| # Creative Commnons crawl filter |
| |
| # 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|https): |
| |
| # skip image and other suffixes we can't yet parse |
| -\.(gif|GIF|jpg|JPG|ico|ICO|css|sit|eps|wmf|rtf|zip|ppt|mpg|xls|gz|rpm|tgz|mov|MOV|exe|mp3|rss|xml|doc|pdf|txt|DOC|PDF|TXT)$ |
| |
| # skip URLs containing certain characters as probable queries, etc. |
| -[?*!@=] |
| |
| # accept anything else |
| +. |
