elialejandro · July 22, 2015 05:00
diff --git a/gethtml.php b/gethtml.php
 <?php 

 $url = 'http://consultas.curp.gob.mx/CurpSP/';

 // disguises the curl using fake headers and a fake user agent.
 function disguise_curl($url)
 {
  $curl = curl_init();

  // Setup headers - I used the same headers from Firefox version 2.0.0.6
  // below was split up because php.net said the line was too long. :/
  $header[0] = "Accept: text/xml,application/xml,application/xhtml+xml,";
  $header[0] .= "text/html;q=0.9,text/plain;q=0.8,image/png,*/*;q=0.5";
  $header[] = "Cache-Control: max-age=0";
  $header[] = "Connection: keep-alive";
  $header[] = "Keep-Alive: 300";
  $header[] = "Accept-Charset: ISO-8859-1,utf-8;q=0.7,*;q=0.7";
  $header[] = "Accept-Language: en-us,en;q=0.5";
  $header[] = "Pragma: "; // browsers keep this blank.

  curl_setopt($curl, CURLOPT_URL, $url);
  curl_setopt($curl, CURLOPT_USERAGENT, 'Googlebot/2.1 (+http://www.google.com/bot.html)');
  curl_setopt($curl, CURLOPT_HTTPHEADER, $header);
  curl_setopt($curl, CURLOPT_REFERER, 'http://www.google.com');
  curl_setopt($curl, CURLOPT_ENCODING, 'gzip,deflate');
  curl_setopt($curl, CURLOPT_AUTOREFERER, true);
  curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);
  curl_setopt($curl, CURLOPT_TIMEOUT, 10);

  $html = curl_exec($curl); // execute the curl command
  curl_close($curl); // close the connection

  return $html; // and finally, return $html
 }

 // uses the function and displays the text off the website
 $text = "<html>" . disguise_curl($url);
 $text = "<html>" . preg_replace('/<[\/]?html>/', "",$text) . "</html>";
 // $xml = new SimpleXMLElement($text);
 $doc = new DOMDocument();
 $doc->loadHTML('<?xml encoding="UTF-8">' .$text);
 include 'Zend/Debug.php';
 Zend_Debug::dump($doc->getElementsByTagName("img"));
 foreach ($doc->getElementsByTagName("img") as $item) {
    Zend_Debug::dump($item->getAttribute("src"));
    echo "http://consultas.curp.gob.mx/CurpSP/" . $item->getAttribute("src");
 }
	<?php

	$url = 'http://consultas.curp.gob.mx/CurpSP/';

	// disguises the curl using fake headers and a fake user agent.
	function disguise_curl($url)
	{
	$curl = curl_init();

	// Setup headers - I used the same headers from Firefox version 2.0.0.6
	// below was split up because php.net said the line was too long. :/
	$header[0] = "Accept: text/xml,application/xml,application/xhtml+xml,";
	$header[0] .= "text/html;q=0.9,text/plain;q=0.8,image/png,/;q=0.5";
	$header[] = "Cache-Control: max-age=0";
	$header[] = "Connection: keep-alive";
	$header[] = "Keep-Alive: 300";
	$header[] = "Accept-Charset: ISO-8859-1,utf-8;q=0.7,*;q=0.7";
	$header[] = "Accept-Language: en-us,en;q=0.5";
	$header[] = "Pragma: "; // browsers keep this blank.

	curl_setopt($curl, CURLOPT_URL, $url);
	curl_setopt($curl, CURLOPT_USERAGENT, 'Googlebot/2.1 (+http://www.google.com/bot.html)');
	curl_setopt($curl, CURLOPT_HTTPHEADER, $header);
	curl_setopt($curl, CURLOPT_REFERER, 'http://www.google.com');
	curl_setopt($curl, CURLOPT_ENCODING, 'gzip,deflate');
	curl_setopt($curl, CURLOPT_AUTOREFERER, true);
	curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);
	curl_setopt($curl, CURLOPT_TIMEOUT, 10);

	$html = curl_exec($curl); // execute the curl command
	curl_close($curl); // close the connection

	return $html; // and finally, return $html
	}

	// uses the function and displays the text off the website
	$text = "<html>" . disguise_curl($url);
	$text = "<html>" . preg_replace('/<[\/]?html>/', "",$text) . "</html>";
	// $xml = new SimpleXMLElement($text);
	$doc = new DOMDocument();
	$doc->loadHTML('<?xml encoding="UTF-8">' .$text);
	include 'Zend/Debug.php';
	Zend_Debug::dump($doc->getElementsByTagName("img"));
	foreach ($doc->getElementsByTagName("img") as $item) {
	Zend_Debug::dump($item->getAttribute("src"));
	echo "http://consultas.curp.gob.mx/CurpSP/" . $item->getAttribute("src");
	}