Nutch 1.3

7 June 2011 - Apache Nutch 1.3 Released

​get nutch

• conf/nutch-site.xml

<property>
  <name>http.agent.name</name>
  <value>waue_test</value>
</property>

• conf/crawl-urlfilter.txt

-^(file|ftp|mailto):

# skip image and other suffixes we can't yet parse
-\.(gif|GIF|jpg|JPG|png|PNG|ico|ICO|css|sit|eps|wmf|zip|ppt|mpg|xls|gz|rpm|tgz|mov|MOV|exe|jpeg|JPEG|bmp|BMP)$

# 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 anything else
+.

echo "http://lucene.apache.org/nutch/" >urls/url.txt
bin/nutch crawl urls -dir crawl2 -depth 2 -topN 50