Repository: nutch Updated Branches: refs/heads/NUTCH-2292 9f3ba3eda -> 0bf453e57 (forced update)
http://git-wip-us.apache.org/repos/asf/nutch/blob/0bf453e5/nutch-plugins/urlfilter-regex/src/test/resources/IntranetCrawling.rules ---------------------------------------------------------------------- diff --git a/nutch-plugins/urlfilter-regex/src/test/resources/IntranetCrawling.rules b/nutch-plugins/urlfilter-regex/src/test/resources/IntranetCrawling.rules new file mode 100644 index 0000000..705bdb2 --- /dev/null +++ b/nutch-plugins/urlfilter-regex/src/test/resources/IntranetCrawling.rules @@ -0,0 +1,27 @@ +# 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 +-\.(gif|GIF|jpg|JPG|ico|ICO|css|sit|eps|wmf|zip|ppt|mpg|xls|gz|rpm|tgz|mov|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 ++^http://([a-z0-9]*\.)*MY.DOMAIN.NAME/ + +# skip everything else +-.
