| 1 | {{{ |
| 2 | # The url filter file used by the crawl command. |
| 3 | |
| 4 | # Better for intranet crawling. |
| 5 | # Be sure to change MY.DOMAIN.NAME to your domain name. |
| 6 | |
| 7 | # Each non-comment, non-blank line contains a regular expression |
| 8 | # prefixed by '+' or '-'. The first matching pattern in the file |
| 9 | # determines whether a URL is included or ignored. If no pattern |
| 10 | # matches, the URL is ignored. |
| 11 | |
| 12 | # skip file:, ftp:, & mailto: urls |
| 13 | -^(file|ftp|mailto): |
| 14 | |
| 15 | # skip image and other suffixes we can't yet parse |
| 16 | -\.(gif|GIF|jpg|JPG|png|PNG|ico|ICO|css|sit|eps|wmf|zip|ppt|mpg|xls|gz|rpm|tgz|mov|MOV|exe|jpeg|JPEG|bmp|BMP|pdf|PDF)$ |
| 17 | |
| 18 | # skip URLs containing certain characters as probable queries, etc. |
| 19 | -[*!@] |
| 20 | |
| 21 | # skip URLs with slash-delimited segment that repeats 3+ times, to break loops |
| 22 | -.*(/.+?)/.*?\1/.*?\1/ |
| 23 | |
| 24 | # accept hosts in MY.DOMAIN.NAME |
| 25 | +^http://([a-z0-9]*\.)*.*/ |
| 26 | |
| 27 | # skip everything else |
| 28 | -. |
| 29 | }}} |