class ArchiveArticle
{
public $raw, $preface, $title, $body;
+ public $meta = [];
function __construct($path)
{
$this->link = preg_replace('{(?:/index)?\.html$}', '', $path);
if (file_exists($this->page)) {
$this->raw = file_get_contents($this->page);
+
+ if (preg_match_all('{
+ \G <meta \s+ property="( [^"]+ )" \s+ content="( [^"]* )" > \s*
+ }x', $this->raw, $meta)) {
+ $matchlen = array_sum(array_map('strlen', $meta[0]));
+ $this->raw = substr($this->raw, $matchlen); # delete matched contents
+ $this->meta = array_combine($meta[1], $meta[2]); # [property => content]
+ }
+
@list ($this->preface, $this->title, $this->body) =
preg_split('{<h2>(.*?)</h2>\s*}', $this->raw, 2, PREG_SPLIT_DELIM_CAPTURE);
}
function safetitle()
{
- return trim(strip_tags($this->title));
+ return trim($this->meta['og:title'] ?? strip_tags($this->title));
}
function name()
{
}
return $this->body;
}
+
function teaser()
{
- 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 $meta[1];
+ if ($override = @$this->meta['og:description']) {
+ # prefer specific page description if found in metadata
+ return $override;
}
if (preg_match('{
}
function image()
{
+ if ($override = @$this->meta['og:image']) {
+ # prefer specific page image if found in metadata
+ return $override;
+ }
+
if ( preg_match('/\bsrc="([^"]*)"/', $this->img, $src) ) {
return $src[1];
}