Monday, 13 August 2018

Convert A sitemap.xml File To A HTML Sitemap With PHP

I have already talked about converting a sitemap.xml file into a urllist.txt file, but what if you want to create a HTML sitemap? If you have a sitemap.xml file then you can use this to spider your site, scrape the contents of each page and populate the HTML file with this information.
The following code does this. For every page it looks for the title tag, the description meta tag and the first h2 tag on the page. These items are then used to construct a segment of HTML for that page.
    

  1. 
<?php
    

    2. 

  2. 
$header = '<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
    

    3. 

  3. 
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
    

    4. 

  4. 
<head>
    

    5. 

  5. 
<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1" />
    

    6. 

  6. 
<title>HTML Sitemap</title>
    

    7. 

  7. 
</head>
    

    8. 

  8. 
<body>';
    

    9. 

  9. 
 
    

    10. 

  10. 
set_time_limit(400);
    

    11. 

  11. 
 
    

    12. 

  12. 
$currentElement = '';
    

    13. 

  13. 
$currentLoc = '';
    

    14. 

  14. 
 
    

    15. 

  15. 
$map = "<h1>HTML Sitemap</h1>"."\n";
    

    16. 

  16. 
 
    

    17. 

  17. 
function parsePage($data)
    

    18. 

  18. 
{
    

    19. 

  19. 
 global $map;
    

    20. 

  20. 
 /*
    

    21. 

  21. 
 if you want to trap a certain file extention then use the syntax below...
    

    22. 

  22. 
 stripos($data, ".php")>0
    

    23. 

  23. 
 stripos($data, ".htm")>0
    

    24. 

  24. 
 stripos($data, ".asp")>0
    

    25. 

  25. 
 */
    

    26. 

  26. 
 if ( stripos($data,".pdf") > 0 ) {
    

    27. 

  27. 
  // if the url is a pdf document.
    

    28. 

  28. 
  $map .= '<p><a href="'.$data.'">PDF document.</a></p>'."\n";
    

    29. 

  29. 
  $map .= '<p>A pdf document.</p>'."\n";
    

    30. 

  30. 
 } elseif ( stripos($data, ".txt")>0 ) {
    

    31. 

  31. 
  // if the url is a text document
    

    32. 

  32. 
  $map .= '<p><a href="'.$data.'">Text document.</a></p>'."\n";
    

    33. 

  33. 
  $map .= '<p>A text document.</p>'."\n";
    

    34. 

  34. 
 } else {
    

    35. 

  35. 
  // try to open it anyway...
    

    36. 

  36. 
  // make sure that you can read the file
    

    37. 

  37. 
  if ( $urlh = @fopen($data, 'rb') ) {
    

    38. 

  38. 
   $contents = '';
    

    39. 

  39. 
   //check php version
    

    40. 

  40. 
   if ( phpversion()>5 ) {
    

    41. 

  41. 
    $contents = stream_get_contents($urlh);
    

    42. 

  42. 
   } else {
    

    43. 

  43. 
    while ( !feof($urlh) ) {
    

    44. 

  44. 
     $contents .= fread($urlh, 8192);
    

    45. 

  45. 
    };
    

    46. 

  46. 
   };
    

    47. 

  47. 
 
    

    48. 

  48. 
   // find the title
    

    49. 

  49. 
   preg_match('/(?<=\<[Tt][Ii][Tt][Ll][Ee]\>)\s*?(.*?)\s*?(?=\<\/[Tt][Ii][Tt][Ll][Ee]\>)/U', $contents, $title);
    

    50. 

  50. 
   $title = $title[0];
    

    51. 

  51. 
 
    

    52. 

  52. 
   // find the first h1 tag
    

    53. 

  53. 
   $header = array();
    

    54. 

  54. 
   preg_match('/(?<=\<[Hh]2\>)(.*?)(?=\<\/[Hh]2\>)/U', $contents, $header);
    

    55. 

  55. 
   $header = strip_tags($header[0]);
    

    56. 

  56. 
 
    

    57. 

  57. 
   if ( strlen($title) > 0 && strlen($header) > 0 ) {
    

    58. 

  58. 
    // print the title and h1 tag in combo
    

    59. 

  59. 
    $map .= '<p class="link"><a href="'.str_replace('&','&amp;',$data).'" title="'.(strlen($header)>0?trim($header):trim($title)).'">'.trim($title).(strlen($header)>0?" - ".trim($header):'').'</a></p>'."\n";
    

    60. 

  60. 
   } elseif ( strlen($title) > 0 ) {
    

    61. 

  61. 
    $map .= '<p class="link"><a href="'.str_replace('&','&amp;',$data).'" title="'.trim($title).'">'.trim($title).'</a></p>'."\n";
    

    62. 

  62. 
   } elseif ( strlen($header) > 0 ) {
    

    63. 

  63. 
    $map .= '<p class="link"><a href="'.str_replace('&','&amp;',$data).'" title="'.trim($header).'">'.trim($header).'</a></p>'."\n";
    

    64. 

  64. 
   };
    

    65. 

  65. 
 
    

    66. 

  66. 
   // find description
    

    67. 

  67. 
   preg_match('/(?<=\<[Mm][Ee][Tt][Aa]\s[Nn][Aa][Mm][Ee]\=\"[Dd]escription\" content\=\")(.*?)(?="\s*?\/?\>)/U', $contents, $description);
    

    68. 

  68. 
   $description = $description[0];
    

    69. 

  69. 
 
    

    70. 

  70. 
   // print description
    

    71. 

  71. 
   if ( strlen($description)>0 ) {
    

    72. 

  72. 
    $map .= '<p class="desc">'.trim($description).'</p>'."\n";
    

    73. 

  73. 
   };
    

    74. 

  74. 
   // close the file
    

    75. 

  75. 
   fclose($urlh);
    

    76. 

  76. 
  };
    

    77. 

  77. 
 };
    

    78. 

  78. 
};
    

    79. 

  79. 
 
    

    80. 

  80. 
/////////// XML PARSE FUNCTIONS HERE /////////////
    

    81. 

  81. 
// the start element function
    

    82. 

  82. 
function startElement($xmlParser, $name, $attribs)
    

    83. 

  83. 
{
    

    84. 

  84. 
 global $currentElement;
    

    85. 

  85. 
 $currentElement = $name;
    

    86. 

  86. 
};
    

    87. 

  87. 
 
    

    88. 

  88. 
// the end element function
    

    89. 

  89. 
function endElement($parser, $name)
    

    90. 

  90. 
{
    

    91. 

  91. 
 global $currentElement,$currentLoc;
    

    92. 

  92. 
 if ( $currentElement == 'loc') {
    

    93. 

  93. 
  parsePage($currentLoc);
    

    94. 

  94. 
  $currentLoc = '';
    

    95. 

  95. 
 };
    

    96. 

  96. 
 $currentElement = '';
    

    97. 

  97. 
};
    

    98. 

  98. 
 
    

    99. 

  99. 
// the character data function
    

    100. 

  100. 
function characterData($parser, $data) 
    

    101. 

  101. 
{
    

    102. 

  102. 
 global $currentElement,$currentLoc;
    

    103. 

  103. 
 // if the current element is loc then it will be a url
    

    104. 

  104. 
 if ( $currentElement == 'loc' ) {
    

    105. 

  105. 
  $currentLoc .= $data;
    

    106. 

  106. 
 };
    

    107. 

  107. 
};
    

    108. 

  108. 
 
    

    109. 

  109. 
// create parse object
    

    110. 

  110. 
$xml_parser = xml_parser_create();
    

    111. 

  111. 
// turn off case folding!
    

    112. 

  112. 
xml_parser_set_option($xml_parser, XML_OPTION_CASE_FOLDING, false);
    

    113. 

  113. 
// set start and end element functions
    

    114. 

  114. 
xml_set_element_handler($xml_parser,"startElement", "endElement");
    

    115. 

  115. 
// set character data function
    

    116. 

  116. 
xml_set_character_data_handler($xml_parser, "characterData");
    

    117. 

  117. 
 
    

    118. 

  118. 
// open xml file
    

    119. 

  119. 
if ( !($fp = fopen('sitemap.xml', "r")) ) {
    

    120. 

  120. 
 die("could not open XML input");
    

    121. 

  121. 
};
    

    122. 

  122. 
 
    

    123. 

  123. 
// read the file - print error if something went wrong.
    

    124. 

  124. 
while ( $data = fread($fp,4096) ) {
    

    125. 

  125. 
 if ( !xml_parse($xml_parser, $data,feof($fp)) ) {
    

    126. 

  126. 
  die(sprintf("XML error: %s at line %d",xml_error_string(xml_get_error_code($xml_parser)), xml_get_current_line_number($xml_parser)));
    

    127. 

  127. 
 };
    

    128. 

  128. 
};
    

    129. 

  129. 
 
    

    130. 

  130. 
// close file
    

    131. 

  131. 
fclose($fp);
    

    132. 

  132. 
 
    

    133. 

  133. 
$footer = '</body>
    

    134. 

  134. 
</html>';
    

    135. 

  135. 
 
    

    136. 

  136. 
// write output to a file
    

    137. 

  137. 
$fp = fopen('sitemap.html', "w+");
    

    138. 

  138. 
fwrite($fp,$header.$map.$footer);
    

    139. 

  139. 
fclose($fp);
    

    140. 

  140. 
 
    

    141. 

  141. 
// print output
    

    142. 

  142. 
echo $header.$map.$footer;
    

    143.
This script prints out the sitemap and also saves the sitemap to a file for later use. This is essential as the script can take a long time to run due to all of the page accessing that it has to do.
This script is fairly complicated and has gone through several versions since I first created it so if you find any improvements or bugs then let me know and I will incorporate them.

0 comments:

Post a Comment

Subscribe to: Post Comments (Atom)