Sincere greetings to all of the apache users!
I'd like to ask you about the reason of nutch 1.10 not following URLS,
not even the ones internal to the domain I'm trying to explore. Attached
you shall find my nutch-default.xml
Thank you in advance.
<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<!--
Licensed to the Apache Software Foundation (ASF) under one or more
contributor license agreements. See the NOTICE file distributed with
this work for additional information regarding copyright ownership.
The ASF licenses this file to You under the Apache License, Version 2.0
(the "License"); you may not use this file except in compliance with
the License. You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
-->
<!-- Do not modify this file directly. Instead, copy entries that you -->
<!-- wish to modify from this file into nutch-site.xml and change them -->
<!-- there. If nutch-site.xml does not already exist, create it. -->
<configuration>
<!-- general properties -->
<property>
<name>store.ip.address</name>
<value>false</value>
<description>Enables us to capture the specific IP address
(InetSocketAddress) of the host which we connect to via
the given protocol. Currently supported is protocol-ftp and
http.
</description>
</property>
<!-- file properties -->
<property>
<name>file.content.limit</name>
<value>65536</value>
<description>The length limit for downloaded content using the file://
protocol, in bytes. If this value is nonnegative (>=0), content longer
than it will be truncated; otherwise, no truncation at all. Do not
confuse this setting with the http.content.limit setting.
</description>
</property>
<property>
<name>file.crawl.parent</name>
<value>true</value>
<description>The crawler is not restricted to the directories that you specified in the
Urls file but it is jumping into the parent directories as well. For your own crawlings you can
change this bahavior (set to false) the way that only directories beneath the directories that you specify get
crawled.</description>
</property>
<property>
<name>file.crawl.redirect_noncanonical</name>
<value>true</value>
<description>
If true, protocol-file treats non-canonical file names as
redirects and does not canonicalize file names internally. A file
name containing symbolic links as path elements is then not
resolved and "fetched" but recorded as redirect with the
canonical name (all links on path are resolved) as redirect
target.
</description>
</property>
<property>
<name>file.content.ignored</name>
<value>true</value>
<description>If true, no file content will be saved during fetch.
And it is probably what we want to set most of time, since file:// URLs
are meant to be local and we can always use them directly at parsing
and indexing stages. Otherwise file contents will be saved.
!! NO IMPLEMENTED YET !!
</description>
</property>
<!-- HTTP properties -->
<property>
<name>http.agent.name</name>
<value>nutch_crawler</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>
<property>
<name>http.robots.agents</name>
<value></value>
<description>Any other agents, apart from 'http.agent.name', that the robots
parser would look for in robots.txt. Multiple agents can be provided using
comma as a delimiter. eg. mybot,foo-spider,bar-crawler
The ordering of agents does NOT matter and the robots parser would make
decision based on the agent which matches first to the robots rules.
Also, there is NO need to add a wildcard (ie. "*") to this string as the
robots parser would smartly take care of a no-match situation.
If no value is specified, by default HTTP agent (ie. 'http.agent.name')
would be used for user agent matching by the robots parser.
</description>
</property>
<property>
<name>http.robot.rules.whitelist</name>
<value></value>
<description>Comma separated list of hostnames or IP addresses to ignore
robot rules parsing for. Use with care and only if you are explicitly
allowed by the site owner to ignore the site's robots.txt!
</description>
</property>
<property>
<name>http.robots.403.allow</name>
<value>true</value>
<description>Some servers return HTTP status 403 (Forbidden) if
/robots.txt doesn't exist. This should probably mean that we are
allowed to crawl the site nonetheless. If this is set to false,
then such sites will be treated as forbidden.</description>
</property>
<property>
<name>http.agent.description</name>
<value></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>
<property>
<name>http.agent.url</name>
<value></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>
<property>
<name>http.agent.email</name>
<value></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>
<property>
<name>http.agent.version</name>
<value>Nutch-1.10</value>
<description>A version string to advertise in the User-Agent
header.</description>
</property>
<property>
<name>http.agent.rotate</name>
<value>false</value>
<description>
If true, instead of http.agent.name, alternating agent names are
chosen from a list provided via http.agent.rotate.file.
</description>
</property>
<property>
<name>http.agent.rotate.file</name>
<value>agents.txt</value>
<description>
File containing alternative user agent names to be used instead of
http.agent.name on a rotating basis if http.agent.rotate is true.
Each line of the file should contain exactly one agent
specification including name, version, description, URL, etc.
</description>
</property>
<property>
<name>http.agent.host</name>
<value></value>
<description>Name or IP address of the host on which the Nutch crawler
would be running. Currently this is used by 'protocol-httpclient'
plugin.
</description>
</property>
<property>
<name>http.timeout</name>
<value>10000</value>
<description>The default network timeout, in milliseconds.</description>
</property>
<property>
<name>http.max.delays</name>
<value>100</value>
<description>The number of times a thread will delay when trying to
fetch a page. Each time it finds that a host is busy, it will wait
fetcher.server.delay. After http.max.delays attepts, it will give
up on the page for now.</description>
</property>
<property>
<name>http.content.limit</name>
<value>65536</value>
<description>The length limit for downloaded content using the http://
protocol, in bytes. If this value is nonnegative (>=0), content longer
than it will be truncated; otherwise, no truncation at all. Do not
confuse this setting with the file.content.limit setting.
</description>
</property>
<property>
<name>http.proxy.host</name>
<value></value>
<description>The proxy hostname. If empty, no proxy is used.</description>
</property>
<property>
<name>http.proxy.port</name>
<value></value>
<description>The proxy port.</description>
</property>
<property>
<name>http.proxy.username</name>
<value></value>
<description>Username for proxy. This will be used by
'protocol-httpclient', if the proxy server requests basic, digest
and/or NTLM authentication. To use this, 'protocol-httpclient' must
be present in the value of 'plugin.includes' property.
NOTE: For NTLM authentication, do not prefix the username with the
domain, i.e. 'susam' is correct whereas 'DOMAIN\susam' is incorrect.
</description>
</property>
<property>
<name>http.proxy.password</name>
<value></value>
<description>Password for proxy. This will be used by
'protocol-httpclient', if the proxy server requests basic, digest
and/or NTLM authentication. To use this, 'protocol-httpclient' must
be present in the value of 'plugin.includes' property.
</description>
</property>
<property>
<name>http.proxy.realm</name>
<value></value>
<description>Authentication realm for proxy. Do not define a value
if realm is not required or authentication should take place for any
realm. NTLM does not use the notion of realms. Specify the domain name
of NTLM authentication as the value for this property. To use this,
'protocol-httpclient' must be present in the value of
'plugin.includes' property.
</description>
</property>
<property>
<name>http.auth.file</name>
<value>httpclient-auth.xml</value>
<description>Authentication configuration file for
'protocol-httpclient' plugin.
</description>
</property>
<property>
<name>http.verbose</name>
<value>false</value>
<description>If true, HTTP will log more verbosely.</description>
</property>
<property>
<name>http.redirect.max</name>
<value>0</value>
<description>The maximum number of redirects the fetcher will follow when
trying to fetch a page. If set to negative or 0, fetcher won't immediately
follow redirected URLs, instead it will record them for later fetching.
</description>
</property>
<property>
<name>http.useHttp11</name>
<value>false</value>
<description>NOTE: at the moment this works only for protocol-httpclient.
If true, use HTTP 1.1, if false use HTTP 1.0 .
</description>
</property>
<property>
<name>http.accept.language</name>
<value>it-it,it;q=0.7,*;q=0.3</value>
<description>Value of the "Accept-Language" request header field.
This allows selecting non-English language as default one to retrieve.
It is a useful setting for search engines build for certain national group.
</description>
</property>
<property>
<name>http.accept</name>
<value>text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8</value>
<description>Value of the "Accept" request header field.
</description>
</property>
<property>
<name>http.store.responsetime</name>
<value>true</value>
<description>Enables us to record the response time of the
host which is the time period between start connection to end
connection of a pages host. The response time in milliseconds
is stored in CrawlDb in CrawlDatum's meta data under key "_rs_"
</description>
</property>
<property>
<name>http.enable.if.modified.since.header</name>
<value>true</value>
<description>Whether Nutch sends an HTTP If-Modified-Since header. It reduces
bandwidth when enabled by not downloading pages that respond with an HTTP
Not-Modified header. URL's that are not downloaded are not passed through
parse or indexing filters. If you regularly modify filters, you should force
Nutch to also download unmodified pages by disabling this feature.
</description>
</property>
<!-- FTP properties -->
<property>
<name>ftp.username</name>
<value>anonymous</value>
<description>ftp login username.</description>
</property>
<property>
<name>ftp.password</name>
<value>[email protected]</value>
<description>ftp login password.</description>
</property>
<property>
<name>ftp.content.limit</name>
<value>65536</value>
<description>The length limit for downloaded content, in bytes.
If this value is nonnegative (>=0), content longer than it will be truncated;
otherwise, no truncation at all.
Caution: classical ftp RFCs never defines partial transfer and, in fact,
some ftp servers out there do not handle client side forced close-down very
well. Our implementation tries its best to handle such situations smoothly.
</description>
</property>
<property>
<name>ftp.timeout</name>
<value>60000</value>
<description>Default timeout for ftp client socket, in millisec.
Please also see ftp.keep.connection below.</description>
</property>
<property>
<name>ftp.server.timeout</name>
<value>100000</value>
<description>An estimation of ftp server idle time, in millisec.
Typically it is 120000 millisec for many ftp servers out there.
Better be conservative here. Together with ftp.timeout, it is used to
decide if we need to delete (annihilate) current ftp.client instance and
force to start another ftp.client instance anew. This is necessary because
a fetcher thread may not be able to obtain next request from queue in time
(due to idleness) before our ftp client times out or remote server
disconnects. Used only when ftp.keep.connection is true (please see below).
</description>
</property>
<property>
<name>ftp.keep.connection</name>
<value>false</value>
<description>Whether to keep ftp connection. Useful if crawling same host
again and again. When set to true, it avoids connection, login and dir list
parser setup for subsequent urls. If it is set to true, however, you must
make sure (roughly):
(1) ftp.timeout is less than ftp.server.timeout
(2) ftp.timeout is larger than (fetcher.threads.fetch * fetcher.server.delay)
Otherwise there will be too many "delete client because idled too long"
messages in thread logs.</description>
</property>
<property>
<name>ftp.follow.talk</name>
<value>false</value>
<description>Whether to log dialogue between our client and remote
server. Useful for debugging.</description>
</property>
<!-- web db properties -->
<property>
<name>db.fetch.interval.default</name>
<value>2592000</value>
<description>The default number of seconds between re-fetches of a page (30 days).
</description>
</property>
<property>
<name>db.fetch.interval.max</name>
<value>7776000</value>
<description>The maximum number of seconds between re-fetches of a page
(90 days). After this period every page in the db will be re-tried, no
matter what is its status.
</description>
</property>
<property>
<name>db.fetch.schedule.class</name>
<value>org.apache.nutch.crawl.DefaultFetchSchedule</value>
<description>The implementation of fetch schedule. DefaultFetchSchedule simply
adds the original fetchInterval to the last fetch time, regardless of
page changes.</description>
</property>
<property>
<name>db.fetch.schedule.adaptive.inc_rate</name>
<value>0.4</value>
<description>If a page is unmodified, its fetchInterval will be
increased by this rate. This value should not
exceed 0.5, otherwise the algorithm becomes unstable.</description>
</property>
<property>
<name>db.fetch.schedule.adaptive.dec_rate</name>
<value>0.2</value>
<description>If a page is modified, its fetchInterval will be
decreased by this rate. This value should not
exceed 0.5, otherwise the algorithm becomes unstable.</description>
</property>
<property>
<name>db.fetch.schedule.adaptive.min_interval</name>
<value>60.0</value>
<description>Minimum fetchInterval, in seconds.</description>
</property>
<property>
<name>db.fetch.schedule.adaptive.max_interval</name>
<value>31536000.0</value>
<description>Maximum fetchInterval, in seconds (365 days).
NOTE: this is limited by db.fetch.interval.max. Pages with
fetchInterval larger than db.fetch.interval.max
will be fetched anyway.</description>
</property>
<property>
<name>db.fetch.schedule.adaptive.sync_delta</name>
<value>true</value>
<description>If true, try to synchronize with the time of page change.
by shifting the next fetchTime by a fraction (sync_rate) of the difference
between the last modification time, and the last fetch time.</description>
</property>
<property>
<name>db.fetch.schedule.adaptive.sync_delta_rate</name>
<value>0.3</value>
<description>See sync_delta for description. This value should not
exceed 0.5, otherwise the algorithm becomes unstable.</description>
</property>
<property>
<name>db.fetch.schedule.mime.file</name>
<value>adaptive-mimetypes.txt</value>
<description>The configuration file for the MimeAdaptiveFetchSchedule.
</description>
</property>
<property>
<name>db.update.additions.allowed</name>
<value>true</value>
<description>If true, updatedb will add newly discovered URLs, if false
only already existing URLs in the CrawlDb will be updated and no new
URLs will be added.
</description>
</property>
<property>
<name>db.preserve.backup</name>
<value>true</value>
<description>If true, updatedb will keep a backup of the previous CrawlDB
version in the old directory. In case of disaster, one can rename old to
current and restore the CrawlDB to its previous state.
</description>
</property>
<property>
<name>db.update.purge.404</name>
<value>true</value>
<description>If true, updatedb will add purge records with status DB_GONE
from the CrawlDB.
</description>
</property>
<property>
<name>db.url.normalizers</name>
<value>true</value>
<description>Normalize urls when updating crawldb</description>
</property>
<property>
<name>db.url.filters</name>
<value>false</value>
<description>Filter urls when updating crawldb</description>
</property>
<property>
<name>db.update.max.inlinks</name>
<value>50000</value>
<description>Maximum number of inlinks to take into account when updating
a URL score in the crawlDB. Only the best scoring inlinks are kept.
</description>
</property>
<property>
<name>db.ignore.internal.links</name>
<value>false</value>
<description>If true, when adding new links to a page, links from
the same host are ignored. This is an effective way to limit the
size of the link database, keeping only the highest quality
links.
</description>
</property>
<property>
<name>db.ignore.external.links</name>
<value>false</value>
<description>If true, outlinks leading from a page to external hosts
will be ignored. This is an effective way to limit the crawl to include
only initially injected hosts, without creating complex URLFilters.
</description>
</property>
<property>
<name>db.injector.overwrite</name>
<value>false</value>
<description>Whether existing records in the CrawlDB will be overwritten
by injected records.
</description>
</property>
<property>
<name>db.injector.update</name>
<value>false</value>
<description>If true existing records in the CrawlDB will be updated with
injected records. Old meta data is preserved. The db.injector.overwrite
parameter has precedence.
</description>
</property>
<property>
<name>db.score.injected</name>
<value>1.0</value>
<description>The score of new pages added by the injector.
</description>
</property>
<property>
<name>db.score.link.external</name>
<value>1.0</value>
<description>The score factor for new pages added due to a link from
another host relative to the referencing page's score. Scoring plugins
may use this value to affect initial scores of external links.
</description>
</property>
<property>
<name>db.score.link.internal</name>
<value>2.0</value>
<description>The score factor for pages added due to a link from the
same host, relative to the referencing page's score. Scoring plugins
may use this value to affect initial scores of internal links.
</description>
</property>
<property>
<name>db.score.count.filtered</name>
<value>false</value>
<description>The score value passed to newly discovered pages is
calculated as a fraction of the original page score divided by the
number of outlinks. If this option is false, only the outlinks that passed
URLFilters will count, if it's true then all outlinks will count.
</description>
</property>
<property>
<name>db.max.inlinks</name>
<value>50000</value>
<description>Maximum number of Inlinks per URL to be kept in LinkDb.
If "invertlinks" finds more inlinks than this number, only the first
N inlinks will be stored, and the rest will be discarded.
</description>
</property>
<property>
<name>db.max.outlinks.per.page</name>
<value>-1</value>
<description>The maximum number of outlinks that we'll process for a page.
If this value is nonnegative (>=0), at most db.max.outlinks.per.page outlinks
will be processed for a page; otherwise, all outlinks will be processed.
</description>
</property>
<property>
<name>db.max.anchor.length</name>
<value>100</value>
<description>The maximum number of characters permitted in an anchor.
</description>
</property>
<property>
<name>db.parsemeta.to.crawldb</name>
<value></value>
<description>Comma-separated list of parse metadata keys to transfer to the crawldb (NUTCH-779).
Assuming for instance that the languageidentifier plugin is enabled, setting the value to 'lang'
will copy both the key 'lang' and its value to the corresponding entry in the crawldb.
</description>
</property>
<property>
<name>db.fetch.retry.max</name>
<value>3</value>
<description>The maximum number of times a url that has encountered
recoverable errors is generated for fetch.</description>
</property>
<property>
<name>db.signature.class</name>
<value>org.apache.nutch.crawl.MD5Signature</value>
<description>The default implementation of a page signature. Signatures
created with this implementation will be used for duplicate detection
and removal.</description>
</property>
<property>
<name>db.signature.text_profile.min_token_len</name>
<value>2</value>
<description>Minimum token length to be included in the signature.
</description>
</property>
<property>
<name>db.signature.text_profile.quant_rate</name>
<value>0.01</value>
<description>Profile frequencies will be rounded down to a multiple of
QUANT = (int)(QUANT_RATE * maxFreq), where maxFreq is a maximum token
frequency. If maxFreq > 1 then QUANT will be at least 2, which means that
for longer texts tokens with frequency 1 will always be discarded.
</description>
</property>
<!-- generate properties -->
<property>
<name>generate.max.count</name>
<value>-1</value>
<description>The maximum number of urls in a single
fetchlist. -1 if unlimited. The urls are counted according
to the value of the parameter generator.count.mode.
</description>
</property>
<property>
<name>generate.count.mode</name>
<value>host</value>
<description>Determines how the URLs are counted for generator.max.count.
Default value is 'host' but can be 'domain'. Note that we do not count
per IP in the new version of the Generator.
</description>
</property>
<property>
<name>generate.update.crawldb</name>
<value>false</value>
<description>For highly-concurrent environments, where several
generate/fetch/update cycles may overlap, setting this to true ensures
that generate will create different fetchlists even without intervening
updatedb-s, at the cost of running an additional job to update CrawlDB.
If false, running generate twice without intervening
updatedb will generate identical fetchlists.</description>
</property>
<property>
<name>generate.min.score</name>
<value>0</value>
<description>Select only entries with a score larger than
generate.min.score.</description>
</property>
<property>
<name>generate.min.interval</name>
<value>-1</value>
<description>Select only entries with a retry interval lower than
generate.min.interval. A value of -1 disables this check.</description>
</property>
<!-- urlpartitioner properties -->
<property>
<name>partition.url.mode</name>
<value>byHost</value>
<description>Determines how to partition URLs. Default value is 'byHost',
also takes 'byDomain' or 'byIP'.
</description>
</property>
<property>
<name>crawl.gen.delay</name>
<value>604800000</value>
<description>
This value, expressed in milliseconds, defines how long we should keep the lock on records
in CrawlDb that were just selected for fetching. If these records are not updated
in the meantime, the lock is canceled, i.e. they become eligible for selecting.
Default value of this is 7 days (604800000 ms).
</description>
</property>
<!-- fetcher properties -->
<property>
<name>fetcher.server.delay</name>
<value>5.0</value>
<description>The number of seconds the fetcher will delay between
successive requests to the same server. Note that this might get
overriden by a Crawl-Delay from a robots.txt and is used ONLY if
fetcher.threads.per.queue is set to 1.
</description>
</property>
<property>
<name>fetcher.server.min.delay</name>
<value>0.0</value>
<description>The minimum number of seconds the fetcher will delay between
successive requests to the same server. This value is applicable ONLY
if fetcher.threads.per.queue is greater than 1 (i.e. the host blocking
is turned off).</description>
</property>
<property>
<name>fetcher.max.crawl.delay</name>
<value>30</value>
<description>
If the Crawl-Delay in robots.txt is set to greater than this value (in
seconds) then the fetcher will skip this page, generating an error report.
If set to -1 the fetcher will never skip such pages and will wait the
amount of time retrieved from robots.txt Crawl-Delay, however long that
might be.
</description>
</property>
<property>
<name>fetcher.threads.fetch</name>
<value>10</value>
<description>The number of FetcherThreads the fetcher should use.
This is also determines the maximum number of requests that are
made at once (each FetcherThread handles one connection). The total
number of threads running in distributed mode will be the number of
fetcher threads * number of nodes as fetcher has one map task per node.
</description>
</property>
<property>
<name>fetcher.threads.per.queue</name>
<value>1</value>
<description>This number is the maximum number of threads that
should be allowed to access a queue at one time. Setting it to
a value > 1 will cause the Crawl-Delay value from robots.txt to
be ignored and the value of fetcher.server.min.delay to be used
as a delay between successive requests to the same server instead
of fetcher.server.delay.
</description>
</property>
<property>
<name>fetcher.queue.mode</name>
<value>byHost</value>
<description>Determines how to put URLs into queues. Default value is 'byHost',
also takes 'byDomain' or 'byIP'.
</description>
</property>
<property>
<name>fetcher.verbose</name>
<value>false</value>
<description>If true, fetcher will log more verbosely.</description>
</property>
<property>
<name>fetcher.parse</name>
<value>true</value>
<description>If true, fetcher will parse content. Default is false, which means
that a separate parsing step is required after fetching is finished.</description>
</property>
<property>
<name>fetcher.store.content</name>
<value>true</value>
<description>If true, fetcher will store content.</description>
</property>
<property>
<name>fetcher.timelimit.mins</name>
<value>-1</value>
<description>This is the number of minutes allocated to the fetching.
Once this value is reached, any remaining entry from the input URL list is skipped
and all active queues are emptied. The default value of -1 deactivates the time limit.
</description>
</property>
<property>
<name>fetcher.max.exceptions.per.queue</name>
<value>-1</value>
<description>The maximum number of protocol-level exceptions (e.g. timeouts) per
host (or IP) queue. Once this value is reached, any remaining entries from this
queue are purged, effectively stopping the fetching from this host/IP. The default
value of -1 deactivates this limit.
</description>
</property>
<property>
<name>fetcher.throughput.threshold.pages</name>
<value>-1</value>
<description>The threshold of minimum pages per second. If the fetcher downloads less
pages per second than the configured threshold, the fetcher stops, preventing slow queue's
from stalling the throughput. This threshold must be an integer. This can be useful when
fetcher.timelimit.mins is hard to determine. The default value of -1 disables this check.
</description>
</property>
<property>
<name>fetcher.throughput.threshold.retries</name>
<value>5</value>
<description>The number of times the fetcher.throughput.threshold is allowed to be exceeded.
This settings prevents accidental slow downs from immediately killing the fetcher thread.
</description>
</property>
<property>
<name>fetcher.throughput.threshold.check.after</name>
<value>5</value>
<description>The number of minutes after which the throughput check is enabled.</description>
</property>
<property>
<name>fetcher.threads.timeout.divisor</name>
<value>2</value>
<description>(EXPERT)The thread time-out divisor to use. By default threads have a time-out
value of mapred.task.timeout / 2. Increase this setting if the fetcher waits too
long before killing hanged threads. Be careful, a too high setting (+8) will most likely kill the
fetcher threads prematurely.
</description>
</property>
<property>
<name>fetcher.queue.depth.multiplier</name>
<value>50</value>
<description>(EXPERT)The fetcher buffers the incoming URLs into queues based on the [host|domain|IP]
(see param fetcher.queue.mode). The depth of the queue is the number of threads times the value of this parameter.
A large value requires more memory but can improve the performance of the fetch when the order of the URLS in the fetch list
is not optimal.
</description>
</property>
<property>
<name>fetcher.follow.outlinks.depth</name>
<value>1</value>
<description>(EXPERT)When fetcher.parse is true and this value is greater than 0 the fetcher will extract outlinks
and follow until the desired depth is reached. A value of 1 means all generated pages are fetched and their first degree
outlinks are fetched and parsed too. Be careful, this feature is in itself agnostic of the state of the CrawlDB and does not
know about already fetched pages. A setting larger than 2 will most likely fetch home pages twice in the same fetch cycle.
It is highly recommended to set db.ignore.external.links to true to restrict the outlink follower to URL's within the same
domain. When disabled (false) the feature is likely to follow duplicates even when depth=1.
A value of -1 of 0 disables this feature.
</description>
</property>
<property>
<name>fetcher.follow.outlinks.num.links</name>
<value>50000</value>
<description>(EXPERT)The number of outlinks to follow when fetcher.follow.outlinks.depth is enabled. Be careful, this can multiply
the total number of pages to fetch. This works with fetcher.follow.outlinks.depth.divisor, by default settings the followed outlinks
at depth 1 is 8, not 4.
</description>
</property>
<property>
<name>fetcher.follow.outlinks.depth.divisor</name>
<value>50000</value>
<description>(EXPERT)The divisor of fetcher.follow.outlinks.num.links per fetcher.follow.outlinks.depth. This decreases the number
of outlinks to follow by increasing depth. The formula used is: outlinks = floor(divisor / depth * num.links). This prevents
exponential growth of the fetch list.
</description>
</property>
<property>
<name>fetcher.follow.outlinks.ignore.external</name>
<value>false</value>
<description>Whether to ignore or follow external links. Set db.ignore.external.links to false and this to true to store outlinks
in the output but not follow them. If db.ignore.external.links is true this directive is ignored.
</description>
</property>
<property>
<name>fetcher.bandwidth.target</name>
<value>-1</value>
<description>Target bandwidth in kilobits per sec for each mapper instance. This is used to adjust the number of
fetching threads automatically (up to fetcher.maxNum.threads). A value of -1 deactivates the functionality, in which case
the number of fetching threads is fixed (see fetcher.threads.fetch).</description>
</property>
<property>
<name>fetcher.maxNum.threads</name>
<value>32</value>
<description>Max number of fetch threads allowed when using fetcher.bandwidth.target. Defaults to fetcher.threads.fetch if unspecified or
set to a value lower than it. </description>
</property>
<property>
<name>fetcher.bandwidth.target.check.everyNSecs</name>
<value>30</value>
<description>(EXPERT) Value in seconds which determines how frequently we should reassess the optimal number of fetch threads when using
fetcher.bandwidth.target. Defaults to 30 and must be at least 1.</description>
</property>
<!-- moreindexingfilter plugin properties -->
<property>
<name>moreIndexingFilter.indexMimeTypeParts</name>
<value>true</value>
<description>Determines whether the index-more plugin will split the mime-type
in sub parts, this requires the type field to be multi valued. Set to true for backward
compatibility. False will not split the mime-type.
</description>
</property>
<property>
<name>moreIndexingFilter.mapMimeTypes</name>
<value>false</value>
<description>Determines whether MIME-type mapping is enabled. It takes a
plain text file with mapped MIME-types. With it the user can map both
application/xhtml+xml and text/html to the same target MIME-type so it
can be treated equally in an index. See conf/contenttype-mapping.txt.
</description>
</property>
<!-- AnchorIndexing filter plugin properties -->
<property>
<name>anchorIndexingFilter.deduplicate</name>
<value>false</value>
<description>With this enabled the indexer will case-insensitive deduplicate anchors
before indexing. This prevents possible hundreds or thousands of identical anchors for
a given page to be indexed but will affect the search scoring (i.e. tf=1.0f).
</description>
</property>
<!-- indexingfilter plugin properties -->
<property>
<name>indexingfilter.order</name>
<value></value>
<description>The order by which index filters are applied.
If empty, all available index filters (as dictated by properties
plugin-includes and plugin-excludes above) are loaded and applied in system
defined order. If not empty, only named filters are loaded and applied
in given order. For example, if this property has value:
org.apache.nutch.indexer.basic.BasicIndexingFilter org.apache.nutch.indexer.more.MoreIndexingFilter
then BasicIndexingFilter is applied first, and MoreIndexingFilter second.
Filter ordering might have impact on result if one filter depends on output of
another filter.
</description>
</property>
<property>
<name>indexer.score.power</name>
<value>0.5</value>
<description>Determines the power of link analyis scores. Each
pages's boost is set to <i>score<sup>scorePower</sup></i> where
<i>score</i> is its link analysis score and <i>scorePower</i> is the
value of this parameter. This is compiled into indexes, so, when
this is changed, pages must be re-indexed for it to take
effect.</description>
</property>
<property>
<name>indexer.max.title.length</name>
<value>100</value>
<description>The maximum number of characters of a title that are indexed. A value of -1 disables this check.
</description>
</property>
<property>
<name>indexer.max.content.length</name>
<value>-1</value>
<description>The maximum number of characters of a content that are indexed.
Content beyond the limit is truncated. A value of -1 disables this check.
</description>
</property>
<property>
<name>indexer.add.domain</name>
<value>true</value>
<description>Whether to add the domain field to a NutchDocument.</description>
</property>
<property>
<name>indexer.skip.notmodified</name>
<value>false</value>
<description>Whether the indexer will skip records with a db_notmodified status.
</description>
</property>
<!-- URL normalizer properties -->
<property>
<name>urlnormalizer.order</name>
<value>org.apache.nutch.net.urlnormalizer.basic.BasicURLNormalizer org.apache.nutch.net.urlnormalizer.regex.RegexURLNormalizer</value>
<description>Order in which normalizers will run. If any of these isn't
activated it will be silently skipped. If other normalizers not on the
list are activated, they will run in random order after the ones
specified here are run.
</description>
</property>
<property>
<name>urlnormalizer.regex.file</name>
<value>regex-normalize.xml</value>
<description>Name of the config file used by the RegexUrlNormalizer class.
</description>
</property>
<property>
<name>urlnormalizer.loop.count</name>
<value>1</value>
<description>Optionally loop through normalizers several times, to make
sure that all transformations have been performed.
</description>
</property>
<!-- mime properties -->
<!--
<property>
<name>mime.types.file</name>
<value>tika-mimetypes.xml</value>
<description>Name of file in CLASSPATH containing filename extension and
magic sequence to mime types mapping information. Overrides the default Tika config
if specified.
</description>
</property>
-->
<property>
<name>mime.type.magic</name>
<value>true</value>
<description>Defines if the mime content type detector uses magic resolution.
</description>
</property>
<!-- plugin properties -->
<property>
<name>plugin.folders</name>
<value>plugins</value>
<description>Directories where nutch plugins are located. Each
element may be a relative or absolute path. If absolute, it is used
as is. If relative, it is searched for on the classpath.</description>
</property>
<property>
<name>plugin.auto-activation</name>
<value>true</value>
<description>Defines if some plugins that are not activated regarding
the plugin.includes and plugin.excludes properties must be automaticaly
activated if they are needed by some actived plugins.
</description>
</property>
<property>
<name>plugin.includes</name>
<value>protocol-http|urlfilter-regex|parse-(html|tika)|filter-xpath|index-(basic|anchor)|indexer-solr|scoring-opic|urlnormalizer-(pass|regex|basic)</value>
<description>Regular expression naming plugin directory names to
include. Any plugin not matching this expression is excluded.
In any case you need at least include the nutch-extensionpoints plugin. By
default Nutch includes crawling just HTML and plain text via HTTP,
and basic indexing and search plugins. In order to use HTTPS please enable
protocol-httpclient, but be aware of possible intermittent problems with the
underlying commons-httpclient library.
</description>
</property>
<property>
<name>plugin.excludes</name>
<value></value>
<description>Regular expression naming plugin directory names to exclude.
</description>
</property>
<property>
<name>urlmeta.tags</name>
<value></value>
<description>
To be used in conjunction with features introduced in NUTCH-655, which allows
for custom metatags to be injected alongside your crawl URLs. Specifying those
custom tags here will allow for their propagation into a pages outlinks, as
well as allow for them to be included as part of an index.
Values should be comma-delimited. ("tag1,tag2,tag3") Do not pad the tags with
white-space at their boundaries, if you are using anything earlier than Hadoop-0.21.
</description>
</property>
<!-- parser properties -->
<property>
<name>parse.plugin.file</name>
<value>parse-plugins.xml</value>
<description>The name of the file that defines the associations between
content-types and parsers.</description>
</property>
<property>
<name>parser.character.encoding.default</name>
<value>windows-1252</value>
<description>The character encoding to fall back to when no other information
is available</description>
</property>
<property>
<name>encodingdetector.charset.min.confidence</name>
<value>-1</value>
<description>A integer between 0-100 indicating minimum confidence value
for charset auto-detection. Any negative value disables auto-detection.
</description>
</property>
<property>
<name>parser.caching.forbidden.policy</name>
<value>content</value>
<description>If a site (or a page) requests through its robot metatags
that it should not be shown as cached content, apply this policy. Currently
three keywords are recognized: "none" ignores any "noarchive" directives.
"content" doesn't show the content, but shows summaries (snippets).
"all" doesn't show either content or summaries.</description>
</property>
<property>
<name>parser.html.impl</name>
<value>neko</value>
<description>HTML Parser implementation. Currently the following keywords
are recognized: "neko" uses NekoHTML, "tagsoup" uses TagSoup.
</description>
</property>
<property>
<name>parser.html.form.use_action</name>
<value>false</value>
<description>If true, HTML parser will collect URLs from form action
attributes. This may lead to undesirable behavior (submitting empty
forms during next fetch cycle). If false, form action attribute will
be ignored.</description>
</property>
<property>
<name>parser.html.outlinks.ignore_tags</name>
<value></value>
<description>Comma separated list of HTML tags, from which outlinks
shouldn't be extracted. Nutch takes links from: a, area, form, frame,
iframe, script, link, img. If you add any of those tags here, it
won't be taken. Default is empty list. Probably reasonable value
for most people would be "img,script,link".</description>
</property>
<property>
<name>htmlparsefilter.order</name>
<value></value>
<description>The order by which HTMLParse filters are applied.
If empty, all available HTMLParse filters (as dictated by properties
plugin-includes and plugin-excludes above) are loaded and applied in system
defined order. If not empty, only named filters are loaded and applied
in given order.
HTMLParse filter ordering MAY have an impact
on end result, as some filters could rely on the metadata generated by a previous filter.
</description>
</property>
<property>
<name>parser.timeout</name>
<value>30</value>
<description>Timeout in seconds for the parsing of a document, otherwise treats it as an exception and
moves on the the following documents. This parameter is applied to any Parser implementation.
Set to -1 to deactivate, bearing in mind that this could cause
the parsing to crash because of a very long or corrupted document.
</description>
</property>
<property>
<name>parse.filter.urls</name>
<value>false</value>
<description>Whether the parser will filter URLs (with the configured URL filters).</description>
</property>
<property>
<name>parse.normalize.urls</name>
<value>true</value>
<description>Whether the parser will normalize URLs (with the configured URL normalizers).</description>
</property>
<property>
<name>parser.skip.truncated</name>
<value>true</value>
<description>Boolean value for whether we should skip parsing for truncated documents. By default this
property is activated due to extremely high levels of CPU which parsing can sometimes take.
</description>
</property>
<!--
<property>
<name>tika.htmlmapper.classname</name>
<value>org.apache.tika.parser.html.IdentityHtmlMapper</value>
<description>Classname of Tika HTMLMapper to use. Influences the elements included in the DOM and hence
the behaviour of the HTMLParseFilters.
</description>
</property>
-->
<property>
<name>tika.uppercase.element.names</name>
<value>true</value>
<description>Determines whether TikaParser should uppercase the element name while generating the DOM
for a page, as done by Neko (used per default by parse-html)(see NUTCH-1592).
</description>
</property>
<!-- urlfilter plugin properties -->
<property>
<name>urlfilter.domain.file</name>
<value>domain-urlfilter.txt</value>
<description>Name of file on CLASSPATH containing either top level domains or
hostnames used by urlfilter-domain (DomainURLFilter) plugin.</description>
</property>
<property>
<name>urlfilter.regex.file</name>
<value>regex-urlfilter.txt</value>
<description>Name of file on CLASSPATH containing regular expressions
used by urlfilter-regex (RegexURLFilter) plugin.</description>
</property>
<property>
<name>urlfilter.automaton.file</name>
<value>automaton-urlfilter.txt</value>
<description>Name of file on CLASSPATH containing regular expressions
used by urlfilter-automaton (AutomatonURLFilter) plugin.</description>
</property>
<property>
<name>urlfilter.prefix.file</name>
<value>prefix-urlfilter.txt</value>
<description>Name of file on CLASSPATH containing url prefixes
used by urlfilter-prefix (PrefixURLFilter) plugin.</description>
</property>
<property>
<name>urlfilter.suffix.file</name>
<value>suffix-urlfilter.txt</value>
<description>Name of file on CLASSPATH containing url suffixes
used by urlfilter-suffix (SuffixURLFilter) plugin.</description>
</property>
<property>
<name>urlfilter.order</name>
<value></value>
<description>The order by which url filters are applied.
If empty, all available url filters (as dictated by properties
plugin-includes and plugin-excludes above) are loaded and applied in system
defined order. If not empty, only named filters are loaded and applied
in given order. For example, if this property has value:
org.apache.nutch.urlfilter.regex.RegexURLFilter org.apache.nutch.urlfilter.prefix.PrefixURLFilter
then RegexURLFilter is applied first, and PrefixURLFilter second.
Since all filters are AND'ed, filter ordering does not have impact
on end result, but it may have performance implication, depending
on relative expensiveness of filters.
</description>
</property>
<!-- scoring filters properties -->
<property>
<name>scoring.filter.order</name>
<value></value>
<description>The order in which scoring filters are applied. This
may be left empty (in which case all available scoring filters will
be applied in system defined order), or a space separated list of
implementation classes.
</description>
</property>
<!-- scoring-depth properties
Add 'scoring-depth' to the list of active plugins
in the parameter 'plugin.includes' in order to use it.
-->
<property>
<name>scoring.depth.max</name>
<value>1000</value>
<description>Max depth value from seed allowed by default.
Can be overriden on a per-seed basis by specifying "_maxdepth_=VALUE"
as a seed metadata. This plugin adds a "_depth_" metadatum to the pages
to track the distance from the seed it was found from.
The depth is used to prioritise URLs in the generation step so that
shallower pages are fetched first.
</description>
</property>
<!-- language-identifier plugin properties -->
<property>
<name>lang.analyze.max.length</name>
<value>2048</value>
<description> The maximum bytes of data to uses to indentify
the language (0 means full content analysis).
The larger is this value, the better is the analysis, but the
slowest it is.
</description>
</property>
<property>
<name>lang.extraction.policy</name>
<value>detect,identify</value>
<description>This determines when the plugin uses detection and
statistical identification mechanisms. The order in which the
detect and identify are written will determine the extraction
policy. Default case (detect,identify) means the plugin will
first try to extract language info from page headers and metadata,
if this is not successful it will try using tika language
identification. Possible values are:
detect
identify
detect,identify
identify,detect
</description>
</property>
<property>
<name>lang.identification.only.certain</name>
<value>false</value>
<description>If set to true with lang.extraction.policy containing identify,
the language code returned by Tika will be assigned to the document ONLY
if it is deemed certain by Tika.
</description>
</property>
<!-- index-static plugin properties -->
<property>
<name>index.static</name>
<value></value>
<description>
Used by plugin index-static to adds fields with static data at indexing time.
You can specify a comma-separated list of fieldname:fieldcontent per Nutch job.
Each fieldcontent can have multiple values separated by space, e.g.,
field1:value1.1 value1.2 value1.3,field2:value2.1 value2.2 ...
It can be useful when collections can't be created by URL patterns,
like in subcollection, but on a job-basis.
</description>
</property>
<!-- index-metadata plugin properties -->
<property>
<name>index.parse.md</name>
<value>metatag.description,metatag.keywords</value>
<description>
Comma-separated list of keys to be taken from the parse metadata to generate fields.
Can be used e.g. for 'description' or 'keywords' provided that these values are generated
by a parser (see parse-metatags plugin)
</description>
</property>
<property>
<name>index.content.md</name>
<value></value>
<description>
Comma-separated list of keys to be taken from the content metadata to generate fields.
</description>
</property>
<property>
<name>index.db.md</name>
<value></value>
<description>
Comma-separated list of keys to be taken from the crawldb metadata to generate fields.
Can be used to index values propagated from the seeds with the plugin urlmeta
</description>
</property>
<!-- index-geoip plugin properties -->
<property>
<name>index.geoip.usage</name>
<value>insightsService</value>
<description>
A string representing the information source to be used for GeoIP information
association. Either enter 'cityDatabase', 'connectionTypeDatabase',
'domainDatabase', 'ispDatabase' or 'insightsService'. If you wish to use any one of the
Database options, you should make one of GeoIP2-City.mmdb, GeoIP2-Connection-Type.mmdb,
GeoIP2-Domain.mmdb or GeoIP2-ISP.mmdb files respectively available on the classpath and
available at runtime.
</description>
</property>
<property>
<name>index.geoip.userid</name>
<value></value>
<description>
The userId associated with the GeoIP2 Precision Services account.
</description>
</property>
<property>
<name>index.geoip.licensekey</name>
<value></value>
<description>
The license key associated with the GeoIP2 Precision Services account.
</description>
</property>
<!-- parse-metatags plugin properties -->
<property>
<name>metatags.names</name>
<value>description,keywords</value>
<description> Names of the metatags to extract, separated by ','.
Use '*' to extract all metatags. Prefixes the names with 'metatag.'
in the parse-metadata. For instance to index description and keywords,
you need to activate the plugin index-metadata and set the value of the
parameter 'index.parse.md' to 'metatag.description,metatag.keywords'.
</description>
</property>
<!-- Temporary Hadoop 0.17.x workaround. -->
<property>
<name>hadoop.job.history.user.location</name>
<value>${hadoop.log.dir}/history/user</value>
<description>Hadoop 0.17.x comes with a default setting to create
user logs inside the output path of the job. This breaks some
Hadoop classes, which expect the output to contain only
part-XXXXX files. This setting changes the output to a
subdirectory of the regular log directory.
</description>
</property>
<!-- linkrank scoring properties -->
<property>
<name>link.ignore.internal.host</name>
<value>false</value>
<description>Ignore outlinks to the same hostname.</description>
</property>
<property>
<name>link.ignore.internal.domain</name>
<value>false</value>
<description>Ignore outlinks to the same domain.</description>
</property>
<property>
<name>link.ignore.limit.page</name>
<value>true</value>
<description>Limit to only a single outlink to the same page.</description>
</property>
<property>
<name>link.ignore.limit.domain</name>
<value>true</value>
<description>Limit to only a single outlink to the same domain.</description>
</property>
<property>
<name>link.analyze.num.iterations</name>
<value>10</value>
<description>The number of LinkRank iterations to run.</description>
</property>
<property>
<name>link.analyze.initial.score</name>
<value>1.0f</value>
<description>The initial score.</description>
</property>
<property>
<name>link.analyze.damping.factor</name>
<value>0.85f</value>
<description>The damping factor.</description>
</property>
<property>
<name>link.delete.gone</name>
<value>false</value>
<description>Whether to delete gone pages from the web graph.</description>
</property>
<property>
<name>link.loops.depth</name>
<value>2</value>
<description>The depth for the loops algorithm.</description>
</property>
<property>
<name>link.score.updater.clear.score</name>
<value>0.0f</value>
<description>The default score for URL's that are not in the web graph.</description>
</property>
<property>
<name>mapreduce.fileoutputcommitter.marksuccessfuljobs</name>
<value>false</value>
<description>Hadoop >= 0.21 generates SUCCESS files in the output which can crash
the readers. This should not be an issue once Nutch is ported to the new MapReduce API
but for now this parameter should prevent such cases.
</description>
</property>
<!-- solr index properties -->
<property>
<name>solr.server.url</name>
<value>http://127.0.0.1:8983/solr/</value>
<description>
Defines the Solr URL into which data should be indexed using the
indexer-solr plugin.
</description>
</property>
<property>
<name>solr.mapping.file</name>
<value>solrindex-mapping.xml</value>
<description>
Defines the name of the file that will be used in the mapping of internal
nutch field names to solr index fields as specified in the target Solr schema.
</description>
</property>
<property>
<name>solr.commit.size</name>
<value>250</value>
<description>
Defines the number of documents to send to Solr in a single update batch.
Decrease when handling very large documents to prevent Nutch from running
out of memory. NOTE: It does not explicitly trigger a server side commit.
</description>
</property>
<property>
<name>solr.commit.index</name>
<value>true</value>
<description>
When closing the indexer, trigger a commit to the Solr server.
</description>
</property>
<property>
<name>solr.auth</name>
<value>false</value>
<description>
Whether to enable HTTP basic authentication for communicating with Solr.
Use the solr.auth.username and solr.auth.password properties to configure
your credentials.
</description>
</property>
<!-- Elasticsearch properties -->
<property>
<name>elastic.host</name>
<value></value>
<description>The hostname to send documents to using TransportClient. Either host
and port must be defined or cluster.</description>
</property>
<property>
<name>elastic.port</name>
<value>9300</value>The port to connect to using TransportClient.<description>
</description>
</property>
<property>
<name>elastic.cluster</name>
<value></value>
<description>The cluster name to discover. Either host and potr must be defined
or cluster.</description>
</property>
<property>
<name>elastic.index</name>
<value>nutch</value>
<description>Default index to send documents to.</description>
</property>
<property>
<name>elastic.max.bulk.docs</name>
<value>250</value>
<description>Maximum size of the bulk in number of documents.</description>
</property>
<property>
<name>elastic.max.bulk.size</name>
<value>2500500</value>
<description>Maximum size of the bulk in bytes.</description>
</property>
<!-- subcollection properties -->
<property>
<name>subcollection.default.fieldname</name>
<value>subcollection</value>
<description>
The default field name for the subcollections.
</description>
</property>
<!-- Headings plugin properties -->
<property>
<name>headings</name>
<value>h1,h2</value>
<description>Comma separated list of headings to retrieve from the document</description>
</property>
<property>
<name>headings.multivalued</name>
<value>false</value>
<description>Whether to support multivalued headings.</description>
</property>
<!-- mimetype-filter plugin properties -->
<property>
<name>mimetype.filter.file</name>
<value>mimetype-filter.txt</value>
<description>
The configuration file for the mimetype-filter plugin. This file contains
the rules used to allow or deny the indexing of certain documents.
</description>
</property>
</configuration>
