欧美日韩二区三区,一区二区中文视频,国产精品一区二区3区

<?xml version="1.0"?>

<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>

<name>http.agent.name</name>

<value>Nutch</value>

<description>HTTP 'User-Agent' request header. MUST NOT be empty -

please set this to a single word uniquely related to your organization.

NOTE: You should also check other related properties:

http.robots.agents

http.agent.description

http.agent.url

http.agent.email

http.agent.version

and set their values appropriately.

</description>

</property>

<name>http.robots.agents</name>

<value>Nutch,*</value>

<description>The agent strings we'll look for in robots.txt files,

comma-separated, in decreasing order of precedence. You should

put the value of http.agent.name as the first agent name, and keep the

default * at the end of the list. E.g.: BlurflDev,Blurfl,*

</description>

</property>

<name>http.agent.description</name>

<value>Nutch Search Engineer</value>

<description>Further description of our bot- this text is used in

the User-Agent header. It appears in parenthesis after the agent name.

</description>

</property>

<name>http.agent.url</name>

<value>http://lucene.apache.org/nutch/bot.html</value>

<description>A URL to advertise in the User-Agent header. This will

appear in parenthesis after the agent name. Custom dictates that this

should be a URL of a page explaining the purpose and behavior of this

crawler.

</description>

</property>

<name>http.agent.email</name>

<value>nutch-agent@lucene.apache.org</value>

<description>An email address to advertise in the HTTP 'From' request

header and User-Agent header. A good practice is to mangle this

address (e.g. 'info at example dot com') to avoid spamming.

</description>

</property>

</configuration>

</path>

<echo>crwaling starting

</echo>

</java>

<echo>crwaling finished

</echo>

</target>

</project>