⭐ 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

📁 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="294" href="#294">294</a>             <strong>case</strong> S_TOO_MANY_EMBED_HOPS:<a name="295" href="#295">295</a>                 <strong>return</strong> <span class="string">"Heritrix("</span> + S_TOO_MANY_EMBED_HOPS<a name="296" href="#296">296</a>                         + <span class="string">")-Too many embed hops"</span>;<a name="297" href="#297">297</a>             <strong>case</strong> S_TOO_MANY_LINK_HOPS:<a name="298" href="#298">298</a>                 <strong>return</strong> <span class="string">"Heritrix("</span> + S_TOO_MANY_LINK_HOPS<a name="299" href="#299">299</a>                         + <span class="string">")-Too many link hops"</span>;<a name="300" href="#300">300</a>             <strong>case</strong> S_TOO_MANY_RETRIES:<a name="301" href="#301">301</a>                 <strong>return</strong> <span class="string">"Heritrix("</span> + S_TOO_MANY_RETRIES + <span class="string">")-Too many retries"</span>;<a name="302" href="#302">302</a>             <strong>case</strong> S_UNATTEMPTED:<a name="303" href="#303">303</a>                 <strong>return</strong> <span class="string">"Heritrix("</span> + S_UNATTEMPTED + <span class="string">")-Unattempted"</span>;<a name="304" href="#304">304</a>             <strong>case</strong> S_UNFETCHABLE_URI:<a name="305" href="#305">305</a>                 <strong>return</strong> <span class="string">"Heritrix("</span> + S_UNFETCHABLE_URI + <span class="string">")-Unfetchable URI"</span>;<a name="306" href="#306">306</a>             <strong>case</strong> S_PROCESSING_THREAD_KILLED:<a name="307" href="#307">307</a>                 <strong>return</strong> <span class="string">"Heritrix("</span> + S_PROCESSING_THREAD_KILLED + <span class="string">")-"</span> +<a name="308" href="#308">308</a>                     <span class="string">"Processing thread killed"</span>;<a name="309" href="#309">309</a>             <em class="comment">// Unknown return code</em><a name="310" href="#310">310</a>             <strong>default</strong> : <strong>return</strong> Integer.toString(code);<a name="311" href="#311">311</a>         }<a name="312" href="#312">312</a>     }<a name="313" href="#313">313</a> <a name="314" href="#314">314</a> <a name="315" href="#315">315</a>     <em>/**<em>*</em></em><a name="316" href="#316">316</a> <em>     * Return the overall/fetch status of this CrawlURI for its</em><a name="317" href="#317">317</a> <em>     * current trip through the processing loop.</em><a name="318" href="#318">318</a> <em>     *</em><a name="319" href="#319">319</a> <em>     * @return a value from FetchStatusCodes</em><a name="320" href="#320">320</a> <em>     */</em><a name="321" href="#321">321</a>     <strong>public</strong> <strong>int</strong> getFetchStatus(){<a name="322" href="#322">322</a>         <strong>return</strong> fetchStatus;<a name="323" href="#323">323</a>     }<a name="324" href="#324">324</a> <a name="325" href="#325">325</a>     <em>/**<em>*</em></em><a name="326" href="#326">326</a> <em>     * Set the overall/fetch status of this CrawlURI for</em><a name="327" href="#327">327</a> <em>     * its current trip through the processing loop.</em><a name="328" href="#328">328</a> <em>     *</em><a name="329" href="#329">329</a> <em>     * @param newstatus a value from FetchStatusCodes</em><a name="330" href="#330">330</a> <em>     */</em><a name="331" href="#331">331</a>     <strong>public</strong> <strong>void</strong> setFetchStatus(<strong>int</strong> newstatus){<a name="332" href="#332">332</a>         fetchStatus = newstatus;<a name="333" href="#333">333</a>     }<a name="334" href="#334">334</a> <a name="335" href="#335">335</a>     <em>/**<em>*</em></em><a name="336" href="#336">336</a> <em>     * Get the number of attempts at getting the document referenced by this</em><a name="337" href="#337">337</a> <em>     * URI.</em><a name="338" href="#338">338</a> <em>     *</em><a name="339" href="#339">339</a> <em>     * @return the number of attempts at getting the document referenced by this</em><a name="340" href="#340">340</a> <em>     *         URI.</em><a name="341" href="#341">341</a> <em>     */</em><a name="342" href="#342">342</a>     <strong>public</strong> <strong>int</strong> getFetchAttempts() {<a name="343" href="#343">343</a>         <strong>return</strong> fetchAttempts;<a name="344" href="#344">344</a>     }<a name="345" href="#345">345</a> <a name="346" href="#346">346</a>     <em>/**<em>*</em></em><a name="347" href="#347">347</a> <em>     * Increment the number of attempts at getting the document referenced by</em><a name="348" href="#348">348</a> <em>     * this URI.</em><a name="349" href="#349">349</a> <em>     *</em><a name="350" href="#350">350</a> <em>     * @return the number of attempts at getting the document referenced by this</em><a name="351" href="#351">351</a> <em>     *         URI.</em><a name="352" href="#352">352</a> <em>     */</em><a name="353" href="#353">353</a>     <strong>public</strong> <strong>int</strong> incrementFetchAttempts() {<a name="354" href="#354">354</a>         <em class="comment">// TODO: rename, this is actually processing-loop-attempts</em><a name="355" href="#355">355</a>         <strong>return</strong> fetchAttempts++;<a name="356" href="#356">356</a>     }<a name="357" href="#357">357</a> <a name="358" href="#358">358</a>     <em>/**<em>*</em></em><a name="359" href="#359">359</a> <em>     * Reset fetchAttempts counter.</em><a name="360" href="#360">360</a> <em>     */</em><a name="361" href="#361">361</a>     <strong>public</strong> <strong>void</strong> resetFetchAttempts() {<a name="362" href="#362">362</a>         <strong>this</strong>.fetchAttempts = 0;<a name="363" href="#363">363</a>     }<a name="364" href="#364">364</a> <a name="365" href="#365">365</a>     <em>/**<em>*</em></em><a name="366" href="#366">366</a> <em>     * Reset deferrals counter.</em><a name="367" href="#367">367</a> <em>     */</em><a name="368" href="#368">368</a>     <strong>public</strong> <strong>void</strong> resetDeferrals() {<a name="369" href="#369">369</a>         <strong>this</strong>.deferrals = 0;<a name="370" href="#370">370</a>     }<a name="371" href="#371">371</a> <a name="372" href="#372">372</a>     <em>/**<em>*</em></em><a name="373" href="#373">373</a> <em>     * Get the next processor to process this URI.</em><a name="374" href="#374">374</a> <em>     *</em><a name="375" href="#375">375</a> <em>     * @return the processor that should process this URI next.</em><a name="376" href="#376">376</a> <em>     */</em><a name="377" href="#377">377</a>     <strong>public</strong> <a href="../../../../org/archive/crawler/framework/Processor.html">Processor</a> nextProcessor() {<a name="378" href="#378">378</a>         <strong>return</strong> nextProcessor;<a name="379" href="#379">379</a>     }<a name="380" href="#380">380</a> <a name="381" href="#381">381</a>     <em>/**<em>*</em></em><a name="382" href="#382">382</a> <em>     * Get the processor chain that should be processing this URI after the</em><a name="383" href="#383">383</a> <em>     * current chain is finished with it.</em><a name="384" href="#384">384</a> <em>     *</em><a name="385" href="#385">385</a> <em>     * @return the next processor chain to process this URI.</em><a name="386" href="#386">386</a> <em>     */</em><a name="387" href="#387">387</a>     <strong>public</strong> <a href="../../../../org/archive/crawler/framework/ProcessorChain.html">ProcessorChain</a> nextProcessorChain() {<a name="388" href="#388">388</a>         <strong>return</strong> nextProcessorChain;<a name="389" href="#389">389</a>     }<a name="390" href="#390">390</a> <a name="391" href="#391">391</a>     <em>/**<em>*</em></em><a name="392" href="#392">392</a> <em>     * Set the next processor to process this URI.</em><a name="393" href="#393">393</a> <em>     *</em><a name="394" href="#394">394</a> <em>     * @param processor the next processor to process this URI.</em><a name="395" href="#395">395</a> <em>     */</em><a name="396" href="#396">396</a>     <strong>public</strong> <strong>void</strong> setNextProcessor(<a href="../../../../org/archive/crawler/framework/Processor.html">Processor</a> processor) {<a name="397" href="#397">397</a>         nextProcessor = processor;<a name="398" href="#398">398</a>     }<a name="399" href="#399">399</a> <a name="400" href="#400">400</a>     <em>/**<em>*</em></em><a name="401" href="#401">401</a> <em>     * Set the next processor chain to process this URI.</em><a name="402" href="#402">402</a> <em>     *</em><a name="403" href="#403">403</a> <em>     * @param nextProcessorChain the next processor chain to process this URI.</em><a name="404" href="#404">404</a> <em>     */</em><a name="405" href="#405">405</a>     <strong>public</strong> <strong>void</strong> setNextProcessorChain(<a href="../../../../org/archive/crawler/framework/ProcessorChain.html">ProcessorChain</a> nextProcessorChain) {<a name="406" href="#406">406</a>         <strong>this</strong>.nextProcessorChain = nextProcessorChain;<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>     * Do all actions associated with setting a &lt;code>CrawlURI&lt;/code> as</em><a name="411" href="#411">411</a> <em>     * requiring a prerequisite.</em><a name="412" href="#412">412</a> <em>     *</em><a name="413" href="#413">413</a> <em>     * @param lastProcessorChain Last processor chain reference.  This chain is</em><a name="414" href="#414">414</a> <em>     * where this &lt;code>CrawlURI&lt;/code> goes next.</em><a name="415" href="#415">415</a> <em>     * @param preq Object to set a prerequisite.</em><a name="416" href="#416">416</a> <em>     * @throws URIException</em><a name="417" href="#417">417</a> <em>     */</em><a name="418" href="#418">418</a>     <strong>public</strong> <strong>void</strong> markPrerequisite(String preq,<a name="419" href="#419">419</a>             <a href="../../../../org/archive/crawler/framework/ProcessorChain.html">ProcessorChain</a> lastProcessorChain) throws URIException {<a name="420" href="#420">420</a>         <a href="../../../../org/archive/crawler/extractor/Link.html">Link</a> link = createLink(preq,Link.PREREQ_MISC,Link.PREREQ_HOP);<a name="421" href="#421">421</a>         setPrerequisiteUri(link);<a name="422" href="#422">422</a>         incrementDeferrals();<a name="423" href="#423">423</a>         setFetchStatus(S_DEFERRED);<a name="424" href="#424">424</a>         skipToProcessorChain(lastProcessorChain);<a name="425" href="#425">425</a>     }<a name="426" href="#426">426</a> <a name="427" href="#427">427</a>     <em>/**<em>*</em></em><a name="428" href="#428">428</a> <em>     * Set a prerequisite for this URI.</em><a name="429" href="#429">429</a> <em>     * &lt;p></em><a name="430" href="#430">430</a> <em>     * A prerequisite is a URI that must be crawled before this URI can be</em><a name="431" href="#431">431</a> <em>     * crawled.</em><a name="432" href="#432">432</a> <em>     *</em><a name="433" href="#433">433</a> <em>     * @param link Link to set as prereq.</em><a name="434" href="#434">434</a> <em>     */</em><a name="435" href="#435">435</a>     <strong>public</strong> <strong>void</strong> setPrerequisiteUri(Object link) {<a name="436" href="#436">436</a>         putObject(A_PREREQUISITE_URI, link);<a name="437" href="#437">437</a>     }<a name="438" href="#438">438</a> <a name="439" href="#439">439</a>     <em>/**<em>*</em></em><a name="440" href="#440">440</a> <em>     * Get the prerequisite for this URI.</em><a name="441" href="#441">441</a> <em>     * &lt;p></em><a name="442" href="#442">442</a> <em>     * A prerequisite is a URI that must be crawled before this URI can be</em><a name="443" href="#443">443</a> <em>     * crawled.</em><a name="444" href="#444">444</a> <em>     *</em>

⌨️ 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 + -