# robots.txt for http://www.swr.de/ # # swr crawler User-agent: swr-gsa-crawler Allow: / # definitions for all bots User-agent: * Crawl-Delay: 30 Disallow: /cgi-bin/ Disallow: /vv=sendungswecker/ Disallow: /pv=print/ Disallow: /pv=mplayer/ Disallow: /vv=pdf/ Disallow: /export/ Disallow: /pv=plain/ Disallow: /pv=email/ Disallow: /index.jpg Disallow: /index.gif Disallow: /index.css Disallow: /index.js Disallow: /index.zip Disallow: /pim=true/ Disallow: /pv=unsurrounded/ Disallow: /format=xml/ Disallow: /vv=rec/ Disallow: /vv=webradio/ Disallow: /vv=mitte/ Disallow: /*?datum=* Disallow: /*date=* Disallow: /forum/ Disallow: /swr1/rp/musik/musikrecherche/ Disallow: /swr1/bw/musik/musikrecherche/ Disallow: /vv=printall/ Disallow: /vv=zoomNoJs/ Disallow: /static/test/ Disallow: /*tagcloud.swf* Disallow: /vv=wma/ Allow: /export/rss/ Allow: /export/jetztlaeuft/ # definitions for the Googlebot and Googlebot-Mobile User-agent: Googlebot Crawl-Delay: 30 Disallow: /*cgi-bin* Disallow: /*vv=sendungswecker* Disallow: /*pv=print* Disallow: /*pv=mplayer* Disallow: /*vv=pdf* Disallow: /*export* Disallow: /*pv=plain* Disallow: /*pv=email* Disallow: /*index.jpg* Disallow: /*index.gif* Disallow: /*index.css* Disallow: /*index.js* Disallow: /*index.zip* Disallow: /*sid=* Disallow: /*session* Disallow: /*pim=true* Disallow: /*pv=unsurrounded* Disallow: /*format=xml* Disallow: /*vv=rec* Disallow: /*vv=webradio* Disallow: /*vv=mitte* Disallow: /*?datum=* Disallow: /*date=* Disallow: /forum/ Disallow: /swr1/rp/musik/musikrecherche/ Disallow: /swr1/bw/musik/musikrecherche/ Disallow: /swr2/programm/sendungen/leben/rueckschau/-/id=660144/nid=660144/did=1757054/xbewx5/index.html Disallow: /swr2/programm/sendungen/leben/rueckschau/-/id=660144/nid=660144/did=1754426/1kugbu8/index.html Disallow: /swr2/programm/sendungen/leben/rueckschau/-/id=660144/nid=660144/did=1754828/9i7no3/index.html Disallow: /*vv=printall* Disallow: /*vv=zoomNoJs* Disallow: /static/test/ Disallow: /*tagcloud.swf* Disallow: /*vv=wma* Allow: /*export/rss* Allow: /*export/jetztlaeuft* #definitions for other bots User-agent: Mediapartners-Google Disallow: / User-agent: Googlebot-Image Disallow: / User-agent: Adsbot-Google Disallow: / User-agent: vscooter Disallow: / User-agent: ia_archiver Disallow: / User-agent: Teleport* Disallow: / User-agent: Webwhacker* Disallow: / User-agent: Webzip* Disallow: / User-agent: Net Attache* Disallow: / User-agent: SiteSnagger* Disallow: / User-agent: HTTrack* Disallow: / User-agent: WebCapture* Disallow: / User-agent: WebSauger* Disallow: / User-agent: yacybot Disallow: / Sitemap: http://www.swr.de/static/sitemap.xml