]>
Commit | Line | Data |
---|---|---|
24619534 | 1 | <?php |
6f87a197 | 2 | /** |
3 | * poche, a read it later open source system | |
4 | * | |
5 | * @category poche | |
6 | * @author Nicolas Lœuillet <support@inthepoche.com> | |
7 | * @copyright 2013 | |
8 | * @license http://www.wtfpl.net/ see COPYING file | |
9 | */ | |
24619534 | 10 | |
c8bbe19b | 11 | /** |
12 | * Permet de générer l'URL de poche pour le bookmarklet | |
13 | */ | |
8046748b | 14 | function get_poche_url() |
c8bbe19b | 15 | { |
16 | $protocol = "http"; | |
17 | if(isset($_SERVER['HTTPS'])) { | |
f0fc5011 | 18 | if($_SERVER['HTTPS'] != "off" && $_SERVER['HTTPS'] != "") { |
c8bbe19b | 19 | $protocol = "https"; |
20 | } | |
21 | } | |
24619534 | 22 | |
c8bbe19b | 23 | return $protocol . "://" . $_SERVER['HTTP_HOST'] . $_SERVER['REQUEST_URI']; |
24619534 | 24 | } |
25 | ||
aa8c9f2a NL |
26 | function encode_string($string) |
27 | { | |
28 | return sha1($string . SALT); | |
29 | } | |
30 | ||
24619534 | 31 | // function define to retrieve url content |
1c182b6c | 32 | function get_external_file($url) |
c8bbe19b | 33 | { |
1c182b6c | 34 | $timeout = 15; |
24619534 | 35 | // spoofing FireFox 18.0 |
36 | $useragent="Mozilla/5.0 (Windows NT 5.1; rv:18.0) Gecko/20100101 Firefox/18.0"; | |
37 | ||
38 | if (in_array ('curl', get_loaded_extensions())) { | |
39 | // Fetch feed from URL | |
40 | $curl = curl_init(); | |
41 | curl_setopt($curl, CURLOPT_URL, $url); | |
42 | curl_setopt($curl, CURLOPT_TIMEOUT, $timeout); | |
43 | curl_setopt($curl, CURLOPT_FOLLOWLOCATION, true); | |
44 | curl_setopt($curl, CURLOPT_RETURNTRANSFER, true); | |
45 | curl_setopt($curl, CURLOPT_HEADER, false); | |
46 | ||
2987031b | 47 | // FOR SSL do not verified certificate |
4ddbd267 | 48 | curl_setopt($curl, CURLOPT_SSL_VERIFYPEER, FALSE); |
2987031b | 49 | curl_setopt($curl, CURLOPT_AUTOREFERER, TRUE ); |
4ddbd267 | 50 | |
24619534 | 51 | // FeedBurner requires a proper USER-AGENT... |
52 | curl_setopt($curl, CURL_HTTP_VERSION_1_1, true); | |
53 | curl_setopt($curl, CURLOPT_ENCODING, "gzip, deflate"); | |
54 | curl_setopt($curl, CURLOPT_USERAGENT, $useragent); | |
55 | ||
56 | $data = curl_exec($curl); | |
57 | ||
58 | $httpcode = curl_getinfo($curl, CURLINFO_HTTP_CODE); | |
59 | ||
60 | $httpcodeOK = isset($httpcode) and ($httpcode == 200 or $httpcode == 301); | |
61 | ||
62 | curl_close($curl); | |
63 | } else { | |
64 | ||
65 | // create http context and add timeout and user-agent | |
4ddbd267 | 66 | $context = stream_context_create(array( |
2987031b | 67 | 'http'=>array('timeout' => $timeout, |
68 | 'header'=> "User-Agent: ".$useragent, /*spoot Mozilla Firefox*/ | |
69 | 'follow_location' => true), | |
70 | // FOR SSL do not verified certificate | |
71 | 'ssl' => array('verify_peer' => false, | |
72 | 'allow_self_signed' => true) | |
73 | ) | |
74 | ); | |
24619534 | 75 | |
76 | // only download page lesser than 4MB | |
77 | $data = @file_get_contents($url, false, $context, -1, 4000000); // We download at most 4 MB from source. | |
24619534 | 78 | |
79 | if(isset($http_response_header) and isset($http_response_header[0])) { | |
80 | $httpcodeOK = isset($http_response_header) and isset($http_response_header[0]) and ((strpos($http_response_header[0], '200 OK') !== FALSE) or (strpos($http_response_header[0], '301 Moved Permanently') !== FALSE)); | |
81 | } | |
82 | } | |
83 | ||
84 | // if response is not empty and response is OK | |
85 | if (isset($data) and isset($httpcodeOK) and $httpcodeOK ) { | |
86 | ||
87 | // take charset of page and get it | |
88 | preg_match('#<meta .*charset=.*>#Usi', $data, $meta); | |
89 | ||
90 | // if meta tag is found | |
91 | if (!empty($meta[0])) { | |
92 | // retrieve encoding in $enc | |
93 | preg_match('#charset="?(.*)"#si', $meta[0], $enc); | |
94 | ||
95 | // if charset is found set it otherwise, set it to utf-8 | |
96 | $html_charset = (!empty($enc[1])) ? strtolower($enc[1]) : 'utf-8'; | |
97 | ||
98 | } else { | |
99 | $html_charset = 'utf-8'; | |
100 | $enc[1] = ''; | |
101 | } | |
102 | ||
103 | // replace charset of url to charset of page | |
104 | $data = str_replace('charset='.$enc[1], 'charset='.$html_charset, $data); | |
105 | ||
106 | return $data; | |
107 | } | |
108 | else { | |
109 | return FALSE; | |
110 | } | |
3c8d80ae | 111 | } |
112 | ||
8046748b | 113 | /** |
114 | * Préparation de l'URL avec récupération du contenu avant insertion en base | |
115 | */ | |
d06f30ef | 116 | function prepare_url($url) |
3c8d80ae | 117 | { |
118 | $parametres = array(); | |
e4d2565e | 119 | $url = html_entity_decode(trim($url)); |
3c8d80ae | 120 | |
121 | // We remove the annoying parameters added by FeedBurner and GoogleFeedProxy (?utm_source=...) | |
122 | // from shaarli, by sebsauvage | |
123 | $i=strpos($url,'&utm_source='); if ($i!==false) $url=substr($url,0,$i); | |
124 | $i=strpos($url,'?utm_source='); if ($i!==false) $url=substr($url,0,$i); | |
125 | $i=strpos($url,'#xtor=RSS-'); if ($i!==false) $url=substr($url,0,$i); | |
126 | ||
e4d2565e | 127 | $title = $url; |
2987031b | 128 | $html = Encoding::toUTF8(get_external_file($url,15)); |
129 | // If get_external_file if not able to retrieve HTTPS content try the same URL with HTTP protocol | |
130 | if (!preg_match('!^https?://!i', $url) && (!isset($html) || strlen($html) <= 0)) { | |
131 | $url = 'http://' . $url; | |
132 | $html = Encoding::toUTF8(get_external_file($url,15)); | |
133 | } | |
3c8d80ae | 134 | |
494e21b4 | 135 | if (function_exists('tidy_parse_string')) { |
136 | $tidy = tidy_parse_string($html, array(), 'UTF8'); | |
137 | $tidy->cleanRepair(); | |
138 | $html = $tidy->value; | |
139 | } | |
140 | ||
3c8d80ae | 141 | if (isset($html) and strlen($html) > 0) |
142 | { | |
143 | $r = new Readability($html, $url); | |
2987031b | 144 | |
d06f30ef | 145 | $r->convertLinksToFootnotes = CONVERT_LINKS_FOOTNOTES; |
2987031b | 146 | $r->revertForcedParagraphElements = REVERT_FORCED_PARAGRAPH_ELEMENTS; |
4ddbd267 | 147 | |
3c8d80ae | 148 | if($r->init()) |
149 | { | |
1c182b6c | 150 | $content = $r->articleContent->innerHTML; |
151 | $parametres['title'] = $r->articleTitle->innerHTML; | |
64458521 | 152 | $parametres['content'] = $content; |
1c182b6c | 153 | return $parametres; |
3c8d80ae | 154 | } |
155 | } | |
156 | ||
1c182b6c | 157 | return FALSE; |
158 | } | |
159 | ||
160 | /** | |
161 | * On modifie les URLS des images dans le corps de l'article | |
162 | */ | |
163 | function filtre_picture($content, $url, $id) | |
164 | { | |
165 | $matches = array(); | |
166 | preg_match_all('#<\s*(img)[^>]+src="([^"]*)"[^>]*>#Si', $content, $matches, PREG_SET_ORDER); | |
167 | foreach($matches as $i => $link) | |
168 | { | |
169 | $link[1] = trim($link[1]); | |
170 | if (!preg_match('#^(([a-z]+://)|(\#))#', $link[1]) ) | |
171 | { | |
172 | $absolute_path = get_absolute_link($link[2],$url); | |
173 | $filename = basename(parse_url($absolute_path, PHP_URL_PATH)); | |
174 | $directory = create_assets_directory($id); | |
175 | $fullpath = $directory . '/' . $filename; | |
176 | download_pictures($absolute_path, $fullpath); | |
177 | $content = str_replace($matches[$i][2], $fullpath, $content); | |
178 | } | |
179 | ||
180 | } | |
181 | ||
182 | return $content; | |
183 | } | |
184 | ||
185 | /** | |
186 | * Retourne le lien absolu | |
187 | */ | |
188 | function get_absolute_link($relative_link, $url) | |
189 | { | |
190 | /* return if already absolute URL */ | |
191 | if (parse_url($relative_link, PHP_URL_SCHEME) != '') return $relative_link; | |
192 | ||
193 | /* queries and anchors */ | |
194 | if ($relative_link[0]=='#' || $relative_link[0]=='?') return $url . $relative_link; | |
195 | ||
196 | /* parse base URL and convert to local variables: | |
197 | $scheme, $host, $path */ | |
198 | extract(parse_url($url)); | |
199 | ||
200 | /* remove non-directory element from path */ | |
201 | $path = preg_replace('#/[^/]*$#', '', $path); | |
202 | ||
203 | /* destroy path if relative url points to root */ | |
204 | if ($relative_link[0] == '/') $path = ''; | |
205 | ||
206 | /* dirty absolute URL */ | |
207 | $abs = $host . $path . '/' . $relative_link; | |
208 | ||
209 | /* replace '//' or '/./' or '/foo/../' with '/' */ | |
210 | $re = array('#(/\.?/)#', '#/(?!\.\.)[^/]+/\.\./#'); | |
211 | for($n=1; $n>0; $abs=preg_replace($re, '/', $abs, -1, $n)) {} | |
212 | ||
213 | /* absolute URL is ready! */ | |
214 | return $scheme.'://'.$abs; | |
215 | } | |
216 | ||
217 | /** | |
218 | * Téléchargement des images | |
219 | */ | |
220 | ||
221 | function download_pictures($absolute_path, $fullpath) | |
222 | { | |
223 | $rawdata = get_external_file($absolute_path); | |
3c8d80ae | 224 | |
1c182b6c | 225 | if(file_exists($fullpath)) { |
226 | unlink($fullpath); | |
227 | } | |
228 | $fp = fopen($fullpath, 'x'); | |
229 | fwrite($fp, $rawdata); | |
230 | fclose($fp); | |
231 | } | |
232 | ||
233 | /** | |
234 | * Crée un répertoire de médias pour l'article | |
235 | */ | |
236 | function create_assets_directory($id) | |
237 | { | |
238 | $assets_path = ABS_PATH; | |
239 | if(!is_dir($assets_path)) { | |
240 | mkdir($assets_path, 0705); | |
241 | } | |
242 | ||
243 | $article_directory = $assets_path . $id; | |
244 | if(!is_dir($article_directory)) { | |
245 | mkdir($article_directory, 0705); | |
246 | } | |
247 | ||
248 | return $article_directory; | |
249 | } | |
250 | ||
251 | /** | |
252 | * Suppression du répertoire d'images | |
253 | */ | |
254 | function remove_directory($directory) | |
255 | { | |
256 | if(is_dir($directory)) { | |
257 | $files = array_diff(scandir($directory), array('.','..')); | |
258 | foreach ($files as $file) { | |
07a19252 | 259 | (is_dir("$directory/$file")) ? remove_directory("$directory/$file") : unlink("$directory/$file"); |
1c182b6c | 260 | } |
261 | return rmdir($directory); | |
262 | } | |
263d6c67 | 263 | } |
264 | ||
a1953dff | 265 | function display_view($view, $id = 0, $full_head = 'yes') |
266 | { | |
f0070a15 | 267 | global $tpl, $store, $msg; |
a1953dff | 268 | |
269 | switch ($view) | |
270 | { | |
44e77bfa | 271 | case 'export': |
272 | $entries = $store->retrieveAll(); | |
6f87a197 | 273 | $tpl->assign('export', myTool::renderJson($entries)); |
44e77bfa | 274 | $tpl->draw('export'); |
275 | logm('export view'); | |
276 | break; | |
016989b7 | 277 | case 'config': |
278 | $tpl->assign('load_all_js', 0); | |
279 | $tpl->draw('head'); | |
280 | $tpl->draw('home'); | |
281 | $tpl->draw('config'); | |
282 | $tpl->draw('js'); | |
283 | $tpl->draw('footer'); | |
284 | logm('config view'); | |
44e77bfa | 285 | break; |
a1953dff | 286 | case 'view': |
14890de3 | 287 | $entry = $store->retrieveOneById($id); |
a1953dff | 288 | |
289 | if ($entry != NULL) { | |
14890de3 | 290 | $tpl->assign('id', $entry['id']); |
291 | $tpl->assign('url', $entry['url']); | |
292 | $tpl->assign('title', $entry['title']); | |
494e21b4 | 293 | $content = $entry['content']; |
294 | if (function_exists('tidy_parse_string')) { | |
295 | $tidy = tidy_parse_string($content, array('indent'=>true, 'show-body-only' => true), 'UTF8'); | |
296 | $tidy->cleanRepair(); | |
297 | $content = $tidy->value; | |
298 | } | |
299 | $tpl->assign('content', $content); | |
14890de3 | 300 | $tpl->assign('is_fav', $entry['is_fav']); |
301 | $tpl->assign('is_read', $entry['is_read']); | |
a1953dff | 302 | $tpl->assign('load_all_js', 0); |
303 | $tpl->draw('view'); | |
304 | } | |
305 | else { | |
306 | logm('error in view call : entry is NULL'); | |
307 | } | |
308 | ||
309 | logm('view link #' . $id); | |
310 | break; | |
311 | default: # home view | |
14890de3 | 312 | $entries = $store->getEntriesByView($view); |
a1953dff | 313 | |
314 | $tpl->assign('entries', $entries); | |
315 | ||
316 | if ($full_head == 'yes') { | |
317 | $tpl->assign('load_all_js', 1); | |
318 | $tpl->draw('head'); | |
319 | $tpl->draw('home'); | |
320 | } | |
321 | ||
322 | $tpl->draw('entries'); | |
323 | ||
324 | if ($full_head == 'yes') { | |
325 | $tpl->draw('js'); | |
326 | $tpl->draw('footer'); | |
327 | } | |
328 | break; | |
329 | } | |
330 | } | |
331 | ||
263d6c67 | 332 | /** |
333 | * Appel d'une action (mark as fav, archive, delete) | |
334 | */ | |
e4d2565e | 335 | function action_to_do($action, $url, $id = 0) |
263d6c67 | 336 | { |
f0070a15 | 337 | global $store, $msg; |
263d6c67 | 338 | |
339 | switch ($action) | |
340 | { | |
341 | case 'add': | |
342 | if ($url == '') | |
343 | continue; | |
344 | ||
6f87a197 | 345 | if (MyTool::isUrl($url)) { |
346 | if($parametres_url = prepare_url($url)) { | |
29c6fd46 | 347 | if ($store->add($url, $parametres_url['title'], $parametres_url['content'])) { |
348 | $last_id = $store->getLastId(); | |
349 | if (DOWNLOAD_PICTURES) { | |
350 | $content = filtre_picture($parametres_url['content'], $url, $last_id); | |
351 | } | |
352 | $msg->add('s', 'the link has been added successfully'); | |
6f87a197 | 353 | } |
29c6fd46 | 354 | else { |
355 | $msg->add('e', 'error during insertion : the link wasn\'t added'); | |
356 | } | |
357 | } | |
358 | else { | |
359 | $msg->add('e', 'error during url preparation : the link wasn\'t added'); | |
360 | logm('error during url preparation'); | |
14890de3 | 361 | } |
1c182b6c | 362 | } |
6f87a197 | 363 | else { |
29c6fd46 | 364 | $msg->add('e', 'error during url preparation : the link is not valid'); |
6f87a197 | 365 | logm($url . ' is not a valid url'); |
366 | } | |
1c182b6c | 367 | |
a81cd067 | 368 | logm('add link ' . $url); |
263d6c67 | 369 | break; |
370 | case 'delete': | |
29c6fd46 | 371 | if ($store->deleteById($id)) { |
372 | remove_directory(ABS_PATH . $id); | |
373 | $msg->add('s', 'the link has been deleted successfully'); | |
374 | logm('delete link #' . $id); | |
375 | } | |
376 | else { | |
377 | $msg->add('e', 'the link wasn\'t deleted'); | |
378 | logm('error : can\'t delete link #' . $id); | |
379 | } | |
263d6c67 | 380 | break; |
139769aa | 381 | case 'toggle_fav' : |
14890de3 | 382 | $store->favoriteById($id); |
e4d2565e | 383 | logm('mark as favorite link #' . $id); |
139769aa | 384 | break; |
385 | case 'toggle_archive' : | |
14890de3 | 386 | $store->archiveById($id); |
e4d2565e | 387 | logm('archive link #' . $id); |
139769aa | 388 | break; |
263d6c67 | 389 | default: |
390 | break; | |
391 | } | |
cf3180f6 | 392 | } |
393 | ||
713b2d69 | 394 | function logm($message) |
395 | { | |
396 | $t = strval(date('Y/m/d_H:i:s')).' - '.$_SERVER["REMOTE_ADDR"].' - '.strval($message)."\n"; | |
a81cd067 | 397 | file_put_contents('./log.txt',$t,FILE_APPEND); |
cdcc8d25 | 398 | } |