Universal classes for XML/HTML scraping

1 files changed, 44 insertions, 0 deletions

diff --git a/providers/HtmlFeed.php b/providers/HtmlFeed.php
new file mode 100644
index 0000000..411cddf
--- /dev/null
+++ b/providers/HtmlFeed.php
@@ -0,0 +1,44 @@
+<?php
+
+namespace Providers;
+
+require_once('XmlFeed.php');
+require_once('../lib/querypath/src/qp.php');
+
+abstract class HtmlFeed extends \Providers\XmlFeed {
+
+    const HTML_FEED_USER_AGENT = 'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US; rv:1.9.0.11) Gecko/2009060215 Firefox/3.0.11 (.NET CLR 3.5.30729)';
+
+    private $_encoding;
+
+    private function __getHttpContent($feedUrl) {
+        $header = array();
+        $header[] = 'Accept: text/xml,application/xml,application/xhtml+xml,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[] = 'Pragma: ';
+        $ch = curl_init($feedUrl);
+        curl_setopt($ch, CURLOPT_USERAGENT, self::HTML_FEED_USER_AGENT);
+        curl_setopt($ch, CURLOPT_HTTPHEADER, $header);
+        curl_setopt($ch, CURLOPT_AUTOREFERER, TRUE);
+        curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
+        curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1);
+        curl_setopt($ch, CURLOPT_ENCODING, '');
+        curl_setopt($ch, CURLOPT_TIMEOUT, 20);
+        $page = curl_exec($ch);
+        curl_close ($ch);
+        $this->_encoding = mb_detect_encoding($page);
+        return $page;
+    }
+
+    protected function _fetchItems() {
+        $page = $this->__getHttpContent($this->_feedUrl);
+        $this->_feedXml = htmlqp($page, NULL, ['convert_from_encoding' => $this->_encoding, 'convert_to_encoding' => $this->_encoding]);
+        return $this->_parseFeedContent($this->_feedXml);
+    }
+
+}
+
+?>