| # The default url filter. |
| # Better for whole-internet crawling. |
| |
| # 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: and mailto: urls |
| -^(file|ftp|mailto): |
| |
| # skip image and other suffixes we can't yet parse |
| -\.(gif|GIF|jpg|JPG|ico|ICO|css|sit|eps|wmf|zip|ppt|mpg|xls|gz|rpm|tgz|mov|MOV|exe)$ |
| |
| # 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 anything else |
| +. |