⭐ 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

📄 crawlorder.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 4 页
字号:
<a name="373" href="#373">373</a>             res = (Integer) getAttribute(<strong>null</strong>, ATTR_MAX_TOE_THREADS);<a name="374" href="#374">374</a>         } <strong>catch</strong> (AttributeNotFoundException e) {<a name="375" href="#375">375</a>             logger.severe(e.getMessage());<a name="376" href="#376">376</a>         }<a name="377" href="#377">377</a>         <strong>return</strong> res.intValue();<a name="378" href="#378">378</a>     }<a name="379" href="#379">379</a> <a name="380" href="#380">380</a>     <em>/**<em>*</em></em><a name="381" href="#381">381</a> <em>     * This method gets the RobotsHonoringPolicy object from the orders file.</em><a name="382" href="#382">382</a> <em>     *</em><a name="383" href="#383">383</a> <em>     * @return the new RobotsHonoringPolicy</em><a name="384" href="#384">384</a> <em>     */</em><a name="385" href="#385">385</a>     <strong>public</strong> <a href="../../../../org/archive/crawler/datamodel/RobotsHonoringPolicy.html">RobotsHonoringPolicy</a> getRobotsHonoringPolicy() {<a name="386" href="#386">386</a>         <strong>try</strong> {<a name="387" href="#387">387</a>             <strong>return</strong> (RobotsHonoringPolicy) getAttribute(<strong>null</strong>, RobotsHonoringPolicy.ATTR_NAME);<a name="388" href="#388">388</a>         } <strong>catch</strong> (AttributeNotFoundException e) {<a name="389" href="#389">389</a>             logger.severe(e.getMessage());<a name="390" href="#390">390</a>             <strong>return</strong> <strong>null</strong>;<a name="391" href="#391">391</a>         } <a name="392" href="#392">392</a>     }<a name="393" href="#393">393</a> <a name="394" href="#394">394</a>     <em>/**<em>* Get the name of the order file.</em></em><a name="395" href="#395">395</a> <em>     *</em><a name="396" href="#396">396</a> <em>     * @return the name of the order file.</em><a name="397" href="#397">397</a> <em>     */</em><a name="398" href="#398">398</a>     <strong>public</strong> String getCrawlOrderName() {<a name="399" href="#399">399</a>         <strong>return</strong> getSettingsHandler().getSettingsObject(<strong>null</strong>).getName();<a name="400" href="#400">400</a>     }<a name="401" href="#401">401</a> <a name="402" href="#402">402</a>     <em>/**<em>*</em></em><a name="403" href="#403">403</a> <em>     * @return The crawl controller.</em><a name="404" href="#404">404</a> <em>     */</em><a name="405" href="#405">405</a>     <strong>public</strong> <a href="../../../../org/archive/crawler/framework/CrawlController.html">CrawlController</a> getController() {<a name="406" href="#406">406</a>         <strong>return</strong> controller;<a name="407" href="#407">407</a>     }<a name="408" href="#408">408</a> <a name="409" href="#409">409</a>     <em>/**<em>*</em></em><a name="410" href="#410">410</a> <em>     * @param controller</em><a name="411" href="#411">411</a> <em>     */</em><a name="412" href="#412">412</a>     <strong>public</strong> <strong>void</strong> setController(<a href="../../../../org/archive/crawler/framework/CrawlController.html">CrawlController</a> controller) {<a name="413" href="#413">413</a>         <strong>this</strong>.controller = controller;<a name="414" href="#414">414</a>     }<a name="415" href="#415">415</a> <a name="416" href="#416">416</a>     <em>/**<em>*</em></em><a name="417" href="#417">417</a> <em>     * Returns the Map of the StatisticsTracking modules that are included in the</em><a name="418" href="#418">418</a> <em>     * configuration that the current instance of this class is representing.</em><a name="419" href="#419">419</a> <em>     * @return Map of the StatisticsTracking modules</em><a name="420" href="#420">420</a> <em>     */</em><a name="421" href="#421">421</a>     <strong>public</strong> <a href="../../../../org/archive/crawler/settings/MapType.html">MapType</a> getLoggers() {<a name="422" href="#422">422</a>         <strong>return</strong> loggers;<a name="423" href="#423">423</a>     }<a name="424" href="#424">424</a> <a name="425" href="#425">425</a>     <em>/**<em>*</em></em><a name="426" href="#426">426</a> <em>     * Checks if the User Agent and From field are set 'correctly' in</em><a name="427" href="#427">427</a> <em>     * the specified Crawl Order.</em><a name="428" href="#428">428</a> <em>     *</em><a name="429" href="#429">429</a> <em>     * @throws FatalConfigurationException</em><a name="430" href="#430">430</a> <em>     */</em><a name="431" href="#431">431</a>     <strong>public</strong> <strong>void</strong> checkUserAgentAndFrom() throws FatalConfigurationException {<a name="432" href="#432">432</a>         <em class="comment">// don't start the crawl if they're using the default user-agent</em><a name="433" href="#433">433</a>         String userAgent = <strong>this</strong>.getUserAgent(<strong>null</strong>);<a name="434" href="#434">434</a>         String from = <strong>this</strong>.getFrom(<strong>null</strong>);<a name="435" href="#435">435</a>         <strong>if</strong> (!(userAgent.matches(ACCEPTABLE_USER_AGENT)<a name="436" href="#436">436</a>             &amp;&amp; from.matches(ACCEPTABLE_FROM))) {<a name="437" href="#437">437</a>             <strong>throw</strong> <strong>new</strong> <a href="../../../../org/archive/crawler/framework/exceptions/FatalConfigurationException.html">FatalConfigurationException</a>(<span class="string">"unacceptable user-agent "</span> +<a name="438" href="#438">438</a>                     <span class="string">" or from (Reedit your order file)."</span>);<a name="439" href="#439">439</a>         }<a name="440" href="#440">440</a>     }<a name="441" href="#441">441</a> <a name="442" href="#442">442</a>     <em>/**<em>*</em></em><a name="443" href="#443">443</a> <em>     * @return Checkpoint directory.</em><a name="444" href="#444">444</a> <em>     */</em><a name="445" href="#445">445</a>     <strong>public</strong> File getCheckpointsDirectory() {<a name="446" href="#446">446</a>         <strong>try</strong> {<a name="447" href="#447">447</a>             <strong>return</strong> getDirectoryRelativeToDiskPath((String) getAttribute(<strong>null</strong>,<a name="448" href="#448">448</a>                     CrawlOrder.ATTR_CHECKPOINTS_PATH));<a name="449" href="#449">449</a>         } <strong>catch</strong> (AttributeNotFoundException e) {<a name="450" href="#450">450</a>             <em class="comment">// TODO Auto-generated catch block</em><a name="451" href="#451">451</a>             e.printStackTrace();<a name="452" href="#452">452</a>             <strong>return</strong> <strong>null</strong>;<a name="453" href="#453">453</a>         }<a name="454" href="#454">454</a>     }<a name="455" href="#455">455</a> <a name="456" href="#456">456</a>     <strong>private</strong> File getDirectoryRelativeToDiskPath(String subpath) {<a name="457" href="#457">457</a>         File disk;<a name="458" href="#458">458</a>         <strong>try</strong> {<a name="459" href="#459">459</a>             disk = getSettingsHandler().getPathRelativeToWorkingDirectory(<a name="460" href="#460">460</a>                     (String) getAttribute(<strong>null</strong>, CrawlOrder.ATTR_DISK_PATH));<a name="461" href="#461">461</a>             <strong>return</strong> <strong>new</strong> File(disk, subpath);<a name="462" href="#462">462</a>         } <strong>catch</strong> (AttributeNotFoundException e) {<a name="463" href="#463">463</a>             <em class="comment">// TODO Auto-generated catch block</em><a name="464" href="#464">464</a>             e.printStackTrace();<a name="465" href="#465">465</a>             <strong>return</strong> <strong>null</strong>;<a name="466" href="#466">466</a>         }<a name="467" href="#467">467</a>     }<a name="468" href="#468">468</a>     <a name="469" href="#469">469</a>     <em>/**<em>*</em></em><a name="470" href="#470">470</a> <em>     * Return fullpath to the directory named by &lt;code>key&lt;/code></em><a name="471" href="#471">471</a> <em>     * in settings.</em><a name="472" href="#472">472</a> <em>     * If directory does not exist, it and all intermediary dirs</em><a name="473" href="#473">473</a> <em>     * will be created.</em><a name="474" href="#474">474</a> <em>     * @param key Key to use going to settings.</em><a name="475" href="#475">475</a> <em>     * @return Full path to directory named by &lt;code>key&lt;/code>.</em><a name="476" href="#476">476</a> <em>     * @throws AttributeNotFoundException</em><a name="477" href="#477">477</a> <em>     */</em><a name="478" href="#478">478</a>     <strong>public</strong> File getSettingsDir(String key)<a name="479" href="#479">479</a>     throws AttributeNotFoundException {<a name="480" href="#480">480</a>         String path = (String)getAttribute(<strong>null</strong>, key);<a name="481" href="#481">481</a>         File f = <strong>new</strong> File(path);<a name="482" href="#482">482</a>         <strong>if</strong> (!f.isAbsolute()) {<a name="483" href="#483">483</a>             f = getDirectoryRelativeToDiskPath(path);<a name="484" href="#484">484</a>         }<a name="485" href="#485">485</a>         <strong>if</strong> (!f.exists()) {<a name="486" href="#486">486</a>             f.mkdirs();<a name="487" href="#487">487</a>         }<a name="488" href="#488">488</a>         <strong>return</strong> f;<a name="489" href="#489">489</a>     }<a name="490" href="#490">490</a>     <a name="491" href="#491">491</a>     <a name="492" href="#492">492</a> }</pre><hr/><div id="footer">This page was automatically generated by <a href="http://maven.apache.org/">Maven</a></div></body></html>

⌨️ 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 + -