⭐ 欢迎来到虫虫下载站! | 📦 资源下载 📁 资源专辑 ℹ️ 关于我们
⭐ 虫虫下载站

📄 heritrix.html

📁 用JAVA编写的,在做实验的时候留下来的,本来想删的,但是传上来,大家分享吧
💻 HTML
📖 第 1 页 / 共 5 页
字号:
<a name="141" href="#141">141</a> <em> * &lt;li>A container such as tomcat or jboss.&lt;/li></em><a name="142" href="#142">142</a> <em> * &lt;/ol></em><a name="143" href="#143">143</a> <em> *</em><a name="144" href="#144">144</a> <em> * @author gojomo</em><a name="145" href="#145">145</a> <em> * @author Kristinn Sigurdsson</em><a name="146" href="#146">146</a> <em> * @author Stack</em><a name="147" href="#147">147</a> <em> */</em><a name="148" href="#148">148</a> <strong>public</strong> <strong>class</strong> <a href="../../../org/archive/crawler/Heritrix.html">Heritrix</a> implements DynamicMBean, MBeanRegistration {<a name="149" href="#149">149</a>     <em>/**<em>*</em></em><a name="150" href="#150">150</a> <em>     * Heritrix logging instance.</em><a name="151" href="#151">151</a> <em>     */</em><a name="152" href="#152">152</a>     <strong>private</strong> <strong>static</strong> <strong>final</strong> Logger logger =<a name="153" href="#153">153</a>         Logger.getLogger(Heritrix.<strong>class</strong>.getName());<a name="154" href="#154">154</a>     <a name="155" href="#155">155</a>     <strong>private</strong> <strong>static</strong> <strong>final</strong> File TMPDIR =<a name="156" href="#156">156</a>         <strong>new</strong> File(System.getProperty(<span class="string">"java.io.tmpdir"</span>, <span class="string">"/tmp"</span>));<a name="157" href="#157">157</a> <a name="158" href="#158">158</a>     <em>/**<em>*</em></em><a name="159" href="#159">159</a> <em>     * Name of the heritrix properties file.</em><a name="160" href="#160">160</a> <em>     */</em><a name="161" href="#161">161</a>     <strong>private</strong> <strong>static</strong> <strong>final</strong> String PROPERTIES = <span class="string">"heritrix.properties"</span>;<a name="162" href="#162">162</a> <a name="163" href="#163">163</a>     <em>/**<em>*</em></em><a name="164" href="#164">164</a> <em>     * Name of the key to use specifying alternate heritrix properties on</em><a name="165" href="#165">165</a> <em>     * command line.</em><a name="166" href="#166">166</a> <em>     */</em><a name="167" href="#167">167</a>     <strong>private</strong> <strong>static</strong> <strong>final</strong> String PROPERTIES_KEY = PROPERTIES;<a name="168" href="#168">168</a>     <a name="169" href="#169">169</a>     <em>/**<em>*</em></em><a name="170" href="#170">170</a> <em>     * Prefix used on properties we'll add to the System.properties list.</em><a name="171" href="#171">171</a> <em>     */</em><a name="172" href="#172">172</a>     <strong>private</strong> <strong>static</strong> <strong>final</strong> String HERITRIX_PROPERTIES_PREFIX = <span class="string">"heritrix."</span>;<a name="173" href="#173">173</a> <a name="174" href="#174">174</a>     <em>/**<em>*</em></em><a name="175" href="#175">175</a> <em>     * Instance of web server if one was started.</em><a name="176" href="#176">176</a> <em>     */</em><a name="177" href="#177">177</a>     <strong>private</strong> <strong>static</strong> <a href="../../../org/archive/crawler/SimpleHttpServer.html">SimpleHttpServer</a> httpServer = <strong>null</strong>;<a name="178" href="#178">178</a> <a name="179" href="#179">179</a>     <em>/**<em>*</em></em><a name="180" href="#180">180</a> <em>     * CrawlJob handler. Manages multiple crawl jobs at runtime.</em><a name="181" href="#181">181</a> <em>     */</em><a name="182" href="#182">182</a>     <strong>private</strong> <a href="../../../org/archive/crawler/admin/CrawlJobHandler.html">CrawlJobHandler</a> jobHandler = <strong>null</strong>;<a name="183" href="#183">183</a> <a name="184" href="#184">184</a>     <em>/**<em>*</em></em><a name="185" href="#185">185</a> <em>     * Heritrix start log file.</em><a name="186" href="#186">186</a> <em>     *</em><a name="187" href="#187">187</a> <em>     * This file contains standard out produced by this main class for startup</em><a name="188" href="#188">188</a> <em>     * only.  Used by heritrix shell script.  Name here MUST match that in the</em><a name="189" href="#189">189</a> <em>     * &lt;code>bin/heritrix&lt;/code> shell script.  This is a DEPENDENCY the shell</em><a name="190" href="#190">190</a> <em>     * wrapper has on this here java heritrix.</em><a name="191" href="#191">191</a> <em>     */</em><a name="192" href="#192">192</a>     <strong>private</strong> <strong>static</strong> <strong>final</strong> String STARTLOG = <span class="string">"heritrix_dmesg.log"</span>;<a name="193" href="#193">193</a> <a name="194" href="#194">194</a>     <em>/**<em>*</em></em><a name="195" href="#195">195</a> <em>     * Default encoding.</em><a name="196" href="#196">196</a> <em>     * </em><a name="197" href="#197">197</a> <em>     * Used for content when fetching if none specified.</em><a name="198" href="#198">198</a> <em>     */</em><a name="199" href="#199">199</a> 	<strong>public</strong> <strong>static</strong> <strong>final</strong> String DEFAULT_ENCODING = <span class="string">"ISO-8859-1"</span>;<a name="200" href="#200">200</a> <a name="201" href="#201">201</a>     <em>/**<em>*</em></em><a name="202" href="#202">202</a> <em>     * Heritrix stderr/stdout log file.</em><a name="203" href="#203">203</a> <em>     *</em><a name="204" href="#204">204</a> <em>     * This file should have nothing in it except messages over which we have</em><a name="205" href="#205">205</a> <em>     * no control (JVM stacktrace, 3rd-party lib emissions).  The wrapper</em><a name="206" href="#206">206</a> <em>     * startup script directs stderr/stdout here. This is an INTERDEPENDENCY</em><a name="207" href="#207">207</a> <em>     * this program has with the wrapper shell script.  Shell can actually</em><a name="208" href="#208">208</a> <em>     * pass us an alternate to use for this file.</em><a name="209" href="#209">209</a> <em>     */</em><a name="210" href="#210">210</a>     <strong>private</strong> <strong>static</strong> String DEFAULT_HERITRIX_OUT = <span class="string">"heritrix_out.log"</span>;<a name="211" href="#211">211</a> <a name="212" href="#212">212</a>     <em>/**<em>*</em></em><a name="213" href="#213">213</a> <em>     * Where to write this classes startup output.</em><a name="214" href="#214">214</a> <em>     * </em><a name="215" href="#215">215</a> <em>     * This out should only be used if Heritrix is being run from the</em><a name="216" href="#216">216</a> <em>     * command-line.</em><a name="217" href="#217">217</a> <em>     */</em><a name="218" href="#218">218</a>     <strong>private</strong> <strong>static</strong> PrintWriter out = <strong>null</strong>;<a name="219" href="#219">219</a> <a name="220" href="#220">220</a>     <em>/**<em>*</em></em><a name="221" href="#221">221</a> <em>     * The org.archive package</em><a name="222" href="#222">222</a> <em>     */</em><a name="223" href="#223">223</a>     <strong>private</strong> <strong>static</strong> <strong>final</strong> String ARCHIVE_PACKAGE = <span class="string">"org.archive."</span>;<a name="224" href="#224">224</a> <a name="225" href="#225">225</a>     <em>/**<em>*</em></em><a name="226" href="#226">226</a> <em>     * The crawler package.</em><a name="227" href="#227">227</a> <em>     */</em><a name="228" href="#228">228</a> 	<strong>private</strong> <strong>static</strong> <strong>final</strong> String CRAWLER_PACKAGE = Heritrix.<strong>class</strong>.getName().<a name="229" href="#229">229</a>         substring(0, Heritrix.<strong>class</strong>.getName().lastIndexOf('.'));<a name="230" href="#230">230</a>     <a name="231" href="#231">231</a>     <em>/**<em>*</em></em><a name="232" href="#232">232</a> <em>     * The root context for a webapp.</em><a name="233" href="#233">233</a> <em>     */</em><a name="234" href="#234">234</a>     <strong>private</strong> <strong>static</strong> <strong>final</strong> String ROOT_CONTEXT = <span class="string">"/"</span>;<a name="235" href="#235">235</a> <a name="236" href="#236">236</a>     <em>/**<em>*</em></em><a name="237" href="#237">237</a> <em>     * Set to true if application is started from command line.</em><a name="238" href="#238">238</a> <em>     */</em><a name="239" href="#239">239</a>     <strong>private</strong> <strong>static</strong> <strong>boolean</strong> commandLine = false;<a name="240" href="#240">240</a>     <a name="241" href="#241">241</a>     <em>/**<em>*</em></em><a name="242" href="#242">242</a> <em>     * True if container initialization has been run.</em><a name="243" href="#243">243</a> <em>     */</em><a name="244" href="#244">244</a>     <strong>private</strong> <strong>static</strong> <strong>boolean</strong> containerInitialized = false;<a name="245" href="#245">245</a>     <a name="246" href="#246">246</a>     <strong>private</strong> <strong>static</strong> <strong>final</strong> String JAR_SUFFIX = <span class="string">".jar"</span>;<a name="247" href="#247">247</a>     <a name="248" href="#248">248</a>     <strong>private</strong> <a href="../../../org/archive/crawler/framework/AlertManager.html">AlertManager</a> alertManager;<a name="249" href="#249">249</a> <a name="250" href="#250">250</a>     <em>/**<em>*</em></em><a name="251" href="#251">251</a> <em>     * The context of the GUI webapp.  Default is root.</em><a name="252" href="#252">252</a> <em>     */</em><a name="253" href="#253">253</a>     <strong>private</strong> <strong>static</strong> String adminContext = ROOT_CONTEXT;<a name="254" href="#254">254</a>     <a name="255" href="#255">255</a>     <em>/**<em>*</em></em><a name="256" href="#256">256</a> <em>     * True if we're to put up a GUI.</em><a name="257" href="#257">257</a> <em>     * Cmdline processing can override.</em><a name="258" href="#258">258</a> <em>     */</em><a name="259" href="#259">259</a>     <strong>private</strong> <strong>static</strong> <strong>boolean</strong> gui =<a name="260" href="#260">260</a>         !PropertyUtils.getBooleanProperty(<span class="string">"heritrix.cmdline.nowui"</span>);<a name="261" href="#261">261</a>     <a name="262" href="#262">262</a>     <em>/**<em>*</em></em><a name="263" href="#263">263</a> <em>     * Port to put the GUI up on.</em><a name="264" href="#264">264</a> <em>     * Cmdline processing can override.</em><a name="265" href="#265">265</a> <em>     */</em><a name="266" href="#266">266</a>     <strong>private</strong> <strong>static</strong> <strong>int</strong> guiPort = SimpleHttpServer.DEFAULT_PORT;<a name="267" href="#267">267</a> <a name="268" href="#268">268</a>     <a name="269" href="#269">269</a>     <em>/**<em>*</em></em><a name="270" href="#270">270</a> <em>     * A collection containing only localhost.  Used as default value</em><a name="271" href="#271">271</a> <em>     * for guiHosts, and passed to SimpleHttpServer when doing selftest.</em><a name="272" href="#272">272</a> <em>     */</em><a name="273" href="#273">273</a>     <strong>final</strong> <strong>private</strong> <strong>static</strong> Collection&lt;String> LOCALHOST_ONLY =<a name="274" href="#274">274</a>      Collections.unmodifiableList(Arrays.asList(<strong>new</strong> String[] { <span class="string">"127.0.0.1"</span> }));<a name="275" href="#275">275</a> <a name="276" href="#276">276</a>     <a name="277" href="#277">277</a>     <em>/**<em>*</em></em><a name="278" href="#278">278</a> <em>     * Hosts to bind the GUI webserver to.</em><a name="279" href="#279">279</a> <em>     * By default, only contans localhost.</em><a name="280" href="#280">280</a> <em>     * Set to an empty collection to indicate that all available network</em><a name="281" href="#281">281</a> <em>     * interfaces should be used for the webserver.</em><a name="282" href="#282">282</a> <em>     */</em><a name="283" href="#283">283</a>     <strong>private</strong> <strong>static</strong> Collection&lt;String> guiHosts = LOCALHOST_ONLY;<a name="284" href="#284">284</a>     <a name="285" href="#285">285</a>     <a name="286" href="#286">286</a>     <em>/**<em>*</em></em><a name="287" href="#287">287</a> <em>     * Web UI server, realm, context name.</em><a name="288" href="#288">288</a> <em>     */</em><a name="289" href="#289">289</a>     <strong>private</strong> <strong>static</strong> String ADMIN = <span class="string">"admin"</span>;

⌨️ 快捷键说明

复制代码 Ctrl + C
搜索代码 Ctrl + F
全屏模式 F11
切换主题 Ctrl + Shift + D
显示快捷键 ?
增大字号 Ctrl + =
减小字号 Ctrl + -