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 epoch_to_gmdate($timestamp)
25 return gmdate('D, d M Y H:i:s', $timestamp) . ' GMT';
30 private $USER_AGENT = "Mozilla/5.0 (Windows NT 6.1; rv:22.0) Gecko/20130405 Firefox/22.0";
32 public function __construct($stylesheet) {
33 $stylesheet_contents = $this->get_contents($stylesheet);
35 $xslDoc = new DOMDocument();
36 $xslDoc->loadXML($stylesheet_contents);
38 $this->xsltProcessor = new XSLTProcessor();
39 $this->xsltProcessor->registerPHPFunctions();
40 $this->xsltProcessor->importStylesheet($xslDoc);
43 private function get_contents($uri) {
44 # https://www.wjsams.com/c/docs/Wiki/Php-HowToSetUserAgentOnFileGetContents
48 'header' => join(array(
49 "Accept-language: en\r\n",
50 "User-Agent: {$this->USER_AGENT}\r\n"
55 $context = stream_context_create($opts);
56 $contents = file_get_contents($uri, false, $context);
60 public function tweep($uri) {
61 $html = $this->get_contents($uri);
63 $xmlDoc = new DOMDocument();
64 $xmlDoc->loadHTML($html);
66 $output = $this->xsltProcessor->transformToXML($xmlDoc);
68 if (FALSE === $output) {
69 trigger_error('XSL transformation failed.', E_USER_ERROR);
78 if (php_sapi_name() != 'cli')
79 $usage = htmlentities("{$_SERVER['SCRIPT_NAME']}?src_url=<src_url>");
81 $usage = "{$argv[0]} <src_url>\n";
83 return "usage: $usage";
86 if (isset($_GET['src_url'])) {
87 $src_url = $_GET['src_url'];
88 } else if (isset($argv[1])) {
94 $url = parse_url($src_url);
95 if (FALSE === $url || empty($url["host"]))
96 die("Invalid url: $url\n");
98 $stylesheet = __DIR__ . "/rss_converter_" . $url["host"] . ".xsl";
99 if (FALSE === file_exists($stylesheet))
100 die("Conversion to RSS not supported: {$url["host"]}\n");
102 $tweeper = new Tweeper($stylesheet);
103 echo $tweeper->tweep($src_url);