3 * tweeper - a Twitter to RSS web scraper
5 * Copyright (C) 2013 Antonio Ospite <ospite@studenti.unina.it>
7 * This program is free software: you can redistribute it and/or modify
8 * it under the terms of the GNU General Public License as published by
9 * the Free Software Foundation, either version 3 of the License, or
10 * (at your option) any later version.
12 * This program is distributed in the hope that it will be useful,
13 * but WITHOUT ANY WARRANTY; without even the implied warranty of
14 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
15 * GNU General Public License for more details.
17 * You should have received a copy of the GNU General Public License
18 * along with this program. If not, see <http://www.gnu.org/licenses/>.
21 date_default_timezone_set('UTC');
23 function str_to_gmdate($date)
25 $timestamp = strtotime($date);
26 return epoch_to_gmdate($timestamp);
29 function epoch_to_gmdate($timestamp)
31 return gmdate('D, d M Y H:i:s', $timestamp) . ' GMT';
36 private $USER_AGENT = "Mozilla/5.0 (Windows NT 6.1; rv:22.0) Gecko/20130405 Firefox/22.0";
38 public function __construct($stylesheet) {
39 $stylesheet_contents = $this->get_contents($stylesheet);
41 $xslDoc = new DOMDocument();
42 $xslDoc->loadXML($stylesheet_contents);
44 $this->xsltProcessor = new XSLTProcessor();
45 $this->xsltProcessor->registerPHPFunctions();
46 $this->xsltProcessor->importStylesheet($xslDoc);
49 private function get_contents($uri) {
50 # https://www.wjsams.com/c/docs/Wiki/Php-HowToSetUserAgentOnFileGetContents
54 'header' => join(array(
55 "Accept-language: en\r\n",
56 "User-Agent: {$this->USER_AGENT}\r\n"
61 $context = stream_context_create($opts);
62 $contents = file_get_contents($uri, false, $context);
66 public function tweep($uri) {
67 $html = $this->get_contents($uri);
69 $xmlDoc = new DOMDocument();
70 $xmlDoc->loadHTML($html);
72 $output = $this->xsltProcessor->transformToXML($xmlDoc);
74 if (FALSE === $output) {
75 trigger_error('XSL transformation failed.', E_USER_ERROR);
84 if (php_sapi_name() != 'cli')
85 $usage = htmlentities("{$_SERVER['SCRIPT_NAME']}?src_url=<src_url>");
87 $usage = "{$argv[0]} <src_url>\n";
89 return "usage: $usage";
92 if (isset($_GET['src_url'])) {
93 $src_url = $_GET['src_url'];
94 } else if (isset($argv[1])) {
95 if ($argv[1] == "-h" || $argv[1] == "--help") {
104 $url = parse_url($src_url);
105 if (FALSE === $url || empty($url["host"]))
106 die("Invalid url: $url\n");
108 $stylesheet = __DIR__ . "/rss_converter_" . $url["host"] . ".xsl";
109 if (FALSE === file_exists($stylesheet))
110 die("Conversion to RSS not supported: {$url["host"]}\n");
112 $tweeper = new Tweeper($stylesheet);
113 echo $tweeper->tweep($src_url);