1 | # This is a example w3mir config file. The file and options are fully
|
---|
2 | # documented in the w3mir man page, and a lot is spelled out in the
|
---|
3 | # w3mir-HOWTO. This file might not be completely updated, but the man
|
---|
4 | # page should be.
|
---|
5 | #
|
---|
6 | # Comment lines start with '#'. Comments are not allowed at end of
|
---|
7 | # lines. The keywords are not casesensitive, but some settings are,
|
---|
8 | # notably fetch/ignore/apply settings, as well as the urls given.
|
---|
9 | #
|
---|
10 | # Available options: recurse, no-date-check, only-nonexistent, list-urls,
|
---|
11 | # lowercase. It is not default to recurse. Options must be the
|
---|
12 | # first directive to appear in the config file.
|
---|
13 | # The options directive needs to be the first directive in the config file
|
---|
14 | # and there can only be one.
|
---|
15 | Options: recurse
|
---|
16 | # Multipele options:
|
---|
17 | # Options: recurse, only-nonexistent
|
---|
18 | # This directive was previously named 'Fetch-options'
|
---|
19 | #
|
---|
20 | # Start here:
|
---|
21 | URL: http://www.stud.ifi.uio.no/~janl/
|
---|
22 | #
|
---|
23 | #
|
---|
24 | # How much noise to make, one of quiet, brief or chatty. Default is brief
|
---|
25 | #Verbosity: brief
|
---|
26 | #
|
---|
27 | # Initial referer. Some servers are very picky....
|
---|
28 | #Initial-Referer: http://foo.bar/
|
---|
29 | #
|
---|
30 | # Headers to disable for anonymitys sake:
|
---|
31 | #Disable-headers: referer, user
|
---|
32 | #
|
---|
33 | # Nicenes, robotrules can be true or false
|
---|
34 | #Robot-Rules: true
|
---|
35 | # Default pause between http connections is now 0 seconds
|
---|
36 | # Pause: 0
|
---|
37 | # Pause between retries, in seconds. If w3mir runs as a once-a-day thing
|
---|
38 | # this can and should be high. I suggest at least one hour (3600 seconds).
|
---|
39 | #Retry-Pause: 600
|
---|
40 | # How many times a failed retrival is retried.
|
---|
41 | #Retries: 3
|
---|
42 | #
|
---|
43 | # URL selection. Order is significant, first Fetch/Ignore rule overrides
|
---|
44 | # later rules. Supply as many as you want. If not matched by ignore rules
|
---|
45 | # a doc is gotten.
|
---|
46 | #Fetch: *.html
|
---|
47 | #
|
---|
48 | # Ignore urls we can't copy anyway. Actually w3mir can copy
|
---|
49 | # many cgi things with no problems. But not always.
|
---|
50 | Ignore: *.cgi
|
---|
51 | Ignore: *-cgi
|
---|
52 | Ignore: *.map
|
---|
53 | #
|
---|
54 | # RE variants are full perl REs. Mix freely with the others. These
|
---|
55 | # must be legal perl REs, including the starting m and any
|
---|
56 | # options you want, like 'i'.
|
---|
57 | #
|
---|
58 | #Fetch-RE: m/jpeg/
|
---|
59 | #Ignore-RE: m/\.gif$/
|
---|
60 | #
|
---|
61 | # URL manipulation. _All_ rules are applied in order. If lowercasing
|
---|
62 | # options is given that is done first. This must be a legal perl
|
---|
63 | # substitution RE. Including the starting s and any options you want,
|
---|
64 | # like 'g' and 'i'.
|
---|
65 | #
|
---|
66 | # This changes the name of all .gif files to .fif
|
---|
67 | #Apply: s/\.gif$/.fif/
|
---|
68 | #
|
---|
69 | # HTTP Proxy server:
|
---|
70 | #HTTP-Proxy: www-cache.uio.no:3128
|
---|
71 | #
|
---|
72 | # HTTP Proxy options:
|
---|
73 | # - 'revalidate': Force proxy to revalidate cached documents.
|
---|
74 | # - 'refresh': Force proxy to get cached documents from server _again_.
|
---|
75 | # - 'no-store': Use if the contents of the documents is sensitive.
|
---|
76 | # - 'no-pragma': Force use of HTTP/1.1 'Cache-Control:' header.
|
---|
77 | # If only 'refresh' is specified the default is to use the 'Pragma: no-cache'
|
---|
78 | # HTTP/1.0 header, this can be overruled with the 'no-pragma' option.
|
---|
79 | # You can be fairly sure any proxy will understand 'refresh', ONLY HTTP/1.1
|
---|
80 | # proxies will understand 'revalidate' and 'no-store'.
|
---|
81 | #proxy-options: refresh
|
---|
82 | #
|
---|
83 | # HTTP Proxy authentication. The mechanism is simpleminded, we either need
|
---|
84 | # to authenticate ourselves with the proxy or not, and there can only be
|
---|
85 | # one user/password tuple, domain/realm information is ignored...
|
---|
86 | # HTTP-Proxy-user: foo
|
---|
87 | # HTTP-Proxy-passwd: bar
|
---|
88 | #
|
---|
89 | # What to do with files, one of save, stdout or forget.
|
---|
90 | #File-disposition: save
|
---|
91 | #
|
---|
92 | # Debug level
|
---|
93 | #Debug: 0|1|2
|
---|
94 | #
|
---|
95 | # Umask, if not the default
|
---|
96 | #Umask: 077
|
---|
97 | #
|
---|
98 | # HTML document editing options
|
---|
99 | #Header: Mirrored from http://www.ifi.uio.no/~janl/ts/
|
---|
100 | #Remove-nomirror: true
|
---|
101 | #
|
---|
102 | # Authentication:
|
---|
103 | #Auth-domain: server:port/realm
|
---|
104 | #Auth-user: me
|
---|
105 | #Auth-passwd: my_password
|
---|
106 | #
|
---|
107 | # You can use '*' in place of server:port and/or realm:
|
---|
108 | #Auth-domain: */*
|
---|
109 | #Auth-user: otherme
|
---|
110 | #Auth-passwd: otherpassword
|
---|
111 | #
|
---|
112 |
|
---|
113 | # 'Fixup' is done by the external w3mfix program. If you want a
|
---|
114 | # mirror that's browseable in a filesystem (as opposed to via a http
|
---|
115 | # server) just put this in:
|
---|
116 | Fixup: run
|
---|
117 |
|
---|
118 | # Related is this, what is the name of the file the http server serves
|
---|
119 | # when a directory URL is requested? w3mir default is index.html.
|
---|
120 | #Index-name: welcome.html
|
---|