Nutch中的所有配置文件都放置在总目录下的conf子文件夹中,最基本的配置文件是conf/nutch-default.xml。这个文件中定义了 Nutch的所有必要设置以及一些默认值,它是不可以被修改的。如果你想进行个性化设置,你需要在conf/nutch-site.xml进行设置,它会 对默认设置进行屏蔽。
Nutch考虑了其可扩展性,你可以自定义插件plugins来定制自己的服务,一些plugins存放于plugins子文件夹。Nutch的网页解析 与索引功能是通过插件形式进行实现的,例如,对HTML文件的解析与索引是通过HTML document parsing plugin, parse-html实现的。所以你完全可以自定义各种解析插件然后对配置文件进行修改,然后你就可以抓取并索引各种类型的文件了。
部分配置介绍
配置1:
<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>
这个配置用来限制下载网页的大小,默认是65536字节,如果Fetch阶段结束后发现页面内容没有下载全,就是因为这个地方的限制。把这个值改大(超过页面字节数)就可以下载全部的网页。
配置2:
<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>
这两个属性是用来设置代理地址和端口.
配置3:
<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>
这个配置用来设定mapper操作以后,partition操作根据Host进行Hash。结果是具有相同Host的URL会被打到同一个Reduce节点上面.
配置4:
<!-- plugin properties ./src/plugin plugins--> <property> <name>plugin.folders</name> <value>plugins</value> <description>eclipse env:./src/plugin deploy:plugins</description> </property>
这个属性是用来指定plugin的目录,在eclipse中执行时需要改为:
./src/plugin
但是在分布式集群运行打成的JOB包时,需要改为plugins
以下是全文介绍
<?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> <!-- file properties --> <property> <name>file.content.limit</name> <value>-1</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.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>jdodrc</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>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> <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-1.4</value> <description>A version string to advertise in the User-Agent header.</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>-1</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>en-us,en-gb,en;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> <!-- FTP properties --> <property> <name>ftp.username</name> <value>anonymous</value> <description>ftp login username.</description> </property> <property> <name>ftp.password</name> <value>anonymous@example.com</value> <description>ftp login password.</description> </property> <property> <name>ftp.content.limit</name> <value>-1</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.default.fetch.interval</name> <value>30</value> <description>(DEPRECATED) The default number of days between re-fetches of a page. </description> </property> <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.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.update.purge.404</name> <value>false</value> <description>If true, updatedb will add purge records with status DB_GONE from the CrawlDB. </description> </property> <property> <name>db.update.max.inlinks</name> <value>10000</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>true</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.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>1.0</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>10000</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>100</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.max.per.host</name> <value>-1</value> <description>(Deprecated). Use generate.max.count and generate.count.mode instead. The maximum number of urls per host in a single fetchlist. -1 if unlimited.</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 days, 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. the become eligible for selecting. Default value of this is 7 days. </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.</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.host is greater than 1 (i.e. the host blocking is turned off).</description> </property> <property> <name>fetcher.max.crawl.delay</name> <value>10</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. Replaces deprecated parameter 'fetcher.threads.per.host'. </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'. Replaces the deprecated parameter 'fetcher.threads.per.host.by.ip'. </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>false</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.threads.timeout.divisor</name> <value>2</value> <description>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. </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.queue.depth.multiplier</name> <value>100</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> <!-- 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> <!-- 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>200</value> <description>The maximum number of characters of a title that are indexed. </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> <!-- 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>ys-parse-news|ys-parse-pdf|ys-index-filter|protocol-http|urlfilter-regex|parse-(html|tika)|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>utf-8</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>parser.fix.embeddedparams</name> <value>true</value> <description>Whether to fix URL embedded params using semi-colons. See NUTCH-436 and NUTCH-1115</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> <!-- 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 the order defined in plugin-includes and plugin-excludes), or a space separated list of implementation classes. </description> </property> <!-- language-identifier plugin properties --> <property> <name>lang.analyze.max.length</name> <value>0</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> A simple plugin called at indexing that adds fields with static data. You can specify a list of fieldname:fieldcontent per nutch job. It can be useful when collections can't be created by urlpatterns, like in subcollection, but on a job-basis. </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> <!-- solr index properties --> <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>1000</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. </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> </configuration>