Mercurial > hg > nutch-mpiwg-plugins

comparison conf/regex-urlfilter.txt @ 0:3b37d71af924 default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
iniitial
author dwinter
date Tue, 26 Feb 2013 15:50:30 +0100
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:3b37d71af924
1 # Licensed to the Apache Software Foundation (ASF) under one or more
2 # contributor license agreements. See the NOTICE file distributed with
3 # this work for additional information regarding copyright ownership.
4 # The ASF licenses this file to You under the Apache License, Version 2.0
5 # (the "License"); you may not use this file except in compliance with
6 # the License. You may obtain a copy of the License at
7 #
8 # http://www.apache.org/licenses/LICENSE-2.0
9 #
10 # Unless required by applicable law or agreed to in writing, software
11 # distributed under the License is distributed on an "AS IS" BASIS,
12 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13 # See the License for the specific language governing permissions and
14 # limitations under the License.
15
16
17 # The default url filter.
18 # Better for whole-internet crawling.
19
20 # Each non-comment, non-blank line contains a regular expression
21 # prefixed by '+' or '-'. The first matching pattern in the file
22 # determines whether a URL is included or ignored. If no pattern
23 # matches, the URL is ignored.
24
25 # skip file: ftp: and mailto: urls
26 -^(file|ftp|mailto):
27
28 # skip image and other suffixes we can't yet parse
29 # for a more extensive coverage use the urlfilter-suffix plugin
30 -\.(gif|GIF|jpg|JPG|png|PNG|ico|ICO|css|CSS|sit|SIT|eps|EPS|wmf|WMF|zip|ZIP|ppt|PPT|mpg|MPG|xls|XLS|gz|GZ|rpm|RPM|tgz|TGZ|mov|MOV|exe|EXE|jpeg|JPEG|bmp|BMP|js|JS)$
31
32 # skip URLs containing certain characters as probable queries, etc.
33 -[?*!@=]
34
35 # skip URLs with slash-delimited segment that repeats 3+ times, to break loops
36 -.*(/[^/]+)/[^/]+\1/[^/]+\1/
37
38
39 # accept anything else
40 +^http://127.0.0.1:18080/www_neu/.*
41 #+^http://127.0.0.1:18080/www_neu/en/staff/index.html
42
43 #+^http://127.0.0.1:18080/www_neu/en/staff/members/.*
44
45 #+^http://127.0.0.1:18080/www_neu/en/research/index.html
46
47 #+^http://127.0.0.1:18080/www_neu/en/research/projects/.*
48
49
50
51
52