From 584e0016f2d27ea8d40e96bf9a312ad0518bd503 Mon Sep 17 00:00:00 2001 From: Antonio Ospite Date: Mon, 16 May 2016 13:10:28 +0200 Subject: [PATCH 1/1] tweeper.php: make json_to_xml() do strictly what its name says Extracting the json data from the HTML does not really belong to the json_to_xml() function. --- tweeper.php | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-) diff --git a/tweeper.php b/tweeper.php index bed6350..0034a0d 100644 --- a/tweeper.php +++ b/tweeper.php @@ -182,18 +182,11 @@ class Tweeper { return $xsltProcessor; } - private function json_to_xml($html, $json_match_expr, $rootName) { - // pre-process, convert json to XML - $ret = preg_match($json_match_expr, $html, $matches); - if ($ret !== 1) { - trigger_error("Cannot match expression: $json_match_expr\n", E_USER_ERROR); - return NULL; - } - + private function json_to_xml($json, $rootName) { // Apparenty the ObjectNormalizer used afterwards is not able to handle // the stdClass object created by json_decode() with the default setting // $assoc = false; so use $assoc = true - $data = json_decode($matches[1], $assoc = true); + $data = json_decode($json, $assoc = true); if (!$data) { return NULL; } @@ -218,7 +211,15 @@ class Tweeper { } private function get_xml_instagram_com($html) { - return $this->json_to_xml($html, '/window._sharedData = (.*);/', 'instagram'); + // extract the json data from the html code + $json_match_expr = '/window._sharedData = (.*);/'; + $ret = preg_match($json_match_expr, $html, $matches); + if ($ret !== 1) { + trigger_error("Cannot match expression: $json_match_expr\n", E_USER_ERROR); + return NULL; + } + + return $this->json_to_xml($matches[1], 'instagram'); } private function preprocess_html_facebook_com($html) { -- 2.1.4