class ArchiveArticle
{
+ public $raw, $preface, $title, $body;
+
function __construct($path)
{
$this->page = $path;
$this->link = preg_replace('{(?:/index)?\.html$}', '', $path);
+ if (file_exists($this->page)) {
+ $this->raw = file_get_contents($this->page);
+ @list ($this->preface, $this->title, $this->body) =
+ preg_split('{<h2>(.*?)</h2>\s*}', $this->raw, 2, PREG_SPLIT_DELIM_CAPTURE);
+ }
}
function __get($col)
return $this->$col = $this->$col(); # run method and cache
}
- function file()
- {
- if (!file_exists($this->page)) return;
- return fopen($this->page, 'r');
- }
-
- function rawtitle()
- {
- return fgets($this->file);
- }
- function title()
- {
- return preg_replace('{<h2>(.*)</h2>\s*}', '\1', $this->rawtitle);
- }
function safetitle()
{
return trim(strip_tags($this->title));
return showdate($this->dateparts);
}
- function body()
- {
- if (!$this->file) return;
- $this->rawtitle;
- return fread($this->file, filesize($this->page) ?: 1);
- }
function story()
{
if ( preg_match('{
}
return $this->body;
}
-
- function raw()
- {
- return $this->rawtitle . $this->body;
- }
function teaser()
{
- if (preg_match('{<p>(.*?)</p>}s', $this->story, $bodyp)) {
- return $bodyp[1];
+ if (preg_match('{
+ <meta \s+ name="description" [^>]* content="([^">]*)"
+ }x', $this->preface, $meta)) {
+ # prefer specific page description if found (assume before title)
+ #TODO: strip from body contents
+ return $meta[1];
+ }
+ if (preg_match('{
+ </h2> (?: \s+ | <p\sclass="nav\b.*?</p> | <div[^>]*> )* <p> (.*?) </p>
+ }sx', $this->raw, $bodyp, PREG_OFFSET_CAPTURE)) {
+ # fallback paragraph contents following the page header
+ if ($bodyp[1][1] < 256) {
+ return $bodyp[1][0];
+ }
}
}