#
# Configuration file for crawl.
# Do not use quotes.
#
[General]
# Directives that determine which URL is being followed
Url-Include=http://.*\.citi\.umich\.edu
Url-Exclude=([^a-z]ads\.|\.(ico|eps|ps|gz|c|h|tar|exe|doc|pdf|ppt|txt|diff)$)

# Directives that determine which images are downloaded and where
# they will be saved.
Img-Include=\.(jpg|jpeg)
Img-Exclude=thumbs\.
Img-Directory=.

# The maximum depth of the crawl, -1 means unlimited, be very
# careful with this.
#Max-Depth=-1

# An external filter that takes URL on stdin, it must return either
# 'n' or 'y' on stdout.
#External-Filter=./external

#Minimum and maximum length of media, unless overwritten below.
Min-Length=20000
Max-Length=400000

[HTTP]
#Agent=Crawl/0.2
#Use-Robots=1
Connections=20
State-File=crawl.state

[image/jpeg]
Min-Length=20000
Max-Length=200000

[audio/mpeg3]
Min-Length=1000000
Max-Length=30000000

[video/mpeg]
Min-Length=2000000
Max-Length=600000000