friendica/include/Scrape.php

243 lines
5.3 KiB
PHP
Raw Normal View History

2010-07-01 19:48:07 -04:00
<?php
require_once('library/HTML5/Parser.php');
if(! function_exists('scrape_dfrn')) {
function scrape_dfrn($url) {
$a = get_app();
2010-07-01 19:48:07 -04:00
$ret = array();
logger('scrape_dfrn: url=' . $url);
2010-07-01 19:48:07 -04:00
$s = fetch_url($url);
if(! $s)
return $ret;
$headers = $a->get_curl_headers();
logger('scrape_dfrn: headers=' . $headers, LOGGER_DEBUG);
$lines = explode("\n",$headers);
if(count($lines)) {
foreach($lines as $line) {
// don't try and run feeds through the html5 parser
if(stristr($line,'content-type:') && ((stristr($line,'application/atom+xml')) || (stristr($line,'application/rss+xml'))))
return ret;
}
}
2010-07-01 19:48:07 -04:00
$dom = HTML5_Parser::parse($s);
if(! $dom)
return $ret;
$items = $dom->getElementsByTagName('link');
// get DFRN link elements
foreach($items as $item) {
$x = $item->getAttribute('rel');
2011-01-23 23:09:34 -05:00
if(($x === 'alternate') && ($item->getAttribute('type') === 'application/atom+xml'))
$ret['feed_atom'] = $item->getAttribute('href');
2010-07-01 19:48:07 -04:00
if(substr($x,0,5) == "dfrn-")
$ret[$x] = $item->getAttribute('href');
if($x === 'lrdd') {
$decoded = urldecode($item->getAttribute('href'));
if(preg_match('/acct:([^@]*)@/',$decoded,$matches))
$ret['nick'] = $matches[1];
}
2010-07-01 19:48:07 -04:00
}
// Pull out hCard profile elements
$items = $dom->getElementsByTagName('*');
foreach($items as $item) {
if(attribute_contains($item->getAttribute('class'), 'vcard')) {
$level2 = $item->getElementsByTagName('*');
foreach($level2 as $x) {
if(attribute_contains($x->getAttribute('class'),'fn'))
$ret['fn'] = $x->textContent;
if(attribute_contains($x->getAttribute('class'),'photo'))
$ret['photo'] = $x->getAttribute('src');
if(attribute_contains($x->getAttribute('class'),'key'))
$ret['key'] = $x->textContent;
}
2010-07-01 19:48:07 -04:00
}
}
return $ret;
}}
if(! function_exists('validate_dfrn')) {
function validate_dfrn($a) {
$errors = 0;
if(! x($a,'key'))
$errors ++;
if(! x($a,'dfrn-request'))
$errors ++;
if(! x($a,'dfrn-confirm'))
$errors ++;
if(! x($a,'dfrn-notify'))
$errors ++;
if(! x($a,'dfrn-poll'))
$errors ++;
return $errors;
}}
if(! function_exists('scrape_meta')) {
function scrape_meta($url) {
2010-07-01 19:48:07 -04:00
$a = get_app();
$ret = array();
logger('scrape_meta: url=' . $url);
$s = fetch_url($url);
if(! $s)
return $ret;
$headers = $a->get_curl_headers();
logger('scrape_meta: headers=' . $headers, LOGGER_DEBUG);
$lines = explode("\n",$headers);
if(count($lines)) {
foreach($lines as $line) {
// don't try and run feeds through the html5 parser
if(stristr($line,'content-type:') && ((stristr($line,'application/atom+xml')) || (stristr($line,'application/rss+xml'))))
return ret;
}
}
$dom = HTML5_Parser::parse($s);
if(! $dom)
return $ret;
2010-07-01 19:48:07 -04:00
$items = $dom->getElementsByTagName('meta');
// get DFRN link elements
foreach($items as $item) {
$x = $item->getAttribute('name');
if(substr($x,0,5) == "dfrn-")
$ret[$x] = $item->getAttribute('content');
}
return $ret;
}}
if(! function_exists('scrape_vcard')) {
function scrape_vcard($url) {
$a = get_app();
$ret = array();
logger('scrape_vcard: url=' . $url);
$s = fetch_url($url);
if(! $s)
return $ret;
$headers = $a->get_curl_headers();
$lines = explode("\n",$headers);
if(count($lines)) {
foreach($lines as $line) {
// don't try and run feeds through the html5 parser
if(stristr($line,'content-type:') && ((stristr($line,'application/atom+xml')) || (stristr($line,'application/rss+xml'))))
return ret;
}
}
$dom = HTML5_Parser::parse($s);
if(! $dom)
return $ret;
// Pull out hCard profile elements
$items = $dom->getElementsByTagName('*');
foreach($items as $item) {
if(attribute_contains($item->getAttribute('class'), 'vcard')) {
$level2 = $item->getElementsByTagName('*');
foreach($level2 as $x) {
if(attribute_contains($x->getAttribute('class'),'fn'))
$ret['fn'] = $x->textContent;
if((attribute_contains($x->getAttribute('class'),'photo'))
|| (attribute_contains($x->getAttribute('class'),'avatar')))
$ret['photo'] = $x->getAttribute('src');
if((attribute_contains($x->getAttribute('class'),'nickname'))
|| (attribute_contains($x->getAttribute('class'),'uid')))
$ret['nick'] = $x->textContent;
}
}
}
return $ret;
}}
2011-01-23 23:09:34 -05:00
if(! function_exists('scrape_feed')) {
function scrape_feed($url) {
$a = get_app();
2011-01-23 23:09:34 -05:00
$ret = array();
$s = fetch_url($url);
if(! $s)
return $ret;
$headers = $a->get_curl_headers();
logger('scrape_feed: headers=' . $headers, LOGGER_DEBUG);
$lines = explode("\n",$headers);
if(count($lines)) {
foreach($lines as $line) {
if(stristr($line,'content-type:')) {
if(stristr($line,'application/atom+xml') || stristr($s,'<feed')) {
$ret['feed_atom'] = $url;
return $ret;
}
if(stristr($line,'application/rss+xml') || stristr($s,'<rss')) {
$ret['feed_rss'] = $url;
2011-04-04 22:36:18 -04:00
return $ret;
}
}
}
}
2011-01-23 23:09:34 -05:00
$dom = HTML5_Parser::parse($s);
if(! $dom)
return $ret;
$items = $dom->getElementsByTagName('link');
// get Atom link elements
foreach($items as $item) {
$x = $item->getAttribute('rel');
if(($x === 'alternate') && ($item->getAttribute('type') === 'application/atom+xml'))
$ret['feed_atom'] = $item->getAttribute('href');
if(($x === 'alternate') && ($item->getAttribute('type') === 'application/rss+xml'))
$ret['feed_rss'] = $item->getAttribute('href');
2011-01-23 23:09:34 -05:00
}
return $ret;
}}