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 define('USER_AGENT', 'Mozilla/5.0 (Windows NT 6.1; rv:22.0) Gecko/20130405 Firefox/22.0');
25 function str_to_gmdate($date)
27 $timestamp = strtotime($date);
28 return epoch_to_gmdate($timestamp);
31 function epoch_to_gmdate($timestamp)
33 return gmdate('D, d M Y H:i:s', $timestamp) . ' GMT';
36 function get_url_info($url)
38 $ch = curl_init($url);
39 curl_setopt_array($ch, array(
40 CURLOPT_HEADER => TRUE,
41 CURLOPT_NOBODY => TRUE,
42 CURLOPT_FOLLOWLOCATION => TRUE, // follow http redirects to get the real URL
43 CURLOPT_RETURNTRANSFER => TRUE,
44 CURLOPT_SSL_VERIFYHOST => FALSE,
45 CURLOPT_SSL_VERIFYPEER => FALSE,
46 CURLOPT_USERAGENT => USER_AGENT,
49 $url_info = curl_getinfo($ch);;
55 function generate_enclosure($url)
57 $url_info = get_url_info($url);
59 switch($url_info['content_type']) {
67 case "application/ogg":
74 $dom = new DomDocument();
75 $enc = $dom->createElement('enclosure');
76 $enc->setAttribute( 'url', $url_info['url']);
77 $enc->setAttribute( 'length', $url_info['download_content_length']);
78 $enc->setAttribute( 'type', $url_info['content_type']);
80 $dom->appendChild($enc);
82 return $dom->saveXML($enc);
91 public function __construct($stylesheet) {
92 $stylesheet_contents = $this->get_contents($stylesheet);
94 $xslDoc = new DOMDocument();
95 $xslDoc->loadXML($stylesheet_contents);
97 $this->xsltProcessor = new XSLTProcessor();
98 $this->xsltProcessor->registerPHPFunctions();
99 $this->xsltProcessor->importStylesheet($xslDoc);
102 private function get_contents($uri) {
103 # https://www.wjsams.com/c/docs/Wiki/Php-HowToSetUserAgentOnFileGetContents
107 'header' => join(array(
108 "Accept-language: en\r\n",
109 "User-Agent: {" + USER_AGENT + "}\r\n"
114 $context = stream_context_create($opts);
115 $contents = file_get_contents($uri, false, $context);
119 public function tweep($uri) {
120 $html = $this->get_contents($uri);
122 $xmlDoc = new DOMDocument();
123 $xmlDoc->loadHTML($html);
125 $output = $this->xsltProcessor->transformToXML($xmlDoc);
127 if (FALSE === $output) {
128 trigger_error('XSL transformation failed.', E_USER_ERROR);
135 function usage($argv)
137 if (php_sapi_name() != 'cli')
138 $usage = htmlentities("{$_SERVER['SCRIPT_NAME']}?src_url=<src_url>");
140 $usage = "{$argv[0]} <src_url>\n";
142 return "usage: $usage";
145 if (isset($_GET['src_url'])) {
146 $src_url = $_GET['src_url'];
147 } else if (isset($argv[1])) {
148 if ($argv[1] == "-h" || $argv[1] == "--help") {
157 $url = parse_url($src_url);
158 if (FALSE === $url || empty($url["host"]))
159 die("Invalid url: $src_url\n");
161 $stylesheet = __DIR__ . "/rss_converter_" . $url["host"] . ".xsl";
162 if (FALSE === file_exists($stylesheet))
163 die("Conversion to RSS not supported: {$url["host"]}\n");
165 $tweeper = new Tweeper($stylesheet);
166 echo $tweeper->tweep($src_url);