topical media & game development

topical media & game development

[] readme course(s) preface I 1 2 II 3 4 III 5 6 7 IV 8 9 10 V 11 12 afterthought(s) appendix reference(s) example(s) resource(s) _

alt-bot-src-10-anonymous-browsing-proxy.php / php


  <?php
  /*

#################################################################

W3Cr SOFTWARE NOTICE AND LICENSE www.w3.org/Consortium/Legal/2002/copyright-software-20021231 This work (and included software, documentation such as READMEs, or other related items) is being provided by the copyright holders under the following license. By obtaining, using and/or copying this work, you (the licensee) agree that you have read, understood, and will comply with the following terms and conditions. Permission to copy, modify, and distribute this software and its documentation, with or without modification, for any purpose and without fee or royalty is hereby granted, provided that you include the following on ALL copies of the software and documentation or portions thereof, including modifications: 1.The full text of this NOTICE in a location viewable to users of the redistributed or derivative work. 2.Any pre-existing intellectual property disclaimers, notices, or terms and conditions. If none exist, the W3C Software Short Notice should be included (hypertext is preferred, text is permitted) within the body of any redistributed or derivative code. 3.Notice of any changes or modifications to the files, including the date changes were made. (We recommend you provide URIs to the location from which the code is derived.) THIS SOFTWARE AND DOCUMENTATION IS PROVIDED "AS IS," AND COPYRIGHT HOLDERS MAKE NO REPRESENTATIONS OR WARRANTIES, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO, WARRANTIES OF MERCHANTABILITY OR FITNESS FOR ANY PARTICULAR PURPOSE OR THAT THE USE OF THE SOFTWARE OR DOCUMENTATION WILL NOT INFRINGE ANY THIRD PARTY PATENTS, COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS. COPYRIGHT HOLDERS WILL NOT BE LIABLE FOR ANY DIRECT, INDIRECT, SPECIAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF ANY USE OF THE SOFTWARE OR DOCUMENTATION. The name and trademarks of copyright holders may NOT be used in advertising or publicity pertaining to the software without specific, written prior permission. Title to copyright in this software and any associated documentation will at all times remain with copyright holders. Copyright 2007, Michael Schrenk THIS SCRIPT IS FOR DEMONSTRATION PURPOSES ONLY! It is not suitable for any use other than demonstrating the concepts presented in Webbots, Spiders and Screen Scrapers.
#################################################################




  */?>
  
  <?php

###########################################################




  # Example: Uaing a webbot/proxy to facilitate anonomous web browsing
  #-----------------------------------------------------------------  
  include(<alt-bot-lib-parse.php>);    # include parse library
  include(<alt-bot-lib-http.php>); # include download library
  include(<alt-bot-lib-resolve-addresses.php>);
  
  # Detect the name of this web page
   $this_server =$ _SERVER['HTTP_HOST'];
   $this_script =$ _SERVER['SCRIPT_NAME'];
   $this_page = "http://".$ this_server. $this_script;
  
  # Identify target
  if(isset($ _GET['v']))
       $target_webpage =$ _GET['v'];
  if(isset( $_GET['target_from_text_box']))$ target_webpage = base64_encode( $_GET['target_from_text_box']);
  
  if(!isset($ target_webpage))
       $target_webpage = base64_encode("http://www.schrenk.com");
  
  ?>$ <table bgcolor="black" width="100%">
      <tr valign="bottom"><form name="proxy">
          <td align="left"><font color="white" size="5"><b>Anonymous<br>Browsing Proxy</b></font></td>
          <td align="right"><font color="white" size="4">Page:</font></td>
          <td width="100"><input type="textbox" name="target_from_text_box"></td>
          <td valign="left">&nbsp;<font color="white">[GO]</font></a>&nbsp;</td>
          </form>    
          <td width="20">&nbsp;</td>
          <td><font color="white" size="3">Proxied Page: <?echo base64_decode(target_webpage);?></font></td>
      </tr>
  </table>
      
      
  <?    
  # Download the target web page, which we will use to identify images
   $page_array = http_get(base64_decode($ target_webpage),  $ref="", GET,$ data_array="", EXCL_HEAD);
  
  # Clean-up the HTML formatting with TIDY
   $web_page = tidy_html($ page_array['FILE']);
  
  # Get the base page address for this page (so we can later obtain fully resolved addresses) 
   $page_base = get_base_page_address($ page_array['STATUS']['url']);
  
  # Remove javascript and HTML comments from web page
   $web_page = remove($ web_page, "<script", "</script>");
   $web_page = remove($ web_page, "<!--", "-->");

################################################




  # Set the relative address for this page so images etc
  # resolve.
  #------------------------------------------------------
   $new_base_value = "$ <base href=\"".page_base."\">";
  if(!stristr( $web_page, "$ <base"))
      {
      # If there is a <head>, insert <BASE> at beginning of <head></head>
      if(stristr(web_page, "<head"))
          {
           $web_page = eregi_replace("<Head>", "<Head>\n".$ new_base_value,  $web_page);
          }
      # Else insert a$ <head><base></head> at beginning of web page
      else 
          {
          web_page = "</head>\n". $new_base_value."\n$ </head>" . web_page;
          }
      }
  # Endof Set Page <BASE>

################################################




  # Start: href substitutions
  #------------------------------------------------------
  
  # Create an array of parsed anchor tags
   $a_tag_array = parse_array($ web_page, "<a", ">");
  for( $xx=0;$ xx<count( $a_tag_array);$ xx++)
      {
      // Get the original href value
       $original_href = get_attribute($ a_tag_array[ $xx], "href");
      // Convert href to a fully resolved address$ fully_resolved_href = get_fully_resolved_address( $original_href,$ page_base);
      
      // Substitute the original href with "this_page?v=fully resolved address"
       $substitution_tag = str_replace($ original_href, trim( $this_page."?v=".base64_encode($ fully_resolved_href)),   $a_tag_array[$ xx]);
  
      // Substitute the original tag with the new one
       $web_page = str_replace($ a_tag_array[ $xx],$ substitution_tag,  $web_page);
      }
  # Endof: href substitutions$

################################################


  
  # Display the target web page
  echo web_page;
  ?>

[] readme course(s) preface I 1 2 II 3 4 III 5 6 7 IV 8 9 10 V 11 12 afterthought(s) appendix reference(s) example(s) resource(s) _

You may not copy or print any of this material without explicit permission of the author or the publisher. In case of other copyright issues, contact the author.