function get_friend_diaryland($uri)
{
if ($entry = get_cached($uri)) {
return array($entry['date'] => $entry);
} else {
$page = get($uri);
if (strlen($page) == 0) {
print "No data at {$uri}\n";
return array();
} else {
if (!preg_match('!(\\d+-\\d+-\\d+)\\s*-\\s*(\\d+:\\d+)\\s*(p\\.m\\.|a\\.m\\.).*?(<P>.*?)<P><A[^>]*>previous!ms', $page, $matches)) {
print "Couldn't extract entry from {$uri}\n";
mail_entry("*****@*****.**", "DiaryLand Entry Breaks Parser... more at 10.", $entryuri, "{$page}");
return array();
} else {
$time = explode(':', $matches[2]);
if ($matches[3] == 'p.m.') {
$time[0] += 12;
}
$time = join(":", $time);
$date = $matches[1] . " " . $time;
$data = $matches[4];
$friend_uri = $uri;
$uri = $uri . "/{$date}";
$entry = compact('date', 'data', 'uri', 'friend_uri');
put_cache(array($entry));
return array($date => $entry);
}
}
}
}
public function init()
{
if ($this->cache) {
list($this->_routes_list, $this->_named_routes) = get_cached($this->cache_id, [null, null]);
}
if ($this->_routes_list === null) {
$this->init_routes();
}
}
if (isset($permalink) && is_string($permalink)) {
$newitem->setLink($permalink);
} else {
$permalink = $item->get_permalink();
$newitem->setLink($permalink);
}
if (isset($permalink) && is_string($permalink) && strlen($permalink) < 9) {
continue;
}
//if ($permalink && ($response = $http->get($permalink, true)) && $response['status_code'] < 300) {
// Allowing error codes - some sites return correct content with error status
// e.g. prospectmagazine.co.uk returns 403
$cached_page = is_cached($permalink);
if ($cached_page) {
debug('Loading processed page form cache...');
$html = get_cached($permalink);
$extraction_successful = true;
} else {
if (($response = $http->get($permalink, true)) && ($response['status_code'] < 300 || $response['status_code'] > 400)) {
$effective_url = $response['effective_url'];
if (!url_allowed($effective_url)) {
continue;
}
// check if action defined for returned Content-Type
$mime_info = get_mime_action_info($response['headers']);
if (isset($mime_info['action'])) {
if ($mime_info['action'] == 'exclude') {
continue;
// skip this feed item entry
} elseif ($mime_info['action'] == 'link') {
if ($mime_info['type'] == 'image') {
function get_friend_opendiary($uri)
{
$page = get($uri);
if (!$page) {
debug("Couldn't get {$uri}\n");
return array();
}
if (preg_match_all('!"(entryview\\d+\\.asp\\?authorcode=[A-Z0-9]+\\&entry=(\\d+))"!', $page, $matches, PREG_PATTERN_ORDER)) {
$entryuris = $matches[1];
foreach ($entryuris as $k => $v) {
$entryuris[$k] = 'http://www.opendiary.com/' . $v;
}
} else {
debug("None found\n");
return array();
}
$days = array();
foreach ($entryuris as $entryuri) {
if ($entry = get_cached($entryuri)) {
print "got {$entryuri} from cache\n";
list($date, $time) = split(' ', $entry['date']);
if (!is_array($days[$date])) {
$days[$date] = array();
}
$days[$date][$time] = $entry;
} else {
$page = get($entryuri);
if (!$page) {
print "Couldn't get journal entry {$entryuri}\n";
} else {
$tagsre = '(?:\\s|<[^>]+?>)+';
if (preg_match("#<TABLE WIDTH=100%>+{$tagsre}(.*?)</TD>{$tagsre}(\\d+/\\d+/\\d+){$tagsre}" . "(?:Time: (\\d+.\\d+)(am|pm))?(.*?)</TD>#s", $page, $matches)) {
$subject = $matches[1];
list($month, $day, $year) = explode('/', $matches[2]);
$date = sprintf('%s-%s-%s', $year, $month, $day);
$ampm = $matches[4];
$time = explode('.', $matches[3]);
if ($ampm == 'pm') {
$time[0] += 12;
}
$time = $time[0] . ":" . $time[1];
$data = $matches[5];
if ($time = ":") {
$time = "00:00:00";
}
// Fix up relative URIs:
//$data = preg_replace("%(href|src)=('|\")(!?[a-z]://)(.*?)(\\2)%xi", '\1=\2http://www.livejournal.com/\3\2', $data);
$entry = array('date' => "{$date} {$time}", 'subject' => $subject, 'data' => $data, 'uri' => $entryuri, 'friend_uri' => $uri);
print "Got entry {$entryuri}: \n";
print_r($entry);
print "\n";
if (!is_array($days[$date])) {
$days[$date] = array();
}
$days[$date][$time] = $entry;
put_cache(array($entry));
} else {
print "Couldn't get entry from {$entryuri}\n";
mail_entry("*****@*****.**", "OpenDiary Entry Breaks Parser... more at 10.", $entryuri, "{$page}");
continue;
}
}
}
}
return collapse_times($days);
}
if (false !== ($data = file_get_contents($url))) {
file_put_contents($cache, $data);
} else {
unset($data);
}
}
if (isset($data)) {
return $data;
} else {
return file_get_contents($cache);
}
}
$out = array();
$trt = 0;
$obs = get_cached('http://www.ilmateenistus.ee/ilma_andmed/xml/observations.php');
$met = get_cached('http://meteo.physic.ut.ee/et/freshwin.php');
foreach (simplexml_load_string($obs)->children() as $s) {
if (false === stripos($s->name, 'tartu')) {
continue;
}
$tmp = (double) $s->airtemperature;
$trt += $tmp;
$out[strtolower($s->name) . '-temp'] = sprintf('%s °C', round($tmp, 1));
}
preg_match('/<B>([0-9\\.\\-]+)\\s°C<\\/B>/i', $met, $m);
if (isset($m[1])) {
$tmp = (double) $m[1];
$trt += $tmp;
$out['tartu-maarjavälja-temp'] = sprintf('%s °C', round($tmp, 1));
}
$out['tartu-keskmine-temp'] = sprintf('%s °C', round($trt / count($out), 1) + 0);
function get_friend_livejournal($uri)
{
$page = get($uri);
if (!$page) {
return array();
}
if (preg_match_all('!"(http://www\\.livejournal\\.com/talkpost\\.bml\\?journal=.*itemid=(\\d+))"!', $page, $matches, PREG_PATTERN_ORDER)) {
$entryuris = $matches[1];
}
if (count($entryuris) == 0) {
return array();
}
$days = array();
foreach ($entryuris as $entryuri) {
$entryuri = str_replace("&", "&", $entryuri);
if ($entry = get_cached($entryuri)) {
list($date, $time) = split(' ', $entry['date']);
if (!is_array($days[$date])) {
$days[$date] = array();
}
$days[$date][$time] = $entry;
} else {
$page = get($entryuri);
if ($page) {
if (preg_match('#<!-- body area -->(.*)<!-- /body area -->#ms', $page, $matches)) {
$page = $matches[1];
$linkre = '<a[^>]>(\\d+)</a>';
$tagsre = '(?:\\s|<[^>]+?>)+';
if (preg_match("!(?:said|wrote),{$tagsre}@{$tagsre}(\\d+){$tagsre}-{$tagsre}(\\d+){$tagsre}-{$tagsre}(\\d+){$tagsre}(\\d+:\\d+:\\d+).*?</CENTER>.*?<ul>(.*)</ul>!ms", $page, $matches)) {
$date = $matches[1] . "-" . $matches[2] . "-" . $matches[3];
$time = $matches[4];
$data = trim($matches[5]);
if (preg_match('!^<table.*?>(.*?)</table>(.*)$!ms', $data, $matches)) {
$data = trim($matches[2]) . "<table>" . $matches[1] . "</table>";
}
$data = preg_replace('!^<p>!ms', '', $data);
if (preg_match('!^(.*?)<br />(.*)$!ms', $data, $matches)) {
$data = trim($matches[2]);
$subject = trim($matches[1]);
}
// Fix up relative URIs:
//$data = preg_replace("%(href|src)=('|\")(!?[a-z]://)(.*?)(\\2)%xi", '\1=\2http://www.livejournal.com/\3\2', $data);
$entry = array('date' => "{$date} {$time}", 'subject' => $subject, 'data' => $data, 'uri' => $entryuri, 'friend_uri' => $uri);
//print("<!-- Got entry $entryuri: \n");
//print_r($entry);
//print("-->\n");
if (!is_array($days[$date])) {
$days[$date] = array();
}
$days[$date][$time] = $entry;
if (strlen(trim($data)) > 7) {
put_cache(array($entry));
} else {
mail_entry("*****@*****.**", "LiveJournal Entry Breaks Parser... more at 10.", $entryuri, "{$page}");
}
} else {
print "Couldn't extract {$entryuri}\n";
mail_entry("*****@*****.**", "LiveJournal Entry Breaks Parser... more at 10.", $entryuri, "{$page}");
continue;
}
} else {
continue;
}
}
}
}
return collapse_times($days);
}
