⭐ 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

📄 crawluri.html

📁 一个开源的网页爬虫一个开源的网页爬虫一个开源的网页爬虫一个开源的网页爬虫一个开源的网页爬虫一个开源的网页爬虫
💻 HTML
📖 第 1 页 / 共 5 页
字号:
<a name="445" href="#445">445</a> <em>     * @return the prerequisite for this URI or null if no prerequisite.</em><a name="446" href="#446">446</a> <em>     */</em><a name="447" href="#447">447</a>     <strong>public</strong> Object getPrerequisiteUri() {<a name="448" href="#448">448</a>         <strong>return</strong> getObject(A_PREREQUISITE_URI);<a name="449" href="#449">449</a>     }<a name="450" href="#450">450</a>     <a name="451" href="#451">451</a>     <em>/**<em>*</em></em><a name="452" href="#452">452</a> <em>     * @return True if this CrawlURI has a prerequisite.</em><a name="453" href="#453">453</a> <em>     */</em><a name="454" href="#454">454</a>     <strong>public</strong> <strong>boolean</strong> hasPrerequisiteUri() {<a name="455" href="#455">455</a>         <strong>return</strong> containsKey(A_PREREQUISITE_URI);<a name="456" href="#456">456</a>     }<a name="457" href="#457">457</a> <a name="458" href="#458">458</a>     <em>/**<em>*</em></em><a name="459" href="#459">459</a> <em>     * Returns true if this CrawlURI is a prerequisite.</em><a name="460" href="#460">460</a> <em>     *</em><a name="461" href="#461">461</a> <em>     * @return true if this CrawlURI is a prerequisite.</em><a name="462" href="#462">462</a> <em>     */</em><a name="463" href="#463">463</a>     <strong>public</strong> <strong>boolean</strong> isPrerequisite() {<a name="464" href="#464">464</a>         <strong>return</strong> <strong>this</strong>.prerequisite;<a name="465" href="#465">465</a>     }<a name="466" href="#466">466</a> <a name="467" href="#467">467</a>     <em>/**<em>*</em></em><a name="468" href="#468">468</a> <em>     * Set if this CrawlURI is itself a prerequisite URI.</em><a name="469" href="#469">469</a> <em>     *</em><a name="470" href="#470">470</a> <em>     * @param prerequisite True if this CrawlURI is itself a prerequiste uri.</em><a name="471" href="#471">471</a> <em>     */</em><a name="472" href="#472">472</a>     <strong>public</strong> <strong>void</strong> setPrerequisite(<strong>boolean</strong> prerequisite) {<a name="473" href="#473">473</a>         <strong>this</strong>.prerequisite = prerequisite;<a name="474" href="#474">474</a>     }<a name="475" href="#475">475</a> <a name="476" href="#476">476</a>     <em>/**<em>*</em></em><a name="477" href="#477">477</a> <em>     * @return This crawl URI as a string wrapped with 'CrawlURI(' +</em><a name="478" href="#478">478</a> <em>     * ')'.</em><a name="479" href="#479">479</a> <em>     */</em><a name="480" href="#480">480</a>     <strong>public</strong> String getCrawlURIString() {<a name="481" href="#481">481</a>         <strong>if</strong> (<strong>this</strong>.cachedCrawlURIString == <strong>null</strong>) {<a name="482" href="#482">482</a>             <strong>synchronized</strong> (<strong>this</strong>) {<a name="483" href="#483">483</a>                 <strong>if</strong> (<strong>this</strong>.cachedCrawlURIString == <strong>null</strong>) {<a name="484" href="#484">484</a>                     <strong>this</strong>.cachedCrawlURIString =<a name="485" href="#485">485</a>                         <span class="string">"CrawlURI("</span> + toString() + <span class="string">")"</span>;<a name="486" href="#486">486</a>                 }<a name="487" href="#487">487</a>             }<a name="488" href="#488">488</a>         }<a name="489" href="#489">489</a>         <strong>return</strong> <strong>this</strong>.cachedCrawlURIString;<a name="490" href="#490">490</a>     }<a name="491" href="#491">491</a> <a name="492" href="#492">492</a>     <em>/**<em>*</em></em><a name="493" href="#493">493</a> <em>     * Get the content type of this URI.</em><a name="494" href="#494">494</a> <em>     *</em><a name="495" href="#495">495</a> <em>     * @return Fetched URIs content type.  May be null.</em><a name="496" href="#496">496</a> <em>     */</em><a name="497" href="#497">497</a>     <strong>public</strong> String getContentType() {<a name="498" href="#498">498</a>         <strong>return</strong> <strong>this</strong>.contentType;<a name="499" href="#499">499</a>     }<a name="500" href="#500">500</a> <a name="501" href="#501">501</a>     <em>/**<em>*</em></em><a name="502" href="#502">502</a> <em>     * Set a fetched uri's content type.</em><a name="503" href="#503">503</a> <em>     *</em><a name="504" href="#504">504</a> <em>     * @param ct Contenttype.  May be null.</em><a name="505" href="#505">505</a> <em>     */</em><a name="506" href="#506">506</a>     <strong>public</strong> <strong>void</strong> setContentType(String ct) {<a name="507" href="#507">507</a>         <strong>this</strong>.contentType = ct;<a name="508" href="#508">508</a>     }<a name="509" href="#509">509</a> <a name="510" href="#510">510</a>     <em>/**<em>*</em></em><a name="511" href="#511">511</a> <em>     * Set the number of the ToeThread responsible for processing this uri.</em><a name="512" href="#512">512</a> <em>     *</em><a name="513" href="#513">513</a> <em>     * @param i the ToeThread number.</em><a name="514" href="#514">514</a> <em>     */</em><a name="515" href="#515">515</a>     <strong>public</strong> <strong>void</strong> setThreadNumber(<strong>int</strong> i) {<a name="516" href="#516">516</a>         threadNumber = i;<a name="517" href="#517">517</a>     }<a name="518" href="#518">518</a> <a name="519" href="#519">519</a>     <em>/**<em>*</em></em><a name="520" href="#520">520</a> <em>     * Get the number of the ToeThread responsible for processing this uri.</em><a name="521" href="#521">521</a> <em>     *</em><a name="522" href="#522">522</a> <em>     * @return the ToeThread number.</em><a name="523" href="#523">523</a> <em>     */</em><a name="524" href="#524">524</a>     <strong>public</strong> <strong>int</strong> getThreadNumber() {<a name="525" href="#525">525</a>         <strong>return</strong> threadNumber;<a name="526" href="#526">526</a>     }<a name="527" href="#527">527</a> <a name="528" href="#528">528</a>     <em>/**<em>*</em></em><a name="529" href="#529">529</a> <em>     * Increment the deferral count.</em><a name="530" href="#530">530</a> <em>     *</em><a name="531" href="#531">531</a> <em>     */</em><a name="532" href="#532">532</a>     <strong>public</strong> <strong>void</strong> incrementDeferrals() {<a name="533" href="#533">533</a>         deferrals++;<a name="534" href="#534">534</a>     }<a name="535" href="#535">535</a> <a name="536" href="#536">536</a>     <em>/**<em>*</em></em><a name="537" href="#537">537</a> <em>     * Get the deferral count.</em><a name="538" href="#538">538</a> <em>     *</em><a name="539" href="#539">539</a> <em>     * @return the deferral count.</em><a name="540" href="#540">540</a> <em>     */</em><a name="541" href="#541">541</a>     <strong>public</strong> <strong>int</strong> getDeferrals() {<a name="542" href="#542">542</a>         <strong>return</strong> deferrals;<a name="543" href="#543">543</a>     }<a name="544" href="#544">544</a> <a name="545" href="#545">545</a>     <em>/**<em>*</em></em><a name="546" href="#546">546</a> <em>     * Remove all attributes set on this uri.</em><a name="547" href="#547">547</a> <em>     * &lt;p></em><a name="548" href="#548">548</a> <em>     * This methods removes the attribute list.</em><a name="549" href="#549">549</a> <em>     */</em><a name="550" href="#550">550</a>     <strong>public</strong> <strong>void</strong> stripToMinimal() {<a name="551" href="#551">551</a>         clearAList();<a name="552" href="#552">552</a>     }<a name="553" href="#553">553</a> <a name="554" href="#554">554</a>     <em>/**<em>* Get the size in bytes of this URI's content.</em></em><a name="555" href="#555">555</a> <em>     * This may be set at any time by any class and therefore should not be</em><a name="556" href="#556">556</a> <em>     * trusted. Primarily it exists to ease the calculation of statistics.</em><a name="557" href="#557">557</a> <em>     * @return contentSize</em><a name="558" href="#558">558</a> <em>     */</em><a name="559" href="#559">559</a>     <strong>public</strong> <strong>long</strong> getContentSize(){<a name="560" href="#560">560</a>         <strong>return</strong> contentSize;<a name="561" href="#561">561</a>     }<a name="562" href="#562">562</a> <a name="563" href="#563">563</a>     <em>/**<em>*</em></em><a name="564" href="#564">564</a> <em>     * Make note of a non-fatal error, local to a particular Processor,</em><a name="565" href="#565">565</a> <em>     * which should be logged somewhere, but allows processing to continue.</em><a name="566" href="#566">566</a> <em>     *</em><a name="567" href="#567">567</a> <em>     * This is how you add to the local-error log (the 'localized' in</em><a name="568" href="#568">568</a> <em>     * the below is making an error local rather than global, not</em><a name="569" href="#569">569</a> <em>     * making a swiss-french version of the error.).</em><a name="570" href="#570">570</a> <em>     * </em><a name="571" href="#571">571</a> <em>     * @param processorName Name of processor the exception was thrown</em><a name="572" href="#572">572</a> <em>     * in.</em><a name="573" href="#573">573</a> <em>     * @param ex Throwable to log.</em><a name="574" href="#574">574</a> <em>     * @param message Extra message to log beyond exception message.</em><a name="575" href="#575">575</a> <em>     */</em><a name="576" href="#576">576</a>     <strong>public</strong> <strong>void</strong> addLocalizedError(<strong>final</strong> String processorName,<a name="577" href="#577">577</a>             <strong>final</strong> Throwable ex, <strong>final</strong> String message) {<a name="578" href="#578">578</a>         List localizedErrors;<a name="579" href="#579">579</a>         <strong>if</strong> (containsKey(A_LOCALIZED_ERRORS)) {<a name="580" href="#580">580</a>             localizedErrors = (List) getObject(A_LOCALIZED_ERRORS);<a name="581" href="#581">581</a>         } <strong>else</strong> {<a name="582" href="#582">582</a>             localizedErrors = <strong>new</strong> ArrayList();<a name="583" href="#583">583</a>             putObject(A_LOCALIZED_ERRORS, localizedErrors);<a name="584" href="#584">584</a>         }<a name="585" href="#585">585</a> <a name="586" href="#586">586</a>         localizedErrors.add(<strong>new</strong> <a href="../../../../org/archive/crawler/datamodel/LocalizedError.html">LocalizedError</a>(processorName, ex, message));<a name="587" href="#587">587</a>         addAnnotation(<span class="string">"le:"</span> + getClassSimpleName(ex.getClass()) + <span class="string">"@"</span> +<a name="588" href="#588">588</a>             processorName);<a name="589" href="#589">589</a>     }<a name="590" href="#590">590</a>     <a name="591" href="#591">591</a>     <em class="comment">// TODO: Move to utils.</em><a name="592" href="#592">592</a>     <strong>protected</strong> String getClassSimpleName(<strong>final</strong> Class c) {<a name="593" href="#593">593</a>         String classname = c.getName();<a name="594" href="#594">594</a>         <strong>int</strong> index = classname.lastIndexOf('.');<a name="595" href="#595">595</a>         <strong>return</strong> ((index > 0 &amp;&amp; (index + 1) &lt; classname.length())?

⌨️ 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 + -