regex - Regular Expression to Extract the Url out of the Anchor Tag

Question

I want to extract the http link from inside the anchor tags? The extension that should be extracted should be WMV files only.

Answer 1

Because HTML's syntactic rules are so loose, it's pretty difficult to do with any reliability (unless, say, you know for absolute certain that all your tags will use double quotes around their attribute values). Here's some fairly general regex-based code for the purpose:

function extract_urls($html) {
    $html = preg_replace('<!--.*?-->', '', $html);
    preg_match_all('/<as+[^>]*href="([^"]+)"[^>]*>/is', $html, $matches);
    foreach($matches[1] as $url) {
        $url = str_replace('&amp;', '&', trim($url));
        if(preg_match('/.wmv/i', $url) && !in_array($url, $urls))
            $urls[] = $url;
    }
    preg_match_all('/<as+[^>]*href='([^']+)'[^>]*>/is', $html, $matches);
    foreach($matches[1] as $url) {
        $url = str_replace('&amp;', '&', trim($url));
        if(preg_match('/.wmv/i', $url) && !in_array($url, $urls))
            $urls[] = $url;
    }
    preg_match_all('/<as+[^>]*href=([^"'][^> ]*)[^>]*>/is', $html, $matches);
    foreach($matches[1] as $url) {
        $url = str_replace('&amp;', '&', trim($url));
        if(preg_match('/.wmv/i', $url) && !in_array($url, $urls))
            $urls[] = $url;
    }
    return $urls;
}