| # The url filter file used by the crawl command. |
| |
| # Better for intranet crawling. |
| # Be sure to change MY.DOMAIN.NAME to your domain name. |
| |
| # Each non-comment, non-blank line contains a regular expression |
| # prefixed by '+' or '-'. The first matching pattern in the file |
| # determines whether a URL is included or ignored. If no pattern |
| # matches, the URL is ignored. |
| |
| # skip file:, ftp:, & mailto: urls |
| -^(?:file|ftp|mailto): |
| |
| # skip image and other suffixes we can't yet parse |
| -(?i)\.(?:gif|jpg|ico|css|sit|eps|wmf|zip|ppt|mpg|xls|gz|rpm|tgz|mov|exe|png)$ |
| |
| # skip URLs containing certain characters as probable queries, etc. |
| -[?*!@=] |
| |
| # skip URLs with slash-delimited segment that repeats 3+ times, to break loops |
| -.*(/.+?)/.*?\1/.*?\1/ |
| |
| # accept hosts in MY.DOMAIN.NAME |
| +^https?://(?:[a-z0-9]*\.)*MY.DOMAIN.NAME/ |
| |
| # skip everything else |
| -. |
