coabot/src/url_metadata.js

const bot = require('bbot');
const request = require('request');

bot.global.text(/(https?:\/\/[^ ,\)"]*)/ig, (b) => {
  // console.log(JSON.stringify(b.envelope.payload, null, 2));
  for (url of b.match) {
    // console.log(JSON.stringify(url, null, 2));
    if (!/(coa|pad)\.crapaud-fou\.org/.test(url)) {
      request(url, (err, res, body) => {
        if (!err) {
          console.log(JSON.stringify(res.request.uri.href, null, 2));
          var re = /<title[^>]*>([^<]*)<\/title>/gi;
          var match = re.exec(body);
          if (match && match[1]) {
            // b.respondEnvelope({ attachments: [] })
            // b.envelope.payload.quickReply({ attachments: [] });
            var extra = "";
            var link = res.request.uri.href;
            if (/youtube.com/.test(res.request.uri.href)) {
              if (t = /[?&]v=([^&]+)/.exec(link)) {
                link = "https://www.youtube.com/watch?v=" + t[1];
                extra += " - [no-cookie](https://www.youtube-nocookie.com/embed/" + t[1] + ")";
                extra += " - [invidio](https://invidio.us/watch?v=" + t[1] + ")";
              }
            }
            b.respond("[:link:](" + url + ") _" + match[1] + "_" + extra);
          }
        }
      });
    }
  }
}, {
  id: 'get-url-metadata'
});