extractorhtmltest.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

<a name="212" href="#212">212</a>             }
<a name="213" href="#213">213</a>         }
<a name="214" href="#214">214</a>         System.out.println(<span class="string">"+HTML Embeds (hopType="</span>+Link.EMBED_HOP+<span class="string">"):"</span>);
<a name="215" href="#215">215</a>         <strong>if</strong> (links != <strong>null</strong>) {
<a name="216" href="#216">216</a>             <strong>for</strong> (Iterator i = links.iterator(); i.hasNext();) {
<a name="217" href="#217">217</a>                 <a href="../../../../org/archive/crawler/extractor/Link.html">Link</a> link = (Link)i.next();
<a name="218" href="#218">218</a>                 <strong>if</strong> (link.getHopType()==Link.EMBED_HOP) {
<a name="219" href="#219">219</a>                     count++;
<a name="220" href="#220">220</a>                     System.out.println(link.getDestination());
<a name="221" href="#221">221</a>                 }
<a name="222" href="#222">222</a>             }
<a name="223" href="#223">223</a>         }
<a name="224" href="#224">224</a>         System.out.
<a name="225" href="#225">225</a>             println(<span class="string">"+HTML Speculative Embeds (hopType="</span>+Link.SPECULATIVE_HOP+<span class="string">"):"</span>);
<a name="226" href="#226">226</a>         <strong>if</strong> (links != <strong>null</strong>) {
<a name="227" href="#227">227</a>             <strong>for</strong> (Iterator i = links.iterator(); i.hasNext();) {
<a name="228" href="#228">228</a>                 <a href="../../../../org/archive/crawler/extractor/Link.html">Link</a> link = (Link)i.next();
<a name="229" href="#229">229</a>                 <strong>if</strong> (link.getHopType()==Link.SPECULATIVE_HOP) {
<a name="230" href="#230">230</a>                     count++;
<a name="231" href="#231">231</a>                     System.out.println(link.getDestination());
<a name="232" href="#232">232</a>                 }
<a name="233" href="#233">233</a>             }
<a name="234" href="#234">234</a>         }
<a name="235" href="#235">235</a>         System.out.
<a name="236" href="#236">236</a>             println(<span class="string">"+HTML Other (all other hopTypes):"</span>);
<a name="237" href="#237">237</a>         <strong>if</strong> (links != <strong>null</strong>) {
<a name="238" href="#238">238</a>             <strong>for</strong> (Iterator i = links.iterator(); i.hasNext();) {
<a name="239" href="#239">239</a>                 <a href="../../../../org/archive/crawler/extractor/Link.html">Link</a> link = (Link) i.next();
<a name="240" href="#240">240</a>                 <strong>if</strong> (link.getHopType() != Link.SPECULATIVE_HOP
<a name="241" href="#241">241</a>                         &amp;&amp; link.getHopType() != Link.NAVLINK_HOP
<a name="242" href="#242">242</a>                         &amp;&amp; link.getHopType() != Link.EMBED_HOP) {
<a name="243" href="#243">243</a>                     count++;
<a name="244" href="#244">244</a>                     System.out.println(link.getHopType() + <span class="string">" "</span>
<a name="245" href="#245">245</a>                             + link.getDestination());
<a name="246" href="#246">246</a>                 }
<a name="247" href="#247">247</a>             }
<a name="248" href="#248">248</a>         }
<a name="249" href="#249">249</a>         System.out.println(<span class="string">"TOTAL URIS EXTRACTED: "</span>+count);
<a name="250" href="#250">250</a>     }
<a name="251" href="#251">251</a> 
<a name="252" href="#252">252</a>     <em>/**<em>*</em></em>
<a name="253" href="#253">253</a> <em>     * Test a particular &lt;embed src=...> construct that was suspicious in</em>
<a name="254" href="#254">254</a> <em>     * the No10GovUk crawl.</em>
<a name="255" href="#255">255</a> <em>     *</em>
<a name="256" href="#256">256</a> <em>     * @throws URIException</em>
<a name="257" href="#257">257</a> <em>     */</em>
<a name="258" href="#258">258</a>     <strong>public</strong> <strong>void</strong> testEmbedSrc() throws URIException {
<a name="259" href="#259">259</a>         <a href="../../../../org/archive/crawler/datamodel/CrawlURI.html">CrawlURI</a> curi=
<a name="260" href="#260">260</a>             <strong>new</strong> <a href="../../../../org/archive/crawler/datamodel/CrawlURI.html">CrawlURI</a>(UURIFactory.getInstance(<span class="string">"http://www.example.org"</span>));
<a name="261" href="#261">261</a>         <em class="comment">// An example from http://www.records.pro.gov.uk/documents/prem/18/1/default.asp?PageId=62&amp;qt=true</em>
<a name="262" href="#262">262</a>         CharSequence cs = <span class="string">"&lt;embed src=\&quot;/documents/prem/18/1/graphics/qtvr/"</span> +
<a name="263" href="#263">263</a>             <span class="string">"hall.mov\&quot; width=\&quot;320\&quot; height=\&quot;212\&quot; controller=\&quot;true\&quot; "</span> +
<a name="264" href="#264">264</a>             <span class="string">"CORRECTION=\&quot;FULL\&quot; pluginspage=\&quot;http://www.apple.com/"</span> +
<a name="265" href="#265">265</a>             <span class="string">"quicktime/download/\&quot; /> "</span>;
<a name="266" href="#266">266</a>         <strong>this</strong>.extractor.extract(curi,cs);
<a name="267" href="#267">267</a>         assertTrue(CollectionUtils.exists(curi.getOutLinks(), <strong>new</strong> Predicate() {
<a name="268" href="#268">268</a>             <strong>public</strong> <strong>boolean</strong> evaluate(Object object) {
<a name="269" href="#269">269</a>                 <strong>return</strong> ((Link) object).getDestination().toString().indexOf(
<a name="270" href="#270">270</a>                         <span class="string">"/documents/prem/18/1/graphics/qtvr/hall.mov"</span>)>=0;
<a name="271" href="#271">271</a>             }
<a name="272" href="#272">272</a>         }));
<a name="273" href="#273">273</a>     }
<a name="274" href="#274">274</a>     
<a name="275" href="#275">275</a>     <em>/**<em>*</em></em>
<a name="276" href="#276">276</a> <em>     * Test a whitespace issue found in href.</em>
<a name="277" href="#277">277</a> <em>     * </em>
<a name="278" href="#278">278</a> <em>     * See [ 963965 ] Either UURI or ExtractHTML should strip whitespace better.</em>
<a name="279" href="#279">279</a> <em>     * https://sourceforge.net/tracker/?func=detail&amp;atid=539099&amp;aid=963965&amp;group_id=73833</em>
<a name="280" href="#280">280</a> <em>     *</em>
<a name="281" href="#281">281</a> <em>     * @throws URIException</em>
<a name="282" href="#282">282</a> <em>     */</em>
<a name="283" href="#283">283</a>     <strong>public</strong> <strong>void</strong> testHrefWhitespace() throws URIException {
<a name="284" href="#284">284</a>         <a href="../../../../org/archive/crawler/datamodel/CrawlURI.html">CrawlURI</a> curi =
<a name="285" href="#285">285</a>             <strong>new</strong> <a href="../../../../org/archive/crawler/datamodel/CrawlURI.html">CrawlURI</a>(UURIFactory.getInstance(<span class="string">"http://www.carsound.dk"</span>));
<a name="286" href="#286">286</a>         CharSequence cs = <span class="string">"&lt;a href=\&quot;http://www.carsound.dk\n\n\n"</span> +
<a name="287" href="#287">287</a>         	<span class="string">"\&quot;\ntarget=\&quot;_blank\&quot;>C.A.R. Sound\n\n\n\n&lt;/a>"</span>;   
<a name="288" href="#288">288</a>         <strong>this</strong>.extractor.extract(curi,cs);
<a name="289" href="#289">289</a>         curi.getOutLinks();
<a name="290" href="#290">290</a>         assertTrue(<span class="string">"Not stripping new lines"</span>, CollectionUtils.exists(curi
<a name="291" href="#291">291</a>                 .getOutLinks(), <strong>new</strong> Predicate() {
<a name="292" href="#292">292</a>             <strong>public</strong> <strong>boolean</strong> evaluate(Object object) {
<a name="293" href="#293">293</a>                 <strong>return</strong> ((Link) object).getDestination().toString().indexOf(
<a name="294" href="#294">294</a>                         <span class="string">"http://www.carsound.dk/"</span>)>=0;
<a name="295" href="#295">295</a>             }
<a name="296" href="#296">296</a>         }));
<a name="297" href="#297">297</a>     }
<a name="298" href="#298">298</a>     
<a name="299" href="#299">299</a>     <strong>public</strong> <strong>static</strong> <strong>void</strong> main(String[] args) throws Exception {
<a name="300" href="#300">300</a>         <strong>if</strong> (args.length != 1 &amp;&amp; args.length != 2) {
<a name="301" href="#301">301</a>             System.err.println(<span class="string">"Usage: "</span> + ExtractorHTMLTest.<strong>class</strong>.getName() +
<a name="302" href="#302">302</a>                 <span class="string">" URL|PATH [ENCODING]"</span>);
<a name="303" href="#303">303</a>             System.exit(1);
<a name="304" href="#304">304</a>         }
<a name="305" href="#305">305</a>         <a href="../../../../org/archive/crawler/extractor/ExtractorHTMLTest.html">ExtractorHTMLTest</a> testCase = <strong>new</strong> <a href="../../../../org/archive/crawler/extractor/ExtractorHTMLTest.html">ExtractorHTMLTest</a>();
<a name="306" href="#306">306</a>         testCase.setUp();
<a name="307" href="#307">307</a>         <strong>try</strong> {
<a name="308" href="#308">308</a>             testCase.runExtractor(testCase.getUURI(args[0]),
<a name="309" href="#309">309</a>                 (args.length == 2)? args[1]: <strong>null</strong>);
<a name="310" href="#310">310</a>         } <strong>finally</strong> {
<a name="311" href="#311">311</a>             testCase.tearDown();
<a name="312" href="#312">312</a>         }
<a name="313" href="#313">313</a>     }
<a name="314" href="#314">314</a> }
</pre>
<hr/><div id="footer">This page was automatically generated by <a href="http://maven.apache.org/">Maven</a></div></body>
</html>