-x | examples/demo_07.php | 37 | ||||
-rwxr-xr-x | examples/demo_08.php | 86 | ||||
-rwxr-xr-x | examples/demo_09.php | 51 | ||||
-rwxr-xr-x | examples/demo_10.php | 55 | ||||
-rwxr-xr-x | examples/demo_11.php | 36 | ||||
-rwxr-xr-x | examples/demo_12.php | 44 | ||||
-rwxr-xr-x | examples/demo_data.htm | 195 | ||||
-rwxr-xr-x | examples/demo_xml.xml | 8 | ||||
-rwxr-xr-x | examples/query_examples.txt | 51 | ||||
-rwxr-xr-x | htmlsql.class.php | 677 | ||||
-rwxr-xr-x | readme.txt | 67 | ||||
-rwxr-xr-x | readme_german.txt | 85 | ||||
-rwxr-xr-x | snoopy.class.php | 1257 |
19 files changed, 2884 insertions, 0 deletions
diff --git a/examples/demo_01.php b/examples/demo_01.php new file mode 100755 index 0000000..a168b82 --- /dev/null +++ b/examples/demo_01.php @@ -0,0 +1,46 @@ +<?php
+
+ /*
+ ** htmlSQL - Example 1
+ **
+ ** Shows a simple query
+ */
+
+ include_once("../snoopy.class.php");
+ include_once("../htmlsql.class.php");
+
+ $wsql = new htmlsql();
+
+ // connect to a URL
+ if (!$wsql->connect('url', 'http://codedump.jonasjohn.de/')){
+ print 'Error while connecting: ' . $wsql->error;
+ exit;
+ }
+
+ /* execute a query:
+
+ This query extracts all links with the classname = nav_item
+ */
+ if (!$wsql->query('SELECT * FROM a WHERE $class == "nav_item"')){
+ print "Query error: " . $wsql->error;
+ exit;
+ }
+
+ // show results:
+ foreach($wsql->fetch_array() as $row){
+
+ print_r($row);
+
+ /*
+ $row is an array and looks like this:
+ Array ( + [href] => /feedback.htm + [class] => nav_item + [tagname] => a + [text] => Feedback + )
+ */
+
+ }
+
+?>
\ No newline at end of file diff --git a/examples/demo_02.php b/examples/demo_02.php new file mode 100755 index 0000000..b660af1 --- /dev/null +++ b/examples/demo_02.php @@ -0,0 +1,38 @@ +<?php
+
+ /*
+ ** htmlSQL - Example 2
+ **
+ ** Shows a simple query and the "href as url" usage
+ */
+
+ include_once("../snoopy.class.php");
+ include_once("../htmlsql.class.php");
+
+ $wsql = new htmlsql();
+
+ // connect to a file
+ if (!$wsql->connect('file', 'demo_data.htm')){
+ print 'Error while connecting: ' . $wsql->error;
+ exit;
+ }
+
+ /* execute a query:
+
+ This query extracts all links from the document
+ and just returns href (as url) and text
+ */
+ if (!$wsql->query('SELECT href as url, text FROM a')){
+ print "Query error: " . $wsql->error;
+ exit;
+ }
+
+ // show results:
+ foreach($wsql->fetch_array() as $row){
+
+ print "Link-URL: " . $row['url'] . "\n";
+ print "Link-Text: " . trim($row['text']) . "\n\n";
+
+ }
+
+?>
\ No newline at end of file diff --git a/examples/demo_03.php b/examples/demo_03.php new file mode 100755 index 0000000..dc05e19 --- /dev/null +++ b/examples/demo_03.php @@ -0,0 +1,37 @@ +<?php
+
+ /*
+ ** htmlSQL - Example 3
+ **
+ ** Shows how to connect to a file and a simple query
+ */
+
+ include_once("../snoopy.class.php");
+ include_once("../htmlsql.class.php");
+
+ $wsql = new htmlsql();
+
+ // connect to a file
+ if (!$wsql->connect('file', 'demo_data.htm')){
+ print 'Error while connecting: ' . $wsql->error;
+ exit;
+ }
+
+ /* execute a query:
+
+ This query searches in all tags for the id == header and returns
+ the tag
+ */
+ if (!$wsql->query('SELECT * FROM * WHERE $id == "header"')){
+ print "Query error: " . $wsql->error;
+ exit;
+ }
+
+ // show results:
+ foreach($wsql->fetch_array() as $row){
+
+ print_r($row);
+
+ }
+
+?>
\ No newline at end of file diff --git a/examples/demo_04.php b/examples/demo_04.php new file mode 100755 index 0000000..5f7df78 --- /dev/null +++ b/examples/demo_04.php @@ -0,0 +1,36 @@ +<?php
+
+ /*
+ ** htmlSQL - Example 4
+ **
+ ** Shows a advanced query with preg_match
+ */
+
+ include_once("../snoopy.class.php");
+ include_once("../htmlsql.class.php");
+
+ $wsql = new htmlsql();
+
+ // connect to a URL
+ if (!$wsql->connect('url', 'http://codedump.jonasjohn.de/links.htm')){
+ print 'Error while connecting: ' . $wsql->error;
+ exit;
+ }
+
+ /* execute a query:
+
+ This query returns all links of an document that start with http://
+ */
+ if (!$wsql->query('SELECT * FROM a WHERE preg_match("/^http:\/\//", $href)')){
+ print "Query error: " . $wsql->error;
+ exit;
+ }
+
+ // show results:
+ foreach($wsql->fetch_array() as $row){
+
+ print_r($row);
+
+ }
+
+?>
\ No newline at end of file diff --git a/examples/demo_05.php b/examples/demo_05.php new file mode 100755 index 0000000..48ea46f --- /dev/null +++ b/examples/demo_05.php @@ -0,0 +1,38 @@ +<?php
+
+ /*
+ ** htmlSQL - Example 5
+ **
+ ** Shows a advanced query (with substr)
+ */
+
+ include_once("../snoopy.class.php");
+ include_once("../htmlsql.class.php");
+
+ $wsql = new htmlsql();
+
+ // connect to a URL
+ if (!$wsql->connect('url', 'http://codedump.jonasjohn.de/links.htm')){
+ print 'Error while connecting: ' . $wsql->error;
+ exit;
+ }
+
+ /* execute a query:
+
+ This query returns all links of an document that not start with /
+ ( / = internal links)
+ */
+ if (!$wsql->query('SELECT * FROM a WHERE substr($href,0,1) != "/"')){
+ print "Query error: " . $wsql->error;
+ exit;
+ }
+
+ // fetch results as object and format as HTML links:
+ foreach($wsql->fetch_objects() as $obj){
+
+ print '<a href="'.$obj->href.'">'.$obj->text.'</a><br/>';
+ print "\n";
+
+ }
+
+?>
\ No newline at end of file diff --git a/examples/demo_06.php b/examples/demo_06.php new file mode 100755 index 0000000..0e2a2c2 --- /dev/null +++ b/examples/demo_06.php @@ -0,0 +1,40 @@ +<?php
+
+ /*
+ ** htmlSQL - Example 6
+ **
+ ** Show how to connect to a string
+ */
+
+ include_once("../snoopy.class.php");
+ include_once("../htmlsql.class.php");
+
+
+ $some_html = '<a href="link1.htm">link1</a> <b>foobar</b> ';
+ $some_html .= '<a href="link2.htm">link2</a> <hr/>';
+
+ $wsql = new htmlsql();
+
+ // connect to a string
+ if (!$wsql->connect('string', $some_html)){
+ print 'Error while connecting: ' . $wsql->error;
+ exit;
+ }
+
+ /* execute a query:
+
+ This query returns all links of the given HTML
+ */
+ if (!$wsql->query('SELECT * FROM a')){
+ print "Query error: " . $wsql->error;
+ exit;
+ }
+
+ // fetch results as array and output them:
+ foreach($wsql->fetch_array() as $row){
+
+ print_r($row);
+
+ }
+
+?>
\ No newline at end of file diff --git a/examples/demo_07.php b/examples/demo_07.php new file mode 100755 index 0000000..f293cb9 --- /dev/null +++ b/examples/demo_07.php @@ -0,0 +1,37 @@ +<?php
+
+ /*
+ ** htmlSQL - Example 7
+ **
+ ** Shows a complex query
+ */
+
+ include_once("../snoopy.class.php");
+ include_once("../htmlsql.class.php");
+
+ $wsql = new htmlsql();
+
+ // connect to a URL
+ if (!$wsql->connect('url', 'http://codedump.jonasjohn.de/browse/lang/php/')){
+ print 'Error while connecting: ' . $wsql->error;
+ exit;
+ }
+
+ /* execute a query:
+
+ This query searches all links where the URL starts with /snippets and the text starts with
+ "array_" => so all links to array functions will be returned
+ */
+ if (!$wsql->query('SELECT * FROM a WHERE preg_match("/^\/snippets/i", $href) and preg_match("/^array_/i", $text)')){
+ print "Query error: " . $wsql->error;
+ exit;
+ }
+
+ // fetch results as array return them:
+ foreach($wsql->fetch_array() as $row){
+
+ print_r($row);
+
+ }
+
+?>
\ No newline at end of file diff --git a/examples/demo_08.php b/examples/demo_08.php new file mode 100755 index 0000000..e25a009 --- /dev/null +++ b/examples/demo_08.php @@ -0,0 +1,86 @@ +<?php
+
+ /*
+ ** htmlSQL - Example 8
+ **
+ ** Shows how to parse a RSS/XML file with htmlSQL
+ */
+
+ include_once("../snoopy.class.php");
+ include_once("../htmlsql.class.php");
+
+ $wsql = new htmlsql();
+
+ // connect to the RSS URL (this URL contains new snippets from my codedump project)
+ if (!$wsql->connect('url', 'http://codedump.jonasjohn.de/rss/')){
+ print 'Error while connecting: ' . $wsql->error;
+ exit;
+ }
+
+ /* execute a query:
+
+ select the text attribute (alias for the tag content) from the <item> tag
+ */
+ if (!$wsql->query('SELECT text FROM item')){
+ print "Query error: " . $wsql->error;
+ exit;
+ }
+
+ // fetch all results as objects:
+ foreach($wsql->fetch_objects() as $obj){
+
+ // create a new htmlsql object:
+ $sub_wsql = new htmlsql();
+
+ // connect to the <item> content:
+ $sub_wsql->connect('string', $obj->text);
+
+ // fetch all attributes of all tags:
+ if (!$sub_wsql->query('SELECT * FROM *')){
+ print "Query error: " . $wsql->error;
+ exit;
+ }
+
+ // this "special" function converts tagnames to keys
+ $sub_wsql->convert_tagname_to_key();
+
+ /* this function converts an array that looks like this:
+
+ $array[0]['tagname'] = 'title';
+ $array[0]['text'] = 'example 1';
+
+ $array[1]['tagname'] = 'link';
+ $array[1]['text'] = 'http://www.example.org/';
+
+ $array[2]['tagname'] = 'description';
+ $array[2]['text'] = 'description bla';
+ $array[2]['fulltext'] = '1'; // additional attribute
+
+ -> to:
+
+ $array['title']['text'] = 'example 1';
+
+ $array[1]['link']['text'] = 'http://www.example.org/';
+
+ $array[2]['description']['text'] = 'description bla';
+ $array[2]['description']['fulltext'] = '1'; // additional attribute
+
+ this makes the array easier to access
+
+ */
+
+
+ // fetch item as array:
+ $item = $sub_wsql->fetch_array();
+
+ // format the extracted links as HTML links and output them:
+ print "<a href=\"" . $item['link']['text'] . "\">";
+ print $item['title']['text'] . "</a><br/>\n";
+
+ // also available:
+ // description, pubDate
+
+
+ }
+
+?>
\ No newline at end of file diff --git a/examples/demo_09.php b/examples/demo_09.php new file mode 100755 index 0000000..25fc23e --- /dev/null +++ b/examples/demo_09.php @@ -0,0 +1,51 @@ +<?php
+
+ /*
+ ** htmlSQL - Example 9
+ **
+ ** Shows how to use the "select" function
+ */
+
+ include_once("../snoopy.class.php");
+ include_once("../htmlsql.class.php");
+
+ $wsql = new htmlsql();
+
+ // connect to a URL
+ if (!$wsql->connect('url', 'http://codedump.jonasjohn.de/')){
+ print 'Error while connecting: ' . $wsql->error;
+ exit;
+ }
+
+ // restricts the search process to the content between
+ // <body> and </body>
+ // this also works with other tags like: head or html, or table
+ $wsql->select('body');
+
+ /*
+ other examples:
+
+ $wsql->select('div',3); <-- selects the third <div>
+
+ $wsql->select('table',0); <-- selects the first table
+ ^ default is also = 0
+ */
+
+
+ /* execute a query:
+
+ This query returns all <h1> headers
+ */
+ if (!$wsql->query('SELECT * FROM h1')){
+ print "Query error: " . $wsql->error;
+ exit;
+ }
+
+ // fetch results as array
+ foreach($wsql->fetch_array() as $row){
+
+ print_r($row);
+
+ }
+
+?>
\ No newline at end of file diff --git a/examples/demo_10.php b/examples/demo_10.php new file mode 100755 index 0000000..961a0a8 --- /dev/null +++ b/examples/demo_10.php @@ -0,0 +1,55 @@ +<?php
+
+ /*
+ ** htmlSQL - Example 10
+ **
+ ** Shows how to use the "isolate_content" function
+ */
+
+ include_once("../snoopy.class.php");
+ include_once("../htmlsql.class.php");
+
+ $wsql = new htmlsql();
+
+ // connect to a URL
+ if (!$wsql->connect('url', 'http://codedump.jonasjohn.de/')){
+ print 'Error while connecting: ' . $wsql->error;
+ exit;
+ }
+
+ /*
+ ** The isolate_content functions works like the select function,
+ ** but you can specify custom HTML parts, the content between
+ ** these two strings will be used for the query process
+ **
+ ** In this case we select all content between "<h1>New snippets</h1>"
+ ** and "<p id="rss">" this returns all snippet links, and no other links
+ ** (like header or navigation links)
+ */
+
+ $wsql->isolate_content('<h1>New snippets</h1>', '<p id="rss">');
+
+ /*
+ other examples:
+
+ $wsql->isolate_content('<body>', '</body>');
+ $wsql->isolate_content('<!--content:start-->', '<!--end-->');
+ */
+
+ /* execute a query:
+
+ This query returns all links:
+ */
+ if (!$wsql->query('SELECT * FROM a')){
+ print "Query error: " . $wsql->error;
+ exit;
+ }
+
+ // fetch results as array
+ foreach($wsql->fetch_array() as $row){
+
+ print_r($row);
+
+ }
+
+?>
\ No newline at end of file diff --git a/examples/demo_11.php b/examples/demo_11.php new file mode 100755 index 0000000..591598f --- /dev/null +++ b/examples/demo_11.php @@ -0,0 +1,36 @@ +<?php
+
+ /*
+ ** htmlSQL - Example 11
+ **
+ ** Shows how to query a simple XML file
+ */
+
+ include_once("../snoopy.class.php");
+ include_once("../htmlsql.class.php");
+
+ $wsql = new htmlsql();
+
+ // connect to the demo XML file:
+ if (!$wsql->connect('file', 'demo_xml.xml')){
+ print 'Error while connecting: ' . $wsql->error;
+ exit;
+ }
+
+ /* execute a query:
+
+ This query returns the id, name and password of all active users
+ */
+ if (!$wsql->query('SELECT id, name, password FROM user WHERE $status == "active"')){
+ print "Query error: " . $wsql->error;
+ exit;
+ }
+
+ // fetch results as array
+ foreach($wsql->fetch_array() as $row){
+
+ print_r($row);
+
+ }
+
+?>
\ No newline at end of file diff --git a/examples/demo_12.php b/examples/demo_12.php new file mode 100755 index 0000000..68d524a --- /dev/null +++ b/examples/demo_12.php @@ -0,0 +1,44 @@ +<?php
+
+ /*
+ ** htmlSQL - Example 12
+ **
+ ** Shows how to replace the user agent and the referer with
+ ** custom values
+ */
+
+ include_once("../snoopy.class.php");
+ include_once("../htmlsql.class.php");
+
+ $wsql = new htmlsql();
+
+ // set a individual agent:
+ $wsql->set_user_agent('MyAgentName/0.9');
+
+ // set a new referer:
+ $wsql->set_referer('http://www.jonasjohn.de/custom/referer/');
+
+
+ // connect to a URL
+ if (!$wsql->connect('url', 'http://codedump.jonasjohn.de/')){
+ print 'Error while connecting: ' . $wsql->error;
+ exit;
+ }
+
+ /* execute a query:
+
+ This query returns all links:
+ */
+ if (!$wsql->query('SELECT * FROM a')){
+ print "Query error: " . $wsql->error;
+ exit;
+ }
+
+ // fetch results as array
+ foreach($wsql->fetch_array() as $row){
+
+ print_r($row);
+
+ }
+
+?>
\ No newline at end of file diff --git a/examples/demo_data.htm b/examples/demo_data.htm new file mode 100755 index 0000000..bd5d766 --- /dev/null +++ b/examples/demo_data.htm @@ -0,0 +1,195 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" + "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> +
+<!--
+ this is a modified HTML source code from www.jonasjohn.de
+ for htmlSQL - testing purposes only
+
+ Copyright (c) 2004-2006 Jonas John
+-->
+ +<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"> +<head> + <title>jonasjohn.de: startpage</title> + + <meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1" /> + <meta http-equiv="Content-Language" content="en" /> + + <meta name="description" content="Personal WebSite of Jonas John." /> + <meta name="keywords" content="jonas, john, photos, design, php, tests, experiments, privat, portfolio" /> + + <meta name="MSSmartTagsPreventParsing" content="true" /> + <meta http-equiv="imagetoolbar" content="no" /> + + + </head> +<body> + +<p class="hidden"> + <a href="#content" accesskey="s">Skip to content...</a> +</p> + +<div id="nav"> + <div id="inner_nav"> + + <a href="http://www.jonasjohn.de/" id="logo" accesskey="h"> + <img src="/img/logo.png" width="137" height="30" alt="jonasjohn.de - logo" /> + </a> + + <div id="lang"> + <span class="hidden">Choose your language:</span> + <a href="/" accesskey="e" id="lang_sel"><img src="/img/l_eng.png" alt="" width="27" height="20" /> english</a> + <a href="/de/" id="lang_def" accesskey="d"><img src="/img/l_de.png" alt="" width="27" height="20" /> deutsch</a> + </div> + + <br class="clear" /> + + <div id="info_panel"></div> + + </div> +</div> + + +<div id="header"> + <div id="inner_header"> + + <span class="hidden">Navigation:</span> + <ul> + <li><a href="/" accesskey="1">Home</a></li> + <li><a href="/lab/" accesskey="2">Lab</a></li> + <li><a href="/pictures/" accesskey="3">Photos</a></li> + <li><a href="/about/" accesskey="4">About me</a></li> + <li><a href="/sitemap.htm" accesskey="5">Sitemap</a></li> + <li><a href="/contact.htm" accesskey="6">Contact</a></li> + </ul> + + <br class="clear" /> + </div> +</div> + +<div id="page"> + <div id="inner_page"> + + <a name="content"></a> + + <div id="h_left"> + + <h1 class="big"> + ¬ welcome to...<br/> + <span class="sub">the personal website of jonas john!</span> + </h1> + + <p> + + Hello and welcome to the personal website of <b>Jonas John</b>. This is my personal + web playground, I use it to present myself and to create some experimental + things. Have fun! + + + <br/> + <br/> + <br/> + + </p> + </div> + + <div id="h_right"> + <p> + <b>News (May 04, 2006):</b><br/> + I published the third version of my website. Now it's almost + completely translated in English. Just a few texts left. + <br/> + <br/> + + <a href="/news.htm" id="more">News archive...</a> + <br/> + </p> + + </div> + + <br class="clear" /> + + <div id="inner_content" class="clear sect_spacer"> + + <div class="large_box"> + + <h2>What do I find here?</h2> + + <div class="halfbox bleft"> + <p> + <a href="/lab/"> + <img src="img/p_code.png" alt="my lab" width="120" height="90" /><br/><span class="plink">Lab</span> + </a> + + Look on this page to get some informations about my + <b>web projects</b> and software that I made. + + </p> + </div> + + <div class="halfbox bright"> + <p> + <a href="/pictures/"> + <img src="img/p_photo.png" alt="photos" class="img_left" width="120" height="90" /><br/><span class="plink">Photos</span> + </a> + + Here you find a few <b>photos</b> I made. I'm an amateur photographer, + so don't expect too much ;-) + + </p> + </div> + + <br class="clear" /> + <br class="clear boxspacer" /> + + <div class="halfbox bleft"> + <p> + <a href="/lab/adblock.htm"> + <img src="img/p_adblock.png" alt="adblock filterset generator" class="img_left" width="120" height="90" /><br/><span class="plink">Adblock F. Generator</span> + </a> + + This <b>Adblock Plus Filterset Generator</b> allows you to create your own customized + filterlist for the Firefox Plugin "Adblock Plus". Just check or uncheck + the filters you want. + + + </p> + </div> + + <div class="halfbox bright"> + <p> + <a href="/lab/codedump.htm"> + <img src="img/p_codedump.png" alt="codedump" class="img_left" width="120" height="90" /><br/><span class="plink">Codedump</span> + </a> + + Here you can find around 70 <b>code snippets</b> for different topics. + The snippet languages are PHP, JavaScript, HTML, Perl and Python. + You can use them freely in your projects (public domain). + + </p> + </div> + + <br class="clear" /> + <br/> + </div> + + <br/> + + <br class="clear" /> + + </div> + + </div> + +</div> + +<div id="footer"> + <p> + Copyright © 2004-2006 Jonas David John. All rights reserved. + <a href="/contact.htm">Imprint</a> + </p> +</div> + +</body> +</html> + diff --git a/examples/demo_xml.xml b/examples/demo_xml.xml new file mode 100755 index 0000000..e54968e --- /dev/null +++ b/examples/demo_xml.xml @@ -0,0 +1,8 @@ +<?xml version="1.0" encoding="ISO-8859-1"?>
+<users>
+ <user id="0" name="admin" password="foobar" status="active"></user>
+ <user id="1" name="jonas" password="heyho" status="active"></user>
+ <user id="2" name="jack" password="daniels" status="drunk"></user>
+ <user id="3" name="bill" password="kill" status="dead"></user>
+ <user id="4" name="homer" password="kenny" status="active"></user>
+</users>
\ No newline at end of file diff --git a/examples/query_examples.txt b/examples/query_examples.txt new file mode 100755 index 0000000..638bd6c --- /dev/null +++ b/examples/query_examples.txt @@ -0,0 +1,51 @@ +
+Some query examples for copy & paste ;-)
+
+
+SELECT * FROM h1
+^ select all <h1> tags
+
+
+SELECT * FROM a
+^ select all links
+
+
+SELECT * FROM td
+^ select all <td>'s
+
+
+SELECT href as url, text FROM a
+^ return href as url and text as text from all links
+
+
+SELECT * FROM a WHERE preg_match("/^http:\/\//", $href)
+^ find all external links
+
+
+SELECT * FROM a WHERE preg_match("/^\/snippets/i", $href) and preg_match("/^array_/i", $text)
+^ find all links starting with /snippets and with a link text starting with "array_"
+
+
+SELECT * FROM *
+^ select all attributes of all tags ;-)
+
+
+SELECT id, name, password FROM user WHERE $status == "active"
+^ select all <user> tags where status="active" (for XML files)
+
+
+SELECT * FROM * WHERE $id == "header"
+^ return all tags with the $id = header
+
+
+SELECT * FROM a WHERE substr($href,0,1) != "/"
+^ select links with URLs that start with / (mainly internal links)
+
+
+SELECT * FROM * WHERE $class == "nav_item"
+^ select all tags with the class = nav_item
+
+
+SELECT * FROM a WHERE ($href == "foo.htm" and $title == "foo") or ($title == "bar")
+^ complex query
+
diff --git a/htmlsql.class.php b/htmlsql.class.php new file mode 100755 index 0000000..2292073 --- /dev/null +++ b/htmlsql.class.php @@ -0,0 +1,677 @@ +<?php
+
+/*
+htmlSQL - version 0.5
+--------------------------------------------------------------------
+htmlSQL is a experimental class to query websites or HTML code with
+an SQL-like language.
+
+AUTHOR: Jonas John (http://www.jonasjohn.de/)
+
+The latest version of htmlSQL can be obtained from:
+http://www.jonasjohn.de/lab/htmlsql.htm
+
+LICENSE:
+--------------------------------------------------------------------
+Copyright (c) 2006 Jonas John. All rights reserved.
+--------------------------------------------------------------------
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions
+are met:
+
+- Redistributions of source code must retain the above copyright
+ notice, this list of conditions and the following disclaimer.
+- Redistributions in binary form must reproduce the above copyright
+ notice, this list of conditions and the following disclaimer in
+ the documentation and/or other materials provided with the distribution.
+- Neither the name of Jonas John nor the names of its contributors
+ may be used to endorse or promote products derived from this
+ software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
+COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS
+OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR
+TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE
+USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+--------------------------------------------------------------------
+
+CHANGELOG:
+
+0.4 -> 0.5 (May 07, 2006):
+- Renamed the project from webSQL to htmlSQL, because webSQL
+ is already existing... :-(
+- Added some error checks and error messages
+- Added the convert_tagname_to_key function and
+ fixed a few issues
+
+0.1 -> 0.4 (April 2006):
+- Created main parts of the class
+
+*/
+
+class htmlsql {
+
+ // configuration:
+
+ // htmlSQL version:
+ var $version = '0.5';
+
+ // referer and user agent:
+ var $referer = '';
+ var $user_agent = 'htmlSQL/0.5';
+
+
+
+ // these are filled on runtime:
+ // (don't touch them)
+
+ // holds snoopy object:
+ var $snoopy = NULL;
+
+ // the results array is stored in here:
+ var $results = array();
+
+ // the results objects are stored in here:
+ var $results_objects = NULL;
+
+ // the error message gets stored in here:
+ var $error = '';
+
+ // the downloaded page is stored in here:
+ var $page = '';
+
+
+ /*
+ ** init_snoopy
+ **
+ ** initializes the snoopy class
+ */
+
+ function init_snoopy(){
+ $this->snoopy = new Snoopy();
+ $this->snoopy->agent = $this->user_agent;
+ $this->snoopy->referer = $this->referer;
+ }
+
+
+ /*
+ ** set_user_agent
+ **
+ ** set a custom user agent
+ */
+
+ function set_user_agent($u){
+ $this->user_agent = $u;
+ }
+
+
+
+ /*
+ ** set_referer
+ **
+ ** sets the referer
+ */
+
+ function set_referer($r){
+ $this->referer = $r;
+ }
+
+
+ /*
+ ** _get_between
+ **
+ ** returns the content between $start and $end
+ */
+
+ function _get_between($content,$start,$end){
+ $r = explode($start, $content);
+ if (isset($r[1])){
+ $r = explode($end, $r[1]);
+ return $r[0];
+ }
+ return '';
+ }
+
+
+ /*
+ ** connect
+ **
+ ** connects to a data source (url, file or string)
+ */
+
+ function connect($type, $resource){
+ if ($type == 'url'){
+ return $this->_fetch_url($resource);
+ }
+ else if ($type == 'file') {
+ if (!file_exists($resource)){
+ $this->error = 'The given file "'.$resource.' does not exist!';
+ return false;
+ }
+ $this->page = file_get_contents($resource); return true;
+ }
+ else if ($type == 'string') { $this->page = $resource; return true; }
+
+ return false;
+ }
+
+
+ /*
+ ** _fetch_url
+ **
+ ** downloads the given URL with snoopy
+ */
+
+ function _fetch_url($url){
+
+ $parsed_url = parse_url($url);
+
+ if (!isset($parsed_url['scheme']) or $parsed_url['scheme'] != 'http'){
+ $this->error = 'Unsupported URL sheme given, please just use "HTTP".';
+ return false;
+ }
+ if (!isset($parsed_url['host']) or $parsed_url['host'] == ''){
+ $this->error = 'Invalid URL given!';
+ return false;
+ }
+
+ $host = $parsed_url['host'];
+ $host .= (isset($parsed_url['port']) and !empty($parsed_url['port'])) ? ':'.$parsed_url['port'] : '';
+ $path = (isset($parsed_url['path']) and !empty($parsed_url['path'])) ? $parsed_url['path'] : '/';
+ $path .= (isset($parsed_url['query']) and !empty($parsed_url['query'])) ? '?'.$parsed_url['query'] : '';
+
+ $url = 'http://' . $host . $path;
+
+ $this->init_snoopy();
+
+ if($this->snoopy->fetch($url)){
+
+ $this->page = $this->snoopy->results;
+
+ // empty buffer:
+ $this->snoopy->results = '';
+ }
+ else {
+ $this->error = 'Could not establish a connection to the given URL!';
+ return false;
+ }
+ return true;
+ }
+
+
+ /*
+ ** _extract_all_tags
+ **
+ **
+ */
+
+ function _extract_all_tags($html, &$tag_names, &$tag_attributes, &$tag_values, $depth=0){
+
+ // stop endless loops:
+ if ($depth > 99999){ return; }
+
+ preg_match_all('/<([a-z0-9\-]+)(.*?)>((.*?)<\/\1>)?/is', $html, $m);
+ if (count($m[0]) != 0){
+ for ($t=0; $t < count($m[0]); $t++){
+
+ $tag_names[] = trim($m[1][$t]);
+ $tag_attributes[] = trim($m[2][$t]);
+ $tag_values[] = trim($m[4][$t]);
+
+ // go deeper:
+ if (trim($m[4][$t]) != '' and preg_match('/<[a-z0-9\-]+.*?>/is', $m[4][$t])){
+ $this->_extract_all_tags($m[4][$t], $tag_names, $tag_attributes, $tag_values, $depth+1);
+ }
+
+ }
+ }
+
+ }
+
+
+ /*
+ ** isolate_content
+ **
+ ** isolates the content to a specific part
+ */
+
+ function isolate_content($start,$end){
+
+ $this->page = $this->_get_between($this->page, $start, $end);
+
+ }
+
+
+ /*
+ ** select
+ **
+ ** restricts the content of a specific tag
+ */
+
+ function select($tagname, $num=0){
+ $num++;
+
+ if ($tagname != ''){
+
+ preg_match('/<'.$tagname.'.*?>(.*?)<\/'.$tagname.'>/is', $this->page, $m);
+
+ if (isset($m[$num]) and !empty($m[$num])){
+ $this->page = $m[$num];
+ }
+ else {
+ $this->error = 'Could not select tag: "'.$tagname.'('.$num.')"!';
+ return false;
+ }
+ }
+ return true;
+ }
+
+
+ /*
+ ** get_content
+ **
+ ** returns the content of an request
+ */
+
+ function get_content(){
+ return $this->page;
+ }
+
+
+ /*
+ ** _clean_array
+ **
+ **
+ */
+
+ function _clean_array($arr){
+ $new = array();
+ for ($x=0; $x < count($arr); $x++){
+ $arr[$x] = trim($arr[$x]);
+ if ($arr[$x] != ''){ $new[] = $arr[$x]; }
+ }
+ return $new;
+ }
+
+
+ /*
+ ** _test_tag
+ **
+ **
+ */
+
+ function _test_tag($tag_attributes, $if_term){
+
+ preg_match_all('/\$([a-z0-9_\-]+)/i', $if_term, $m);
+ if (isset($m[1])){
+ for ($x=0; $x < count($m[1]); $x++){
+ $varname = $m[1][$x];
+ $$varname = '';
+ }
+ }
+
+ $new_list = array();
+ while (list($k,$v) = each($tag_attributes)){
+ $k = preg_replace('/[^a-z0-9_\-]/i', '', $k);
+ if ($k != ''){ $new_list[$k] = $v; }
+ }
+ unset($tag_attributes);
+
+ extract($new_list);
+
+ $r = false;
+ if (@eval('$r = ('.$if_term.');') === false){
+ $this->error = 'The WHERE statement is invalid (eval() failed)!';
+ return false;
+ }
+
+ return $r;
+
+ }
+
+
+ /*
+ ** _match_tags
+ **
+ **
+ */
+
+ function _match_tags(&$results, &$return_values, &$where_term, &$tag_attributes, &$tag_values, &$tag_names){
+
+ $search_mode = ''; $search_attribute = ''; $search_term = '';
+
+ /*
+ ** parse:
+ **
+ ** href LIKE ".htm"
+ ** class = "foo"
+ */
+
+ $where_term = trim($where_term);
+
+ $search_mode = ($where_term == '') ? 'match_all' : 'eval';
+
+ for ($x=0; $x < count($tag_attributes); $x++){
+
+ $tag_attributes[$x] = $this->parse_attributes($tag_attributes[$x]);
+
+ if (is_array($tag_names)){
+ $tag_attributes[$x]['tagname'] = isset($tag_names[$x]) ? $tag_names[$x] : '';
+ }
+ else { $tag_attributes[$x]['tagname'] = $tag_names; } // string
+
+ $tag_attributes[$x]['text'] = isset($tag_values[$x]) ? $tag_values[$x] : '';
+
+ if ($search_mode == 'eval'){
+
+ if ($this->_test_tag($tag_attributes[$x], $where_term)){
+ $this->_add_result($results, $return_values, $tag_attributes[$x]);
+ }
+
+ }
+ else if ($search_mode == 'match_all'){
+ $this->_add_result($results, $return_values, $tag_attributes[$x]);
+ }
+ }
+ }
+
+
+ /*
+ ** query
+ **
+ ** performs a query
+ */
+
+ function query($term){
+
+ // query results are stored in here:
+ $results = array();
+ $this->results = NULL;
+ $this->results_objects = NULL;
+
+ $term = trim($term);
+ if ($term == ''){
+ $this->error = 'Empty query given!';
+ return false;
+ }
+
+ // match query:
+ preg_match('/^SELECT (.*?) FROM (.*)$/i', $term, $m);
+
+ // parse returns values
+ // SELECT * FROM ...
+ // SELECT foo,bar FROM ...
+ $return_values = isset($m[1]) ? trim($m[1]) : '*';
+ if ($return_values != '*'){
+ $return_values = explode(',', strtolower($return_values));
+ $return_values = $this->_clean_array($return_values);
+ }
+
+ // match from and where part:
+ //
+ // ... FROM * WHERE $id=="one"
+ // ... FROM a WHERE $class=="red"
+ // ... FROM a
+ // ... FROM *
+ $last = isset($m[2]) ? trim($m[2]) : '';
+
+ $search_term = '';
+ $where_term = '';
+
+ if (preg_match('/^(.*?) WHERE (.*?)$/i', $last, $m)){
+ $search_term = trim($m[1]);
+ $where_term = trim($m[2]);
+ }
+ else {
+ $search_term = $last;
+ }
+
+ /*
+ ** find tags:
+ */
+
+ if ($search_term == '*'){
+ // search all
+
+ $tag_names = array();
+ $tag_attributes = array();
+ $tag_values = array();
+
+ $html = $this->page;
+
+ $this->_extract_all_tags($html, $tag_names, $tag_attributes, $tag_values);
+
+ $this->_match_tags($results, $return_values, $where_term, $tag_attributes, $tag_values, $tag_names);
+
+ }
+ else {
+
+ // search term is a tag
+
+ $tagname = trim($search_term);
+
+ $tag_attributes = array();
+ $tag_values = array();
+
+ $regexp = '<'.$tagname.'([ \t].*?|)>((.*?)<\/'.$tagname.'>)?';
+ preg_match_all('/'.$regexp.'/is', $this->page, $m);
+
+ if (count($m[0]) != 0){
+ $tag_attributes = $m[1];
+ $tag_values = $m[3];
+ }
+
+ $this->_match_tags($results, $return_values, $where_term, $tag_attributes, $tag_values, $tagname);
+ }
+
+ $this->results = $results;
+
+ // was there a error during the search process?
+ if ($this->error != ''){
+ return false;
+ }
+
+ return true;
+
+ }
+
+ /*
+ ** convert_tagname_to_key
+ **
+ ** converts the tagname to the array key
+ */
+
+ function convert_tagname_to_key(){
+
+ $new_array = array();
+
+ while(list($key,$val) = each($this->results)){
+
+ if (isset($val['tagname'])){
+ $tag_name = $val['tagname'];
+ unset($val['tagname']);
+ }
+ else { $tag_name = '(empty)'; }
+
+ $new_array[$tag_name] = $val;
+
+ }
+
+ $this->results = $new_array;
+ }
+
+
+ /*
+ ** fetch_array
+ **
+ ** returns the results as an array
+ */
+
+ function fetch_array(){
+ return $this->results;
+ }
+
+
+ /*
+ ** _array2object
+ **
+ ** converts an array to an object
+ */
+
+ function _array2object($array) {
+
+ if (is_array($array)) {
+
+ $obj = new StdClass();
+
+ foreach ($array as $key => $val){
+ $obj->$key = $val;
+ }
+
+ }
+ else { $obj = $array; }
+
+ return $obj;
+ }
+
+
+ /*
+ ** fetch_objects
+ **
+ ** returns the results as objects
+ */
+
+ function fetch_objects(){
+
+ if ($this->results_objects == NULL){
+
+ $results = array();
+
+ reset($this->results);
+ while(list($key,$val) = each($this->results)){
+ $results[$key] = $this->_array2object($val);
+ }
+
+ $this->results_objects = $results;
+
+ return $this->results_objects;
+ }
+ else {
+ return $this->results_objects;
+ }
+ }
+
+ /*
+ ** get_result_count
+ **
+ ** returns the number of results
+ */
+
+ function get_result_count(){
+ return count($this->results);
+ }
+
+
+ /*
+ ** _add_result
+ **
+ **
+ */
+
+ function _add_result(&$results, $return_values, $tag_attributes){
+
+ if ($return_values == '*'){
+ $results[] = $tag_attributes;
+ }
+ else if (is_array($return_values)){
+
+ $new_result = array();
+
+ reset($return_values);
+ for ($t=0; $t < count($return_values); $t++){
+
+ $_tagname = explode(' as ', $return_values[$t]);
+ $_caption = $return_values[$t];
+
+ if (count($_tagname) != 1){
+ $_caption = trim($_tagname[1]);
+ $_tagname = trim($_tagname[0]);
+ }
+ else { $_tagname = $_caption; }
+
+ $new_result[$_caption] = isset($tag_attributes[$_tagname]) ? $tag_attributes[$_tagname] : '';
+ }
+ $results[] = $new_result;
+ }
+ }
+
+
+ /*
+ ** parse_attributes
+ **
+ ** parses HTML attributes and returns an array
+ */
+
+ function parse_attributes($attrib){
+
+ $attrib .= '>';
+
+ $mode = 'search_key';
+ $tmp = '';
+ $current_key = '';
+
+ $attributes = array();
+
+ for ($x=0; $x < strlen($attrib); $x++){
+
+ $char = $attrib[$x];
+
+ if ($char == '=' and $mode == 'search_key'){
+ $current_key = trim($tmp);
+ $tmp = '';
+ $mode = 'value';
+ }
+ else if ($mode == 'search_key' and preg_match('/[ \t\s\r\n>]/', $char)){
+ $current_key = strtolower(trim($tmp));
+ if ($current_key != ''){ $attributes[$current_key] = ''; }
+ $tmp = ''; $current_key = '';
+ }
+ else if ($mode == 'value' and $char == '"'){ $mode = 'find_value_ending_a'; }
+ else if ($mode == 'value' and $char == '\''){ $mode = 'find_value_ending_b'; }
+ else if ($mode == 'value'){ $tmp .= $char; $mode = 'find_value_ending_c'; }
+ else if (
+ ($mode == 'find_value_ending_a' and $char == '"') or
+ ($mode == 'find_value_ending_b' and $char == '\'') or
+ ($mode == 'find_value_ending_c' and preg_match('/[ \t\s\r\n>]/', $char))
+ ){
+
+ $mode = 'search_key';
+
+ if ($current_key != ''){
+ $current_key = strtolower($current_key);
+ $attributes[$current_key] = $tmp;
+ }
+ $tmp = '';
+ }
+ else { $tmp .= $char; }
+ }
+
+ if ($mode != 'search_key' and $current_key != ''){
+ $current_key = strtolower($current_key);
+ $attributes[$current_key] = trim(preg_replace('/>+$/', '', $tmp));
+ }
+
+ return $attributes;
+
+ }
+
+}
+
+?>
\ No newline at end of file diff --git a/readme.txt b/readme.txt new file mode 100755 index 0000000..742a254 --- /dev/null +++ b/readme.txt @@ -0,0 +1,67 @@ +htmlSQL - Version 0.5 - README
+---------------------------------------------------------------------
+AUTHOR: Jonas John (http://www.jonasjohn.de/)
+
+
+DESCRIPTION:
+---------------------------------------------------------------------
+htmlSQL is a experimental PHP class which allows you to access HTML
+values by an SQL like syntax. This means that you don't have to write
+complex functions (regular expressions) to extract specific values.
+The htmlSQL queries look like this:
+
+SELECT href,title FROM a WHERE $class == "list"
+ ^ Attributes ^ ^ search query (can be empty)
+ to return ^
+ ^ HTML tag to search in
+ "*" is possible = all tags
+
+This query returns an array with all links that contain
+the attribute class="list".
+
+All web transfers in htmlSQL are using the awesome Snoopy class
+(package version 1.2.3 - URL: http://snoopy.sourceforge.net/)
+But for file or string queries Snoopy is not required. You find all
+Snoopy related documents (copyright, readme, etc) in the snoopy_data/
+folder.
+
+
+HOW TO USE:
+---------------------------------------------------------------------
+Just include the "snoopy.class.php" and the "htmlsql.class.php" files
+into your PHP scripts and look at the examples (examples/) to get an
+idea of how to use the htmlSQL class. It should be very simple :-)
+
+
+BACKGROUND / IDEA:
+---------------------------------------------------------------------
+I had this idea while extracting some data from a website. As I realized
+that the algorithms and functions to extract links and other tags are
+often the same - I had the idea to combine all functions to an universal
+usable class. While drinking a coffee and thinking on that problem, I
+thought it would be cool to access HTML elements by using SQL. So I
+started creating this class...
+
+
+WARNING:
+---------------------------------------------------------------------
+The eval() function is used for the WHERE statement. Make sure that all
+user data is checked and filtered against malicious PHP code.
+Never trust user input!
+
+
+TODO:
+---------------------------------------------------------------------
+- enhance the HTML parser
+- test htmlSQL with invalid and bad HTML files
+- replace the ugly eval() method for the WHERE statement
+ with an own method
+- more error checks
+- include the LIMIT function/method like in SQL
+
+
+LICENSE:
+---------------------------------------------------------------------
+htmlSQL uses a modified BSD license, you find the full license text
+in the "htmlsql.class.php".
+
diff --git a/readme_german.txt b/readme_german.txt new file mode 100755 index 0000000..ffecc5a --- /dev/null +++ b/readme_german.txt @@ -0,0 +1,85 @@ +htmlSQL - Version 0.5 - README
+---------------------------------------------------------------------
+AUTHOR: Jonas John (http://www.jonasjohn.de/)
+
+BESCHREIBUNG:
+---------------------------------------------------------------------
+htmlSQL ist eine experimentelle PHP Klasse mit der man auf HTML
+Elemente über eine SQL ähnliche Syntax zugreifen kann. Das
+bedeutet das man nicht mehr über komplizierte Funktionen
+bestimmte Tags extrahieren muss, sondern einfach eine Query
+wie diese ausführt:
+
+SELECT href,title FROM a WHERE $class == "liste"
+ ^ HTML Attrib. ^ ^ Abfrage (kann auch leer sein)
+ die zurück- ^
+ gegeben ^ HTML Tags die durchsucht werden sollen
+ werden sollen "*" ist hier möglich = alle Tags
+
+Diese Abfrage gibt einen Array aller Links mit dem Attribut class="liste"
+zurück.
+
+Alle HTTP Verbindungen in htmlSQL benützen die wunderbare Snoopy Klasse
+(Package Version 1.2.3 - URL: http://snoopy.sourceforge.net/).
+Allerdings wird Snoopy nicht für "file" oder "string" Queries benötigt.
+Alle Snoopy betreffenden Dokumente (z.B: Copyright-Infos, Readme, usw.)
+befinden sich im "snoopy_data/" Unterordner.
+
+
+INSTALLATION / ANWENDUNG:
+---------------------------------------------------------------------
+Um htmlSQL in eigenen Projekten zu benützen ist es nur notwendig die
+zwei Dateien "snoopy.class.php" und die "htmlsql.class.php" zu laden
+(mit include oder z.B. require). Danach kann htmlSQL, wie in den
+Beispielen (siehe examples/-Ordner), angesprochen werden. Dies sollte
+nicht allzu schwer sein :-)
+
+
+HINTERGRUND / GESCHICHTE:
+---------------------------------------------------------------------
+Ich hatte die Idee zu dieser Klasse als ich Daten von einer Web-Seite
+extrahiert habe und dabei merkte das sich die Funktionen und Quelltexte
+oftmals wiederholen. Da kam mir die Idee das ganze zu vereinfachen und
+eine universelle Klasse dafür zu entwickeln.
+
+
+WARNUNG:
+---------------------------------------------------------------------
+Für die Abfragen wird die eval()-Funktion benützt. Deshalb sollten alle
+vom Besucher abhängige Daten wie z.b. IDs geprüft oder ggf. gefiltert
+werden da es ansonsten möglich wäre schadhaften PHP Quelltext auszuführen.
+Vertraue niemals Benutzereingaben!
+
+
+TODO:
+---------------------------------------------------------------------
+- den internen HTML Parser verbessern
+- ein eigenes Query system entwickeln und nicht
+ das PHP eigene nutzen ( Die eval()-Lösung gefällt mir nicht wirklich)
+- Mehr Fehlerprüfungen
+- LIMIT Funktion einbauen
+
+
+ANWENDUNGSGEBIETE VON HTMLSQL:
+---------------------------------------------------------------------
+- Daten von anderen Web-Seiten auslesen
+- HTML basierte Datenbanken?
+- XML Daten auslesen
+
+
+LIZENZ:
+---------------------------------------------------------------------
+htmlSQL benützt eine modifizierte BSD Lizenz, welche ziemlich offen ist.
+Der Lizenztext befindet sich in der "htmlsql.class.php".
+Kurz zusammengefasst besagt er folgendes:
+
+- Die htmlSQL Klasse kann frei in kommerziellen und nicht-kommerziellen
+ Projekten benützt werden
+- Die Klasse darf mit oder ohne Änderungen frei weitergegeben werden
+- Der Copyright-Hinweis darf nicht entfernt werden
+- Der Autor übernimmt keine Haftung für eventuelle Schäden
+- Der Name des Autors oder anderen beteiligten Autoren darf nur mit
+ schriftlicher Genehmigung benützt werden um für Produkte, welche
+ htmlSQL benützen, zu werben
+
+
diff --git a/snoopy.class.php b/snoopy.class.php new file mode 100755 index 0000000..77e5b73 --- /dev/null +++ b/snoopy.class.php @@ -0,0 +1,1257 @@ +<?php + +/************************************************* + +Snoopy - the PHP net client +Author: Monte Ohrt <monte@ispi.net> +Copyright (c): 1999-2000 ispi, all rights reserved +Version: 1.01 + + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + +You may contact the author of Snoopy by e-mail at: +monte@ispi.net + +Or, write to: +Monte Ohrt +CTO, ispi +237 S. 70th suite 220 +Lincoln, NE 68510 + +The latest version of Snoopy can be obtained from: +http://snoopy.sourceforge.net/ + +*************************************************/ + +class Snoopy +{ + /**** Public variables ****/ + + /* user definable vars */ + + var $host = "www.php.net"; // host name we are connecting to + var $port = 80; // port we are connecting to + var $proxy_host = ""; // proxy host to use + var $proxy_port = ""; // proxy port to use + var $proxy_user = ""; // proxy user to use + var $proxy_pass = ""; // proxy password to use + + var $agent = "Snoopy v1.2.3"; // agent we masquerade as + var $referer = ""; // referer info to pass + var $cookies = array(); // array of cookies to pass + // $cookies["username"]="joe"; + var $rawheaders = array(); // array of raw headers to send + // $rawheaders["Content-type"]="text/html"; + + var $maxredirs = 5; // http redirection depth maximum. 0 = disallow + var $lastredirectaddr = ""; // contains address of last redirected address + var $offsiteok = true; // allows redirection off-site + var $maxframes = 0; // frame content depth maximum. 0 = disallow + var $expandlinks = true; // expand links to fully qualified URLs. + // this only applies to fetchlinks() + // submitlinks(), and submittext() + var $passcookies = true; // pass set cookies back through redirects + // NOTE: this currently does not respect + // dates, domains or paths. + + var $user = ""; // user for http authentication + var $pass = ""; // password for http authentication + + // http accept types + var $accept = "image/gif, image/x-xbitmap, image/jpeg, image/pjpeg, */*"; + + var $results = ""; // where the content is put + + var $error = ""; // error messages sent here + var $response_code = ""; // response code returned from server + var $headers = array(); // headers returned from server sent here + var $maxlength = 500000; // max return data length (body) + var $read_timeout = 0; // timeout on read operations, in seconds + // supported only since PHP 4 Beta 4 + // set to 0 to disallow timeouts + var $timed_out = false; // if a read operation timed out + var $status = 0; // http request status + + var $temp_dir = "/tmp"; // temporary directory that the webserver + // has permission to write to. + // under Windows, this should be C:\temp + + var $curl_path = "/usr/local/bin/curl"; + // Snoopy will use cURL for fetching + // SSL content if a full system path to + // the cURL binary is supplied here. + // set to false if you do not have + // cURL installed. See http://curl.haxx.se + // for details on installing cURL. + // Snoopy does *not* use the cURL + // library functions built into php, + // as these functions are not stable + // as of this Snoopy release. + + /**** Private variables ****/ + + var $_maxlinelen = 4096; // max line length (headers) + + var $_httpmethod = "GET"; // default http request method + var $_httpversion = "HTTP/1.0"; // default http request version + var $_submit_method = "POST"; // default submit method + var $_submit_type = "application/x-www-form-urlencoded"; // default submit type + var $_mime_boundary = ""; // MIME boundary for multipart/form-data submit type + var $_redirectaddr = false; // will be set if page fetched is a redirect + var $_redirectdepth = 0; // increments on an http redirect + var $_frameurls = array(); // frame src urls + var $_framedepth = 0; // increments on frame depth + + var $_isproxy = false; // set if using a proxy server + var $_fp_timeout = 30; // timeout for socket connection + +/*======================================================================*\ + Function: fetch + Purpose: fetch the contents of a web page + (and possibly other protocols in the + future like ftp, nntp, gopher, etc.) + Input: $URI the location of the page to fetch + Output: $this->results the output text from the fetch +\*======================================================================*/ + + function fetch($URI) + { + + //preg_match("|^([^:]+)://([^:/]+)(:[\d]+)*(.*)|",$URI,$URI_PARTS); + $URI_PARTS = parse_url($URI); + if (!empty($URI_PARTS["user"])) + $this->user = $URI_PARTS["user"]; + if (!empty($URI_PARTS["pass"])) + $this->pass = $URI_PARTS["pass"]; + if (empty($URI_PARTS["query"])) + $URI_PARTS["query"] = ''; + if (empty($URI_PARTS["path"])) + $URI_PARTS["path"] = ''; + + switch(strtolower($URI_PARTS["scheme"])) + { + case "http": + $this->host = $URI_PARTS["host"]; + if(!empty($URI_PARTS["port"])) + $this->port = $URI_PARTS["port"]; + if($this->_connect($fp)) + { + if($this->_isproxy) + { + // using proxy, send entire URI + $this->_httprequest($URI,$fp,$URI,$this->_httpmethod); + } + else + { + $path = $URI_PARTS["path"].($URI_PARTS["query"] ? "?".$URI_PARTS["query"] : ""); + // no proxy, send only the path + $this->_httprequest($path, $fp, $URI, $this->_httpmethod); + } + + $this->_disconnect($fp); + + if($this->_redirectaddr) + { + /* url was redirected, check if we've hit the max depth */ + if($this->maxredirs > $this->_redirectdepth) + { + // only follow redirect if it's on this site, or offsiteok is true + if(preg_match("|^http://".preg_quote($this->host)."|i",$this->_redirectaddr) || $this->offsiteok) + { + /* follow the redirect */ + $this->_redirectdepth++; + $this->lastredirectaddr=$this->_redirectaddr; + $this->fetch($this->_redirectaddr); + } + } + } + + if($this->_framedepth < $this->maxframes && count($this->_frameurls) > 0) + { + $frameurls = $this->_frameurls; + $this->_frameurls = array(); + + while(list(,$frameurl) = each($frameurls)) + { + if($this->_framedepth < $this->maxframes) + { + $this->fetch($frameurl); + $this->_framedepth++; + } + else + break; + } + } + } + else + { + return false; + } + return true; + break; + case "https": + if(!$this->curl_path) + return false; + if(function_exists("is_executable")) + if (!is_executable($this->curl_path)) + return false; + $this->host = $URI_PARTS["host"]; + if(!empty($URI_PARTS["port"])) + $this->port = $URI_PARTS["port"]; + if($this->_isproxy) + { + // using proxy, send entire URI + $this->_httpsrequest($URI,$URI,$this->_httpmethod); + } + else + { + $path = $URI_PARTS["path"].($URI_PARTS["query"] ? "?".$URI_PARTS["query"] : ""); + // no proxy, send only the path + $this->_httpsrequest($path, $URI, $this->_httpmethod); + } + + if($this->_redirectaddr) + { + /* url was redirected, check if we've hit the max depth */ + if($this->maxredirs > $this->_redirectdepth) + { + // only follow redirect if it's on this site, or offsiteok is true + if(preg_match("|^http://".preg_quote($this->host)."|i",$this->_redirectaddr) || $this->offsiteok) + { + /* follow the redirect */ + $this->_redirectdepth++; + $this->lastredirectaddr=$this->_redirectaddr; + $this->fetch($this->_redirectaddr); + } + } + } + + if($this->_framedepth < $this->maxframes && count($this->_frameurls) > 0) + { + $frameurls = $this->_frameurls; + $this->_frameurls = array(); + + while(list(,$frameurl) = each($frameurls)) + { + if($this->_framedepth < $this->maxframes) + { + $this->fetch($frameurl); + $this->_framedepth++; + } + else + break; + } + } + return true; + break; + default: + // not a valid protocol + $this->error = 'Invalid protocol "'.$URI_PARTS["scheme"].'"\n'; + return false; + break; + } + return true; + } + +/*======================================================================*\ + Function: submit + Purpose: submit an http form + Input: $URI the location to post the data + $formvars the formvars to use. + format: $formvars["var"] = "val"; + $formfiles an array of files to submit + format: $formfiles["var"] = "/dir/filename.ext"; + Output: $this->results the text output from the post +\*======================================================================*/ + + function submit($URI, $formvars="", $formfiles="") + { + unset($postdata); + + $postdata = $this->_prepare_post_body($formvars, $formfiles); + + $URI_PARTS = parse_url($URI); + if (!empty($URI_PARTS["user"])) + $this->user = $URI_PARTS["user"]; + if (!empty($URI_PARTS["pass"])) + $this->pass = $URI_PARTS["pass"]; + if (empty($URI_PARTS["query"])) + $URI_PARTS["query"] = ''; + if (empty($URI_PARTS["path"])) + $URI_PARTS["path"] = ''; + + switch(strtolower($URI_PARTS["scheme"])) + { + case "http": + $this->host = $URI_PARTS["host"]; + if(!empty($URI_PARTS["port"])) + $this->port = $URI_PARTS["port"]; + if($this->_connect($fp)) + { + if($this->_isproxy) + { + // using proxy, send entire URI + $this->_httprequest($URI,$fp,$URI,$this->_submit_method,$this->_submit_type,$postdata); + } + else + { + $path = $URI_PARTS["path"].($URI_PARTS["query"] ? "?".$URI_PARTS["query"] : ""); + // no proxy, send only the path + $this->_httprequest($path, $fp, $URI, $this->_submit_method, $this->_submit_type, $postdata); + } + + $this->_disconnect($fp); + + if($this->_redirectaddr) + { + /* url was redirected, check if we've hit the max depth */ + if($this->maxredirs > $this->_redirectdepth) + { + if(!preg_match("|^".$URI_PARTS["scheme"]."://|", $this->_redirectaddr)) + $this->_redirectaddr = $this->_expandlinks($this->_redirectaddr,$URI_PARTS["scheme"]."://".$URI_PARTS["host"]); + + // only follow redirect if it's on this site, or offsiteok is true + if(preg_match("|^http://".preg_quote($this->host)."|i",$this->_redirectaddr) || $this->offsiteok) + { + /* follow the redirect */ + $this->_redirectdepth++; + $this->lastredirectaddr=$this->_redirectaddr; + if( strpos( $this->_redirectaddr, "?" ) > 0 ) + $this->fetch($this->_redirectaddr); // the redirect has changed the request method from post to get + else + $this->submit($this->_redirectaddr,$formvars, $formfiles); + } + } + } + + if($this->_framedepth < $this->maxframes && count($this->_frameurls) > 0) + { + $frameurls = $this->_frameurls; + $this->_frameurls = array(); + + while(list(,$frameurl) = each($frameurls)) + { + if($this->_framedepth < $this->maxframes) + { + $this->fetch($frameurl); + $this->_framedepth++; + } + else + break; + } + } + + } + else + { + return false; + } + return true; + break; + case "https": + if(!$this->curl_path) + return false; + if(function_exists("is_executable")) + if (!is_executable($this->curl_path)) + return false; + $this->host = $URI_PARTS["host"]; + if(!empty($URI_PARTS["port"])) + $this->port = $URI_PARTS["port"]; + if($this->_isproxy) + { + // using proxy, send entire URI + $this->_httpsrequest($URI, $URI, $this->_submit_method, $this->_submit_type, $postdata); + } + else + { + $path = $URI_PARTS["path"].($URI_PARTS["query"] ? "?".$URI_PARTS["query"] : ""); + // no proxy, send only the path + $this->_httpsrequest($path, $URI, $this->_submit_method, $this->_submit_type, $postdata); + } + + if($this->_redirectaddr) + { + /* url was redirected, check if we've hit the max depth */ + if($this->maxredirs > $this->_redirectdepth) + { + if(!preg_match("|^".$URI_PARTS["scheme"]."://|", $this->_redirectaddr)) + $this->_redirectaddr = $this->_expandlinks($this->_redirectaddr,$URI_PARTS["scheme"]."://".$URI_PARTS["host"]); + + // only follow redirect if it's on this site, or offsiteok is true + if(preg_match("|^http://".preg_quote($this->host)."|i",$this->_redirectaddr) || $this->offsiteok) + { + /* follow the redirect */ + $this->_redirectdepth++; + $this->lastredirectaddr=$this->_redirectaddr; + if( strpos( $this->_redirectaddr, "?" ) > 0 ) + $this->fetch($this->_redirectaddr); // the redirect has changed the request method from post to get + else + $this->submit($this->_redirectaddr,$formvars, $formfiles); + } + } + } + + if($this->_framedepth < $this->maxframes && count($this->_frameurls) > 0) + { + $frameurls = $this->_frameurls; + $this->_frameurls = array(); + + while(list(,$frameurl) = each($frameurls)) + { + if($this->_framedepth < $this->maxframes) + { + $this->fetch($frameurl); + $this->_framedepth++; + } + else + break; + } + } + return true; + break; + + default: + // not a valid protocol + $this->error = 'Invalid protocol "'.$URI_PARTS["scheme"].'"\n'; + return false; + break; + } + return true; + } + +/*======================================================================*\ + Function: fetchlinks + Purpose: fetch the links from a web page + Input: $URI where you are fetching from + Output: $this->results an array of the URLs +\*======================================================================*/ + + function fetchlinks($URI) + { + if ($this->fetch($URI)) + { + if($this->lastredirectaddr) + $URI = $this->lastredirectaddr; + if(is_array($this->results)) + { + for($x=0;$x<count($this->results);$x++) + $this->results[$x] = $this->_striplinks($this->results[$x]); + } + else + $this->results = $this->_striplinks($this->results); + + if($this->expandlinks) + $this->results = $this->_expandlinks($this->results, $URI); + return true; + } + else + return false; + } + +/*======================================================================*\ + Function: fetchform + Purpose: fetch the form elements from a web page + Input: $URI where you are fetching from + Output: $this->results the resulting html form +\*======================================================================*/ + + function fetchform($URI) + { + + if ($this->fetch($URI)) + { + + if(is_array($this->results)) + { + for($x=0;$x<count($this->results);$x++) + $this->results[$x] = $this->_stripform($this->results[$x]); + } + else + $this->results = $this->_stripform($this->results); + + return true; + } + else + return false; + } + + +/*======================================================================*\ + Function: fetchtext + Purpose: fetch the text from a web page, stripping the links + Input: $URI where you are fetching from + Output: $this->results the text from the web page +\*======================================================================*/ + + function fetchtext($URI) + { + if($this->fetch($URI)) + { + if(is_array($this->results)) + { + for($x=0;$x<count($this->results);$x++) + $this->results[$x] = $this->_striptext($this->results[$x]); + } + else + $this->results = $this->_striptext($this->results); + return true; + } + else + return false; + } + +/*======================================================================*\ + Function: submitlinks + Purpose: grab links from a form submission + Input: $URI where you are submitting from + Output: $this->results an array of the links from the post +\*======================================================================*/ + + function submitlinks($URI, $formvars="", $formfiles="") + { + if($this->submit($URI,$formvars, $formfiles)) + { + if($this->lastredirectaddr) + $URI = $this->lastredirectaddr; + if(is_array($this->results)) + { + for($x=0;$x<count($this->results);$x++) + { + $this->results[$x] = $this->_striplinks($this->results[$x]); + if($this->expandlinks) + $this->results[$x] = $this->_expandlinks($this->results[$x],$URI); + } + } + else + { + $this->results = $this->_striplinks($this->results); + if($this->expandlinks) + $this->results = $this->_expandlinks($this->results,$URI); + } + return true; + } + else + return false; + } + +/*======================================================================*\ + Function: submittext + Purpose: grab text from a form submission + Input: $URI where you are submitting from + Output: $this->results the text from the web page +\*======================================================================*/ + + function submittext($URI, $formvars = "", $formfiles = "") + { + if($this->submit($URI,$formvars, $formfiles)) + { + if($this->lastredirectaddr) + $URI = $this->lastredirectaddr; + if(is_array($this->results)) + { + for($x=0;$x<count($this->results);$x++) + { + $this->results[$x] = $this->_striptext($this->results[$x]); + if($this->expandlinks) + $this->results[$x] = $this->_expandlinks($this->results[$x],$URI); + } + } + else + { + $this->results = $this->_striptext($this->results); + if($this->expandlinks) + $this->results = $this->_expandlinks($this->results,$URI); + } + return true; + } + else + return false; + } + + + +/*======================================================================*\ + Function: set_submit_multipart + Purpose: Set the form submission content type to + multipart/form-data +\*======================================================================*/ + function set_submit_multipart() + { + $this->_submit_type = "multipart/form-data"; + } + + +/*======================================================================*\ + Function: set_submit_normal + Purpose: Set the form submission content type to + application/x-www-form-urlencoded +\*======================================================================*/ + function set_submit_normal() + { + $this->_submit_type = "application/x-www-form-urlencoded"; + } + + + + +/*======================================================================*\ + Private functions +\*======================================================================*/ + + +/*======================================================================*\ + Function: _striplinks + Purpose: strip the hyperlinks from an html document + Input: $document document to strip. + Output: $match an array of the links +\*======================================================================*/ + + function _striplinks($document) + { + preg_match_all("'<\s*a\s.*?href\s*=\s* # find <a href= + ([\"\'])? # find single or double quote + (?(1) (.*?)\\1 | ([^\s\>]+)) # if quote found, match up to next matching + # quote, otherwise match up to next space + 'isx",$document,$links); + + + // catenate the non-empty matches from the conditional subpattern + + while(list($key,$val) = each($links[2])) + { + if(!empty($val)) + $match[] = $val; + } + + while(list($key,$val) = each($links[3])) + { + if(!empty($val)) + $match[] = $val; + } + + // return the links + return $match; + } + +/*======================================================================*\ + Function: _stripform + Purpose: strip the form elements from an html document + Input: $document document to strip. + Output: $match an array of the links +\*======================================================================*/ + + function _stripform($document) + { + preg_match_all("'<\/?(FORM|INPUT|SELECT|TEXTAREA|(OPTION))[^<>]*>(?(2)(.*(?=<\/?(option|select)[^<>]*>[\r\n]*)|(?=[\r\n]*))|(?=[\r\n]*))'Usi",$document,$elements); + + // catenate the matches + $match = implode("\r\n",$elements[0]); + + // return the links + return $match; + } + + + +/*======================================================================*\ + Function: _striptext + Purpose: strip the text from an html document + Input: $document document to strip. + Output: $text the resulting text +\*======================================================================*/ + + function _striptext($document) + { + + // I didn't use preg eval (//e) since that is only available in PHP 4.0. + // so, list your entities one by one here. I included some of the + // more common ones. + + $search = array("'<script[^>]*?>.*?</script>'si", // strip out javascript + "'<[\/\!]*?[^<>]*?>'si", // strip out html tags + "'([\r\n])[\s]+'", // strip out white space + "'&(quot|#34|#034|#x22);'i", // replace html entities + "'&(amp|#38|#038|#x26);'i", // added hexadecimal values + "'&(lt|#60|#060|#x3c);'i", + "'&(gt|#62|#062|#x3e);'i", + "'&(nbsp|#160|#xa0);'i", + "'&(iexcl|#161);'i", + "'&(cent|#162);'i", + "'&(pound|#163);'i", + "'&(copy|#169);'i", + "'&(reg|#174);'i", + "'&(deg|#176);'i", + "'&(#39|#039|#x27);'", + "'&(euro|#8364);'i", // europe + "'&a(uml|UML);'", // german + "'&o(uml|UML);'", + "'&u(uml|UML);'", + "'&A(uml|UML);'", + "'&O(uml|UML);'", + "'&U(uml|UML);'", + "'ß'i", + ); + $replace = array( "", + "", + "\\1", + "\"", + "&", + "<", + ">", + " ", + chr(161), + chr(162), + chr(163), + chr(169), + chr(174), + chr(176), + chr(39), + chr(128), + "ä", + "ö", + "ü", + "Ä", + "Ö", + "Ü", + "ß", + ); + + $text = preg_replace($search,$replace,$document); + + return $text; + } + +/*======================================================================*\ + Function: _expandlinks + Purpose: expand each link into a fully qualified URL + Input: $links the links to qualify + $URI the full URI to get the base from + Output: $expandedLinks the expanded links +\*======================================================================*/ + + function _expandlinks($links,$URI) + { + + preg_match("/^[^\?]+/",$URI,$match); + + $match = preg_replace("|/[^\/\.]+\.[^\/\.]+$|","",$match[0]); + $match = preg_replace("|/$|","",$match); + $match_part = parse_url($match); + $match_root = + $match_part["scheme"]."://".$match_part["host"]; + + $search = array( "|^http://".preg_quote($this->host)."|i", + "|^(\/)|i", + "|^(?!http://)(?!mailto:)|i", + "|/\./|", + "|/[^\/]+/\.\./|" + ); + + $replace = array( "", + $match_root."/", + $match."/", + "/", + "/" + ); + + $expandedLinks = preg_replace($search,$replace,$links); + + return $expandedLinks; + } + +/*======================================================================*\ + Function: _httprequest + Purpose: go get the http data from the server + Input: $url the url to fetch + $fp the current open file pointer + $URI the full URI + $body body contents to send if any (POST) + Output: +\*======================================================================*/ + + function _httprequest($url,$fp,$URI,$http_method,$content_type="",$body="") + { + $cookie_headers = ''; + if($this->passcookies && $this->_redirectaddr) + $this->setcookies(); + + $URI_PARTS = parse_url($URI); + if(empty($url)) + $url = "/"; + $headers = $http_method." ".$url." ".$this->_httpversion."\r\n"; + if(!empty($this->agent)) + $headers .= "User-Agent: ".$this->agent."\r\n"; + if(!empty($this->host) && !isset($this->rawheaders['Host'])) { + $headers .= "Host: ".$this->host; + if(!empty($this->port)) + $headers .= ":".$this->port; + $headers .= "\r\n"; + } + if(!empty($this->accept)) + $headers .= "Accept: ".$this->accept."\r\n"; + if(!empty($this->referer)) + $headers .= "Referer: ".$this->referer."\r\n"; + if(!empty($this->cookies)) + { + if(!is_array($this->cookies)) + $this->cookies = (array)$this->cookies; + + reset($this->cookies); + if ( count($this->cookies) > 0 ) { + $cookie_headers .= 'Cookie: '; + foreach ( $this->cookies as $cookieKey => $cookieVal ) { + $cookie_headers .= $cookieKey."=".urlencode($cookieVal)."; "; + } + $headers .= substr($cookie_headers,0,-2) . "\r\n"; + } + } + if(!empty($this->rawheaders)) + { + if(!is_array($this->rawheaders)) + $this->rawheaders = (array)$this->rawheaders; + while(list($headerKey,$headerVal) = each($this->rawheaders)) + $headers .= $headerKey.": ".$headerVal."\r\n"; + } + if(!empty($content_type)) { + $headers .= "Content-type: $content_type"; + if ($content_type == "multipart/form-data") + $headers .= "; boundary=".$this->_mime_boundary; + $headers .= "\r\n"; + } + if(!empty($body)) + $headers .= "Content-length: ".strlen($body)."\r\n"; + if(!empty($this->user) || !empty($this->pass)) + $headers .= "Authorization: Basic ".base64_encode($this->user.":".$this->pass)."\r\n"; + + //add proxy auth headers + if(!empty($this->proxy_user)) + $headers .= 'Proxy-Authorization: ' . 'Basic ' . base64_encode($this->proxy_user . ':' . $this->proxy_pass)."\r\n"; + + + $headers .= "\r\n"; + + // set the read timeout if needed + if ($this->read_timeout > 0) + socket_set_timeout($fp, $this->read_timeout); + $this->timed_out = false; + + fwrite($fp,$headers.$body,strlen($headers.$body)); + + $this->_redirectaddr = false; + unset($this->headers); + + while($currentHeader = fgets($fp,$this->_maxlinelen)) + { + if ($this->read_timeout > 0 && $this->_check_timeout($fp)) + { + $this->status=-100; + return false; + } + + if($currentHeader == "\r\n") + break; + + // if a header begins with Location: or URI:, set the redirect + if(preg_match("/^(Location:|URI:)/i",$currentHeader)) + { + // get URL portion of the redirect + preg_match("/^(Location:|URI:)[ ]+(.*)/i",chop($currentHeader),$matches); + // look for :// in the Location header to see if hostname is included + if(!preg_match("|\:\/\/|",$matches[2])) + { + // no host in the path, so prepend + $this->_redirectaddr = $URI_PARTS["scheme"]."://".$this->host.":".$this->port; + // eliminate double slash + if(!preg_match("|^/|",$matches[2])) + $this->_redirectaddr .= "/".$matches[2]; + else + $this->_redirectaddr .= $matches[2]; + } + else + $this->_redirectaddr = $matches[2]; + } + + if(preg_match("|^HTTP/|",$currentHeader)) + { + if(preg_match("|^HTTP/[^\s]*\s(.*?)\s|",$currentHeader, $status)) + { + $this->status= $status[1]; + } + $this->response_code = $currentHeader; + } + + $this->headers[] = $currentHeader; + } + + $results = ''; + do { + $_data = fread($fp, $this->maxlength); + if (strlen($_data) == 0) { + break; + } + $results .= $_data; + } while(true); + + if ($this->read_timeout > 0 && $this->_check_timeout($fp)) + { + $this->status=-100; + return false; + } + + // check if there is a a redirect meta tag + + if(preg_match("'<meta[\s]*http-equiv[^>]*?content[\s]*=[\s]*[\"\']?\d+;[\s]*URL[\s]*=[\s]*([^\"\']*?)[\"\']?>'i",$results,$match)) + + { + $this->_redirectaddr = $this->_expandlinks($match[1],$URI); + } + + // have we hit our frame depth and is there frame src to fetch? + if(($this->_framedepth < $this->maxframes) && preg_match_all("'<frame\s+.*src[\s]*=[\'\"]?([^\'\"\>]+)'i",$results,$match)) + { + $this->results[] = $results; + for($x=0; $x<count($match[1]); $x++) + $this->_frameurls[] = $this->_expandlinks($match[1][$x],$URI_PARTS["scheme"]."://".$this->host); + } + // have we already fetched framed content? + elseif(is_array($this->results)) + $this->results[] = $results; + // no framed content + else + $this->results = $results; + + return true; + } + +/*======================================================================*\ + Function: _httpsrequest + Purpose: go get the https data from the server using curl + Input: $url the url to fetch + $URI the full URI + $body body contents to send if any (POST) + Output: +\*======================================================================*/ + + function _httpsrequest($url,$URI,$http_method,$content_type="",$body="") + { + if($this->passcookies && $this->_redirectaddr) + $this->setcookies(); + + $headers = array(); + + $URI_PARTS = parse_url($URI); + if(empty($url)) + $url = "/"; + // GET ... header not needed for curl + //$headers[] = $http_method." ".$url." ".$this->_httpversion; + if(!empty($this->agent)) + $headers[] = "User-Agent: ".$this->agent; + if(!empty($this->host)) + if(!empty($this->port)) + $headers[] = "Host: ".$this->host.":".$this->port; + else + $headers[] = "Host: ".$this->host; + if(!empty($this->accept)) + $headers[] = "Accept: ".$this->accept; + if(!empty($this->referer)) + $headers[] = "Referer: ".$this->referer; + if(!empty($this->cookies)) + { + if(!is_array($this->cookies)) + $this->cookies = (array)$this->cookies; + + reset($this->cookies); + if ( count($this->cookies) > 0 ) { + $cookie_str = 'Cookie: '; + foreach ( $this->cookies as $cookieKey => $cookieVal ) { + $cookie_str .= $cookieKey."=".urlencode($cookieVal)."; "; + } + $headers[] = substr($cookie_str,0,-2); + } + } + if(!empty($this->rawheaders)) + { + if(!is_array($this->rawheaders)) + $this->rawheaders = (array)$this->rawheaders; + while(list($headerKey,$headerVal) = each($this->rawheaders)) + $headers[] = $headerKey.": ".$headerVal; + } + if(!empty($content_type)) { + if ($content_type == "multipart/form-data") + $headers[] = "Content-type: $content_type; boundary=".$this->_mime_boundary; + else + $headers[] = "Content-type: $content_type"; + } + if(!empty($body)) + $headers[] = "Content-length: ".strlen($body); + if(!empty($this->user) || !empty($this->pass)) + $headers[] = "Authorization: BASIC ".base64_encode($this->user.":".$this->pass); + + for($curr_header = 0; $curr_header < count($headers); $curr_header++) { + $safer_header = strtr( $headers[$curr_header], "\"", " " ); + $cmdline_params .= " -H \"".$safer_header."\""; + } + + if(!empty($body)) + $cmdline_params .= " -d \"$body\""; + + if($this->read_timeout > 0) + $cmdline_params .= " -m ".$this->read_timeout; + + $headerfile = tempnam($temp_dir, "sno"); + + $safer_URI = strtr( $URI, "\"", " " ); // strip quotes from the URI to avoid shell access + exec($this->curl_path." -D \"$headerfile\"".$cmdline_params." \"".$safer_URI."\"",$results,$return); + + if($return) + { + $this->error = "Error: cURL could not retrieve the document, error $return."; + return false; + } + + + $results = implode("\r\n",$results); + + $result_headers = file("$headerfile"); + + $this->_redirectaddr = false; + unset($this->headers); + + for($currentHeader = 0; $currentHeader < count($result_headers); $currentHeader++) + { + + // if a header begins with Location: or URI:, set the redirect + if(preg_match("/^(Location: |URI: )/i",$result_headers[$currentHeader])) + { + // get URL portion of the redirect + preg_match("/^(Location: |URI:)\s+(.*)/",chop($result_headers[$currentHeader]),$matches); + // look for :// in the Location header to see if hostname is included + if(!preg_match("|\:\/\/|",$matches[2])) + { + // no host in the path, so prepend + $this->_redirectaddr = $URI_PARTS["scheme"]."://".$this->host.":".$this->port; + // eliminate double slash + if(!preg_match("|^/|",$matches[2])) + $this->_redirectaddr .= "/".$matches[2]; + else + $this->_redirectaddr .= $matches[2]; + } + else + $this->_redirectaddr = $matches[2]; + } + + if(preg_match("|^HTTP/|",$result_headers[$currentHeader])) + $this->response_code = $result_headers[$currentHeader]; + + $this->headers[] = $result_headers[$currentHeader]; + } + + // check if there is a a redirect meta tag + + if(preg_match("'<meta[\s]*http-equiv[^>]*?content[\s]*=[\s]*[\"\']?\d+;[\s]*URL[\s]*=[\s]*([^\"\']*?)[\"\']?>'i",$results,$match)) + { + $this->_redirectaddr = $this->_expandlinks($match[1],$URI); + } + + // have we hit our frame depth and is there frame src to fetch? + if(($this->_framedepth < $this->maxframes) && preg_match_all("'<frame\s+.*src[\s]*=[\'\"]?([^\'\"\>]+)'i",$results,$match)) + { + $this->results[] = $results; + for($x=0; $x<count($match[1]); $x++) + $this->_frameurls[] = $this->_expandlinks($match[1][$x],$URI_PARTS["scheme"]."://".$this->host); + } + // have we already fetched framed content? + elseif(is_array($this->results)) + $this->results[] = $results; + // no framed content + else + $this->results = $results; + + unlink("$headerfile"); + + return true; + } + +/*======================================================================*\ + Function: setcookies() + Purpose: set cookies for a redirection +\*======================================================================*/ + + function setcookies() + { + for($x=0; $x<count($this->headers); $x++) + { + if(preg_match('/^set-cookie:[\s]+([^=]+)=([^;]+)/i', $this->headers[$x],$match)) + $this->cookies[$match[1]] = urldecode($match[2]); + } + } + + +/*======================================================================*\ + Function: _check_timeout + Purpose: checks whether timeout has occurred + Input: $fp file pointer +\*======================================================================*/ + + function _check_timeout($fp) + { + if ($this->read_timeout > 0) { + $fp_status = socket_get_status($fp); + if ($fp_status["timed_out"]) { + $this->timed_out = true; + return true; + } + } + return false; + } + +/*======================================================================*\ + Function: _connect + Purpose: make a socket connection + Input: $fp file pointer +\*======================================================================*/ + + function _connect(&$fp) + { + if(!empty($this->proxy_host) && !empty($this->proxy_port)) + { + $this->_isproxy = true; + + $host = $this->proxy_host; + $port = $this->proxy_port; + } + else + { + $host = $this->host; + $port = $this->port; + } + + $this->status = 0; + + if($fp = fsockopen( + $host, + $port, + $errno, + $errstr, + $this->_fp_timeout + )) + { + // socket connection succeeded + + return true; + } + else + { + // socket connection failed + $this->status = $errno; + switch($errno) + { + case -3: + $this->error="socket creation failed (-3)"; + case -4: + $this->error="dns lookup failure (-4)"; + case -5: + $this->error="connection refused or timed out (-5)"; + default: + $this->error="connection failed (".$errno.")"; + } + return false; + } + } +/*======================================================================*\ + Function: _disconnect + Purpose: disconnect a socket connection + Input: $fp file pointer +\*======================================================================*/ + + function _disconnect($fp) + { + return(fclose($fp)); + } + + +/*======================================================================*\ + Function: _prepare_post_body + Purpose: Prepare post body according to encoding type + Input: $formvars - form variables + $formfiles - form upload files + Output: post body +\*======================================================================*/ + + function _prepare_post_body($formvars, $formfiles) + { + settype($formvars, "array"); + settype($formfiles, "array"); + $postdata = ''; + + if (count($formvars) == 0 && count($formfiles) == 0) + return; + + switch ($this->_submit_type) { + case "application/x-www-form-urlencoded": + reset($formvars); + while(list($key,$val) = each($formvars)) { + if (is_array($val) || is_object($val)) { + while (list($cur_key, $cur_val) = each($val)) { + $postdata .= urlencode($key)."[]=".urlencode($cur_val)."&"; + } + } else + $postdata .= urlencode($key)."=".urlencode($val)."&"; + } + break; + + case "multipart/form-data": + $this->_mime_boundary = "Snoopy".md5(uniqid(microtime())); + + reset($formvars); + while(list($key,$val) = each($formvars)) { + if (is_array($val) || is_object($val)) { + while (list($cur_key, $cur_val) = each($val)) { + $postdata .= "--".$this->_mime_boundary."\r\n"; + $postdata .= "Content-Disposition: form-data; name=\"$key\[\]\"\r\n\r\n"; + $postdata .= "$cur_val\r\n"; + } + } else { + $postdata .= "--".$this->_mime_boundary."\r\n"; + $postdata .= "Content-Disposition: form-data; name=\"$key\"\r\n\r\n"; + $postdata .= "$val\r\n"; + } + } + + reset($formfiles); + while (list($field_name, $file_names) = each($formfiles)) { + settype($file_names, "array"); + while (list(, $file_name) = each($file_names)) { + if (!is_readable($file_name)) continue; + + $fp = fopen($file_name, "r"); + $file_content = fread($fp, filesize($file_name)); + fclose($fp); + $base_name = basename($file_name); + + $postdata .= "--".$this->_mime_boundary."\r\n"; + $postdata .= "Content-Disposition: form-data; name=\"$field_name\"; filename=\"$base_name\"\r\n\r\n"; + $postdata .= "$file_content\r\n"; + } + } + $postdata .= "--".$this->_mime_boundary."--\r\n"; + break; + } + + return $postdata; + } +} + +?> |