⭐ 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

📄 kw3writerprocessor.html

📁 网络爬虫开源代码
💻 HTML
📖 第 1 页 / 共 3 页
字号:
<a name="312" href="#312">312</a>       <em class="comment">// Get things we need to write in this part</em><a name="313" href="#313">313</a>       String uri = curi.toString();<a name="314" href="#314">314</a>       String ip = getHostAddress(curi);<a name="315" href="#315">315</a>       <strong>long</strong> headerLength = ris.getHeaderSize();<a name="316" href="#316">316</a>       <strong>long</strong> contentLength = ris.getContentSize();<a name="317" href="#317">317</a>       <strong>long</strong> archiveTime = System.currentTimeMillis() / 1000; <em class="comment">// Fetchtime in seconds</em><a name="318" href="#318">318</a>       <strong>int</strong> statusCode = curi.getFetchStatus();<a name="319" href="#319">319</a>       String headerMd5 = <strong>null</strong>;<a name="320" href="#320">320</a>       Object contentMd5 = <strong>null</strong>;       <a name="321" href="#321">321</a>       <a name="322" href="#322">322</a>       <em class="comment">// Get headerMd5</em><a name="323" href="#323">323</a>       ByteArrayOutputStream baos = <strong>new</strong> ByteArrayOutputStream();<a name="324" href="#324">324</a>       ris.readHeaderTo(baos);<a name="325" href="#325">325</a>       headerMd5 = stringToMD5(baos.toString());              <a name="326" href="#326">326</a>       <a name="327" href="#327">327</a>       <em class="comment">// Get contentMd5</em><a name="328" href="#328">328</a>       contentMd5 = curi.getContentDigest();<a name="329" href="#329">329</a>       <strong>if</strong> (contentMd5 != <strong>null</strong>)<a name="330" href="#330">330</a>           contentMd5 = getHexString((byte[]) contentMd5);<a name="331" href="#331">331</a>       <a name="332" href="#332">332</a>       StringBuffer buffer = <strong>new</strong> StringBuffer();<a name="333" href="#333">333</a>       buffer.append(<span class="string">"MIME-version: 1.1"</span> + LF);<a name="334" href="#334">334</a>       buffer.append(<span class="string">"Content-Type: multipart/mixed; boundary="</span> + boundary + LF);<a name="335" href="#335">335</a>       buffer.append(<span class="string">"HTTP-Part: ArchiveInfo"</span> + LF);<a name="336" href="#336">336</a>       buffer.append(COLLECTION_KEY + COLON + WS + <strong>this</strong>.collection + LF);<a name="337" href="#337">337</a>       buffer.append(HARVESTER_KEY + COLON + WS + <strong>this</strong>.harvester + LF);<a name="338" href="#338">338</a>       buffer.append(URL_KEY + COLON + WS + uri + LF);<a name="339" href="#339">339</a>       buffer.append(IP_ADDRESS_KEY + COLON + WS + ip + LF);<a name="340" href="#340">340</a>       buffer.append(HEADER_LENGTH_KEY + COLON + WS + headerLength + LF);<a name="341" href="#341">341</a>       buffer.append(HEADER_MD5_KEY + COLON + WS + headerMd5 + LF);<a name="342" href="#342">342</a>       buffer.append(CONTENT_LENGTH_KEY + COLON + WS + contentLength + LF);<a name="343" href="#343">343</a>       buffer.append(CONTENT_MD5_KEY + COLON + WS + contentMd5 + LF);<a name="344" href="#344">344</a>       buffer.append(ARCHIVE_TIME_KEY + COLON + WS+ archiveTime + LF);<a name="345" href="#345">345</a>       buffer.append(STATUS_CODE_KEY + COLON + WS + statusCode + LF + LF);       <a name="346" href="#346">346</a>       out.write(buffer.toString().getBytes());       <a name="347" href="#347">347</a>   }<a name="348" href="#348">348</a>   <a name="349" href="#349">349</a>   <strong>protected</strong> <strong>void</strong> writeHeaderPart(String boundary, <a href="../../../../org/archive/io/ReplayInputStream.html">ReplayInputStream</a> ris,<a name="350" href="#350">350</a>           OutputStream out) <a name="351" href="#351">351</a>           throws IOException {<a name="352" href="#352">352</a>       StringBuffer buffer = <strong>new</strong> StringBuffer();<a name="353" href="#353">353</a>       buffer.append(<span class="string">"--"</span> + boundary + LF);<a name="354" href="#354">354</a>       buffer.append(<span class="string">"Content-Type: text/plain; charset=\&quot;US-ascii\&quot;"</span> + LF);<a name="355" href="#355">355</a>       buffer.append(<span class="string">"HTTP-Part: Header"</span> + LF + LF );<a name="356" href="#356">356</a>       out.write(buffer.toString().getBytes());<a name="357" href="#357">357</a>       ris.readHeaderTo(out);       <a name="358" href="#358">358</a>   }<a name="359" href="#359">359</a>   <a name="360" href="#360">360</a>   <strong>protected</strong> <strong>void</strong> writeContentPart(String boundary, <a href="../../../../org/archive/crawler/datamodel/CrawlURI.html">CrawlURI</a> curi,<a name="361" href="#361">361</a>           <a href="../../../../org/archive/io/ReplayInputStream.html">ReplayInputStream</a> ris, OutputStream out) <a name="362" href="#362">362</a>           throws IOException {<a name="363" href="#363">363</a>       <em class="comment">// Get things we need to write in this part</em><a name="364" href="#364">364</a>       String uri = curi.toString();<a name="365" href="#365">365</a>       String contentType = curi.getContentType();<a name="366" href="#366">366</a>       <strong>long</strong> contentLength = ris.getContentSize();      <a name="367" href="#367">367</a>       <em class="comment">// Only write content if there is some</em><a name="368" href="#368">368</a>       <strong>if</strong> (contentLength == 0)   <strong>return</strong>;<a name="369" href="#369">369</a>              <a name="370" href="#370">370</a>       StringBuffer buffer = <strong>new</strong> StringBuffer();<a name="371" href="#371">371</a>       buffer.append(<span class="string">"--"</span> + boundary + LF);<a name="372" href="#372">372</a>       buffer.append(<span class="string">"Content-Type: "</span> + contentType + LF);<a name="373" href="#373">373</a>       buffer.append(<span class="string">"HTTP-Part: Content"</span> + LF + LF);<a name="374" href="#374">374</a>       out.write(buffer.toString().getBytes());<a name="375" href="#375">375</a>       <a name="376" href="#376">376</a>       <strong>if</strong> (contentLength > <strong>this</strong>.maxSize) {<a name="377" href="#377">377</a>           ris.readContentTo(out, <strong>this</strong>.maxSize);<a name="378" href="#378">378</a>           logger.info(<span class="string">" Truncated url: "</span> + uri + <span class="string">", Size: "</span> + contentLength +<a name="379" href="#379">379</a>                   <span class="string">", Content-type: "</span> + contentType);<a name="380" href="#380">380</a>       } <strong>else</strong> {<a name="381" href="#381">381</a>           ris.readContentTo(out);<a name="382" href="#382">382</a>       }<a name="383" href="#383">383</a>   }<a name="384" href="#384">384</a> <a name="385" href="#385">385</a>   <em class="comment">// --- Private helper functions --- //</em><a name="386" href="#386">386</a>   <em class="comment">/*</em><a name="387" href="#387">387</a> <em class="comment">   * Get a MD5 checksum based on a String. </em><a name="388" href="#388">388</a> <em class="comment">   */</em> <a name="389" href="#389">389</a>   <strong>private</strong> String stringToMD5(String str) {<a name="390" href="#390">390</a>       <strong>try</strong> {<a name="391" href="#391">391</a>           byte b[] = str.getBytes();<a name="392" href="#392">392</a>           MessageDigest md = MessageDigest.getInstance(<span class="string">"MD5"</span>);<a name="393" href="#393">393</a>           md.update(b);<a name="394" href="#394">394</a>           byte[] digest = md.digest();<a name="395" href="#395">395</a>           <strong>return</strong> getHexString(digest);<a name="396" href="#396">396</a>       } <strong>catch</strong> (NoSuchAlgorithmException e) {<a name="397" href="#397">397</a>           logger.log(Level.WARNING, <span class="string">"md5 error"</span>, e);<a name="398" href="#398">398</a>       } <a name="399" href="#399">399</a>       <strong>return</strong> <strong>null</strong>;<a name="400" href="#400">400</a>   }<a name="401" href="#401">401</a> <a name="402" href="#402">402</a>   <em class="comment">/*<em class="comment"> </em></em><a name="403" href="#403">403</a> <em class="comment">   * Fast convert a byte array to a hex string with possible leading zero.</em><a name="404" href="#404">404</a> <em class="comment">   */</em><a name="405" href="#405">405</a>   <strong>private</strong> String getHexString(byte[] b) {<a name="406" href="#406">406</a>       StringBuffer sb = <strong>new</strong> StringBuffer();<a name="407" href="#407">407</a>       <strong>for</strong> (<strong>int</strong> i = 0; i &lt; b.length; i++) {<a name="408" href="#408">408</a>           String tmp = Integer.toHexString(b[i] &amp; 0xff);<a name="409" href="#409">409</a>           <strong>if</strong> (tmp.length() &lt; 2)<a name="410" href="#410">410</a>               sb.append(<span class="string">"0"</span> + tmp);<a name="411" href="#411">411</a>           <strong>else</strong><a name="412" href="#412">412</a>               sb.append(tmp);<a name="413" href="#413">413</a>       }<a name="414" href="#414">414</a>       <strong>return</strong> sb.toString();<a name="415" href="#415">415</a>   }<a name="416" href="#416">416</a> <a name="417" href="#417">417</a>   <em class="comment">/*<em class="comment"> </em></em><a name="418" href="#418">418</a> <em class="comment">   * Chmods for all newly created directories.</em><a name="419" href="#419">419</a> <em class="comment">   */</em><a name="420" href="#420">420</a>   <strong>private</strong> <strong>void</strong> chmods(File dir, File arcsDir) {<a name="421" href="#421">421</a>       String topdir = arcsDir.getAbsolutePath();<a name="422" href="#422">422</a>       chmod(dir, <strong>this</strong>.chmodValue);<a name="423" href="#423">423</a>       File parent = dir.getParentFile();<a name="424" href="#424">424</a>       <strong>while</strong> (!parent.getAbsolutePath().equalsIgnoreCase((topdir))) {<a name="425" href="#425">425</a>           chmod(parent, <strong>this</strong>.chmodValue);<a name="426" href="#426">426</a>           parent = parent.getParentFile();<a name="427" href="#427">427</a>       }<a name="428" href="#428">428</a>       <a name="429" href="#429">429</a>   }<a name="430" href="#430">430</a> <a name="431" href="#431">431</a>   <em class="comment">/*<em class="comment"> </em></em><a name="432" href="#432">432</a> <em class="comment">   * Chmod for a specific file or directory.</em><a name="433" href="#433">433</a> <em class="comment">   */</em><a name="434" href="#434">434</a>   <strong>private</strong> <strong>void</strong> chmod(File file, String permissions) {<a name="435" href="#435">435</a>       Process proc = <strong>null</strong>;<a name="436" href="#436">436</a>       <strong>try</strong> {<a name="437" href="#437">437</a>           proc = Runtime.getRuntime().exec(<span class="string">"chmod "</span> + permissions + <span class="string">" "</span> +<a name="438" href="#438">438</a>                   file.getAbsolutePath());<a name="439" href="#439">439</a>           proc.waitFor();<a name="440" href="#440">440</a>           proc.getInputStream().close();<a name="441" href="#441">441</a>           proc.getOutputStream().close();<a name="442" href="#442">442</a>           proc.getErrorStream().close();<a name="443" href="#443">443</a>       } <strong>catch</strong> (IOException e) {<a name="444" href="#444">444</a>           logger.log(Level.WARNING, <span class="string">"chmod failed"</span>, e);<a name="445" href="#445">445</a>       } <strong>catch</strong> (InterruptedException e) {<a name="446" href="#446">446</a>           logger.log(Level.WARNING, <span class="string">"chmod failed"</span>, e);<a name="447" href="#447">447</a>       }<a name="448" href="#448">448</a>   }<a name="449" href="#449">449</a> <a name="450" href="#450">450</a>   <strong>private</strong> String getHostAddress(<a href="../../../../org/archive/crawler/datamodel/CrawlURI.html">CrawlURI</a> curi) {<a name="451" href="#451">451</a>       <a href="../../../../org/archive/crawler/datamodel/CrawlHost.html">CrawlHost</a> h = getController().getServerCache().getHostFor(curi);<a name="452" href="#452">452</a>       <strong>if</strong> (h == <strong>null</strong>) {<a name="453" href="#453">453</a>           <strong>throw</strong> <strong>new</strong> NullPointerException(<span class="string">"Crawlhost is null for "</span> + curi + <span class="string">" "</span> +<a name="454" href="#454">454</a>                   curi.getVia());<a name="455" href="#455">455</a>       }<a name="456" href="#456">456</a>       InetAddress a = h.getIP();<a name="457" href="#457">457</a>       <strong>if</strong> (a == <strong>null</strong>) {<a name="458" href="#458">458</a>           <strong>throw</strong> <strong>new</strong> NullPointerException(<span class="string">"Address is null for "</span> + curi + <span class="string">" "</span> +<a name="459" href="#459">459</a>              curi.getVia() + <span class="string">". Address "</span> +<a name="460" href="#460">460</a>                  ((h.getIpFetched() == CrawlHost.IP_NEVER_LOOKED_UP) ?<a name="461" href="#461">461</a>                      <span class="string">"was never looked up."</span> :<a name="462" href="#462">462</a>                      (System.currentTimeMillis() - h.getIpFetched()) + <span class="string">" ms ago."</span>));<a name="463" href="#463">463</a>       }<a name="464" href="#464">464</a>       <strong>return</strong> h.getIP().getHostAddress();<a name="465" href="#465">465</a>   }<a name="466" href="#466">466</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 + -