📄 crawlserver.html
字号:
<a name="250" href="#250">250</a> RobotsHonoringPolicy honoringPolicy =<a name="251" href="#251">251</a> settingsHandler.getOrder().getRobotsHonoringPolicy();<a name="252" href="#252">252</a> <strong>this</strong>.robots.honoringPolicy = honoringPolicy;<a name="253" href="#253">253</a> }<a name="254" href="#254">254</a> }<a name="255" href="#255">255</a> <a name="256" href="#256">256</a> <em>/**<em>* Get the settings handler.</em></em><a name="257" href="#257">257</a> <em> *</em><a name="258" href="#258">258</a> <em> * @return the settings handler.</em><a name="259" href="#259">259</a> <em> */</em><a name="260" href="#260">260</a> <strong>public</strong> <a href="../../../../org/archive/crawler/settings/SettingsHandler.html">SettingsHandler</a> getSettingsHandler() {<a name="261" href="#261">261</a> <strong>return</strong> <strong>this</strong>.settingsHandler;<a name="262" href="#262">262</a> }<a name="263" href="#263">263</a> <a name="264" href="#264">264</a> <em>/**<em>* Get the settings object in effect for this server.</em></em><a name="265" href="#265">265</a> <em> * @param curi</em><a name="266" href="#266">266</a> <em> *</em><a name="267" href="#267">267</a> <em> * @return the settings object in effect for this server.</em><a name="268" href="#268">268</a> <em> * @throws URIException</em><a name="269" href="#269">269</a> <em> */</em><a name="270" href="#270">270</a> <strong>private</strong> <a href="../../../../org/archive/crawler/settings/CrawlerSettings.html">CrawlerSettings</a> getSettings(<a href="../../../../org/archive/crawler/datamodel/CandidateURI.html">CandidateURI</a> curi) {<a name="271" href="#271">271</a> <strong>try</strong> {<a name="272" href="#272">272</a> <strong>return</strong> <strong>this</strong>.settingsHandler.<a name="273" href="#273">273</a> getSettings(curi.getUURI().getReferencedHost(),<a name="274" href="#274">274</a> curi.getUURI());<a name="275" href="#275">275</a> } <strong>catch</strong> (URIException e) {<a name="276" href="#276">276</a> <strong>return</strong> <strong>null</strong>;<a name="277" href="#277">277</a> }<a name="278" href="#278">278</a> }<a name="279" href="#279">279</a> <a name="280" href="#280">280</a> <em>/**<em>* Set the settings handler to be used by this server.</em></em><a name="281" href="#281">281</a> <em> *</em><a name="282" href="#282">282</a> <em> * @param settingsHandler the settings handler to be used by this server.</em><a name="283" href="#283">283</a> <em> */</em><a name="284" href="#284">284</a> <strong>public</strong> <strong>void</strong> setSettingsHandler(<a href="../../../../org/archive/crawler/settings/SettingsHandler.html">SettingsHandler</a> settingsHandler) {<a name="285" href="#285">285</a> <strong>this</strong>.settingsHandler = settingsHandler;<a name="286" href="#286">286</a> }<a name="287" href="#287">287</a> <a name="288" href="#288">288</a> <strong>public</strong> <strong>void</strong> incrementConsecutiveConnectionErrors() {<a name="289" href="#289">289</a> <strong>this</strong>.consecutiveConnectionErrors++;<a name="290" href="#290">290</a> }<a name="291" href="#291">291</a> <a name="292" href="#292">292</a> <strong>public</strong> <strong>void</strong> resetConsecutiveConnectionErrors() {<a name="293" href="#293">293</a> <strong>this</strong>.consecutiveConnectionErrors = 0;<a name="294" href="#294">294</a> }<a name="295" href="#295">295</a> <a name="296" href="#296">296</a> <em>/**<em>*</em></em><a name="297" href="#297">297</a> <em> * @return Credential avatars for this server. Returns null if none.</em><a name="298" href="#298">298</a> <em> */</em><a name="299" href="#299">299</a> <strong>public</strong> Set getCredentialAvatars() {<a name="300" href="#300">300</a> <strong>return</strong> <strong>this</strong>.avatars;<a name="301" href="#301">301</a> }<a name="302" href="#302">302</a> <a name="303" href="#303">303</a> <em>/**<em>*</em></em><a name="304" href="#304">304</a> <em> * @return True if there are avatars attached to this instance.</em><a name="305" href="#305">305</a> <em> */</em><a name="306" href="#306">306</a> <strong>public</strong> <strong>boolean</strong> hasCredentialAvatars() {<a name="307" href="#307">307</a> <strong>return</strong> <strong>this</strong>.avatars != <strong>null</strong> && <strong>this</strong>.avatars.size() > 0;<a name="308" href="#308">308</a> }<a name="309" href="#309">309</a> <a name="310" href="#310">310</a> <em>/**<em>*</em></em><a name="311" href="#311">311</a> <em> * Add an avatar.</em><a name="312" href="#312">312</a> <em> *</em><a name="313" href="#313">313</a> <em> * @param ca Credential avatar to add to set of avatars.</em><a name="314" href="#314">314</a> <em> */</em><a name="315" href="#315">315</a> <strong>public</strong> <strong>void</strong> addCredentialAvatar(<a href="../../../../org/archive/crawler/datamodel/credential/CredentialAvatar.html">CredentialAvatar</a> ca) {<a name="316" href="#316">316</a> <strong>if</strong> (<strong>this</strong>.avatars == <strong>null</strong>) {<a name="317" href="#317">317</a> <strong>this</strong>.avatars = <strong>new</strong> HashSet();<a name="318" href="#318">318</a> }<a name="319" href="#319">319</a> <strong>this</strong>.avatars.add(ca);<a name="320" href="#320">320</a> }<a name="321" href="#321">321</a> <a name="322" href="#322">322</a> <em>/**<em>*</em></em><a name="323" href="#323">323</a> <em> * If true then valid robots.txt information has been retrieved. If false</em><a name="324" href="#324">324</a> <em> * either no attempt has been made to fetch robots.txt or the attempt</em><a name="325" href="#325">325</a> <em> * failed.</em><a name="326" href="#326">326</a> <em> *</em><a name="327" href="#327">327</a> <em> * @return Returns the validRobots.</em><a name="328" href="#328">328</a> <em> */</em><a name="329" href="#329">329</a> <strong>public</strong> <strong>boolean</strong> isValidRobots() {<a name="330" href="#330">330</a> <strong>return</strong> validRobots;<a name="331" href="#331">331</a> }<a name="332" href="#332">332</a> <a name="333" href="#333">333</a> <em>/**<em>*</em></em><a name="334" href="#334">334</a> <em> * Get key to use doing lookup on server instances.</em><a name="335" href="#335">335</a> <em> * @param cauri CandidateURI we're to get server key for.</em><a name="336" href="#336">336</a> <em> * @return String to use as server key.</em><a name="337" href="#337">337</a> <em> * @throws URIException</em><a name="338" href="#338">338</a> <em> */</em><a name="339" href="#339">339</a> <strong>public</strong> <strong>static</strong> String getServerKey(<a href="../../../../org/archive/crawler/datamodel/CandidateURI.html">CandidateURI</a> cauri)<a name="340" href="#340">340</a> throws URIException {<a name="341" href="#341">341</a> <em class="comment">// TODO: evaluate if this is really necessary -- why not </em><a name="342" href="#342">342</a> <em class="comment">// make the server of a dns CandidateURI the looked-up domain,</em><a name="343" href="#343">343</a> <em class="comment">// also simplifying FetchDNS?</em><a name="344" href="#344">344</a> String key = cauri.getUURI().getAuthorityMinusUserinfo();<a name="345" href="#345">345</a> <strong>if</strong> (key == <strong>null</strong>) {<a name="346" href="#346">346</a> <em class="comment">// Fallback for cases where getAuthority() fails (eg 'dns:'.</em><a name="347" href="#347">347</a> <em class="comment">// DNS UURIs have the 'domain' in the 'path' parameter, not</em><a name="348" href="#348">348</a> <em class="comment">// in the authority).</em><a name="349" href="#349">349</a> key = cauri.getUURI().getCurrentHierPath();<a name="350" href="#350">350</a> <strong>if</strong>(key != <strong>null</strong> && !key.matches(<span class="string">"[-_//w//.:]+"</span>)) {<a name="351" href="#351">351</a> <em class="comment">// Not just word chars and dots and colons and dashes and</em><a name="352" href="#352">352</a> <em class="comment">// underscores; throw away</em><a name="353" href="#353">353</a> key = <strong>null</strong>;<a name="354" href="#354">354</a> }<a name="355" href="#355">355</a> }<a name="356" href="#356">356</a> <strong>if</strong> (key != <strong>null</strong> &&<a name="357" href="#357">357</a> cauri.getUURI().getScheme().equals(UURIFactory.HTTPS)) {<a name="358" href="#358">358</a> <em class="comment">// If https and no port specified, add default https port to</em><a name="359" href="#359">359</a> <em class="comment">// distinuish https from http server without a port.</em><a name="360" href="#360">360</a> <strong>if</strong> (!key.matches(<span class="string">".+:[0-9]+"</span>)) {<a name="361" href="#361">361</a> key += <span class="string">":"</span> + UURIFactory.HTTPS_PORT;<a name="362" href="#362">362</a> }<a name="363" href="#363">363</a> }<a name="364" href="#364">364</a> <strong>return</strong> key;<a name="365" href="#365">365</a> }<a name="366" href="#366">366</a> <a name="367" href="#367">367</a> <em class="comment">/*<em class="comment"> (non-Javadoc)</em></em><a name="368" href="#368">368</a> <em class="comment"> * @see org.archive.crawler.datamodel.CrawlSubstats.HasCrawlSubstats#getSubstats()</em><a name="369" href="#369">369</a> <em class="comment"> */</em><a name="370" href="#370">370</a> <strong>public</strong> <a href="../../../../org/archive/crawler/datamodel/CrawlSubstats.html">CrawlSubstats</a> getSubstats() {<a name="371" href="#371">371</a> <strong>return</strong> substats;<a name="372" href="#372">372</a> }<a name="373" href="#373">373</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 + -