pdfparser.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="136" href="#136">136</a>         ArrayList generationList = (ArrayList)encounteredReferences.get(generation);
<a name="137" href="#137">137</a> 
<a name="138" href="#138">138</a>         Iterator scanList = generationList.iterator();
<a name="139" href="#139">139</a>         <strong>while</strong>(scanList.hasNext()){
<a name="140" href="#140">140</a>             <strong>if</strong>( ((Integer)scanList.next()).intValue() == id){
<a name="141" href="#141">141</a>                 <strong>return</strong> <strong>true</strong>;
<a name="142" href="#142">142</a>             }
<a name="143" href="#143">143</a>         }
<a name="144" href="#144">144</a>         <strong>return</strong> false;
<a name="145" href="#145">145</a>     }
<a name="146" href="#146">146</a> 
<a name="147" href="#147">147</a>     <em>/**<em>*</em></em>
<a name="148" href="#148">148</a> <em>     * Note that an object (id/generation pair) has been seen by this parser</em>
<a name="149" href="#149">149</a> <em>     * so that it can be handled differently when it is encountered again.</em>
<a name="150" href="#150">150</a> <em>     * @param generation</em>
<a name="151" href="#151">151</a> <em>     * @param id</em>
<a name="152" href="#152">152</a> <em>     */</em>
<a name="153" href="#153">153</a>     <strong>protected</strong> <strong>void</strong> markAsSeen(<strong>int</strong> generation, <strong>int</strong> id){
<a name="154" href="#154">154</a>         ArrayList objectIds = (ArrayList)encounteredReferences.get(generation);
<a name="155" href="#155">155</a>         objectIds.add( <strong>new</strong> Integer(id));
<a name="156" href="#156">156</a>     }
<a name="157" href="#157">157</a> 
<a name="158" href="#158">158</a>     <em>/**<em>*</em></em>
<a name="159" href="#159">159</a> <em>     * Get a list of URIs retrieved from the Pdf during the</em>
<a name="160" href="#160">160</a> <em>     * extractURIs operation.</em>
<a name="161" href="#161">161</a> <em>     * @return A list of URIs retrieved from the Pdf during the</em>
<a name="162" href="#162">162</a> <em>     * extractURIs operation.</em>
<a name="163" href="#163">163</a> <em>     */</em>
<a name="164" href="#164">164</a>     <strong>public</strong> ArrayList getURIs(){
<a name="165" href="#165">165</a>         <strong>return</strong> foundURIs;
<a name="166" href="#166">166</a>     }
<a name="167" href="#167">167</a> 
<a name="168" href="#168">168</a>     <em>/**<em>*</em></em>
<a name="169" href="#169">169</a> <em>     * Initialize opens the document for reading.  This is done implicitly</em>
<a name="170" href="#170">170</a> <em>     * by the constuctor.  This should only need to be called directly following</em>
<a name="171" href="#171">171</a> <em>     * a reset.</em>
<a name="172" href="#172">172</a> <em>     * @throws IOException</em>
<a name="173" href="#173">173</a> <em>     */</em>
<a name="174" href="#174">174</a>     <strong>protected</strong> <strong>void</strong> initialize() throws IOException{
<a name="175" href="#175">175</a>         <strong>if</strong>(document != <strong>null</strong>){
<a name="176" href="#176">176</a>             documentReader = <strong>new</strong> PdfReader(document);
<a name="177" href="#177">177</a>         }
<a name="178" href="#178">178</a> 
<a name="179" href="#179">179</a>         catalog = documentReader.getCatalog();
<a name="180" href="#180">180</a>     }
<a name="181" href="#181">181</a> 
<a name="182" href="#182">182</a>     <em>/**<em>*</em></em>
<a name="183" href="#183">183</a> <em>     * Extract URIs from all objects found in a Pdf document's catalog.</em>
<a name="184" href="#184">184</a> <em>     * Returns an array list representing all URIs found in the document catalog tree.</em>
<a name="185" href="#185">185</a> <em>     * @return URIs from all objects found in a Pdf document's catalog.</em>
<a name="186" href="#186">186</a> <em>     */</em>
<a name="187" href="#187">187</a>     <strong>public</strong> ArrayList extractURIs(){
<a name="188" href="#188">188</a>         extractURIs(catalog);
<a name="189" href="#189">189</a>         <strong>return</strong> getURIs();
<a name="190" href="#190">190</a>     }
<a name="191" href="#191">191</a> 
<a name="192" href="#192">192</a>     <em>/**<em>*</em></em>
<a name="193" href="#193">193</a> <em>     * Parse a PdfDictionary, looking for URIs recursively and adding</em>
<a name="194" href="#194">194</a> <em>     * them to foundURIs</em>
<a name="195" href="#195">195</a> <em>     * @param entity</em>
<a name="196" href="#196">196</a> <em>     */</em>
<a name="197" href="#197">197</a>     <strong>protected</strong> <strong>void</strong> extractURIs(PdfObject entity){
<a name="198" href="#198">198</a> 
<a name="199" href="#199">199</a>             <em class="comment">// deal with dictionaries</em>
<a name="200" href="#200">200</a>             <strong>if</strong>(entity.isDictionary()){
<a name="201" href="#201">201</a> 
<a name="202" href="#202">202</a>                 PdfDictionary dictionary= (PdfDictionary)entity;
<a name="203" href="#203">203</a> 
<a name="204" href="#204">204</a>                 Set allkeys = dictionary.getKeys();
<a name="205" href="#205">205</a>                 Iterator iterator = allkeys.iterator();
<a name="206" href="#206">206</a> 
<a name="207" href="#207">207</a>                 <strong>while</strong>(iterator.hasNext()){
<a name="208" href="#208">208</a>                     PdfName key = (PdfName)iterator.next();
<a name="209" href="#209">209</a>                     PdfObject value = dictionary.get(key);
<a name="210" href="#210">210</a> 
<a name="211" href="#211">211</a>                     <em class="comment">// see if it's the key is a UR[I,L]</em>
<a name="212" href="#212">212</a>                     <strong>if</strong>( key.toString().equals(<span class="string">"/URI"</span>) ||
<a name="213" href="#213">213</a> 		            key.toString().equals(<span class="string">"/URL"</span>) ) {
<a name="214" href="#214">214</a>                         foundURIs.add(dictionary.get(key).toString());
<a name="215" href="#215">215</a> 
<a name="216" href="#216">216</a>                     }<strong>else</strong>{
<a name="217" href="#217">217</a>                         <strong>this</strong>.extractURIs( dictionary.get( key ) );
<a name="218" href="#218">218</a>                     }
<a name="219" href="#219">219</a> 
<a name="220" href="#220">220</a>                 }
<a name="221" href="#221">221</a> 
<a name="222" href="#222">222</a>             <em class="comment">// deal with arrays</em>
<a name="223" href="#223">223</a>             }<strong>else</strong> <strong>if</strong>(entity.isArray()){
<a name="224" href="#224">224</a> 
<a name="225" href="#225">225</a>                 PdfArray array = (PdfArray)entity;
<a name="226" href="#226">226</a>                 ArrayList arrayObjects = array.getArrayList();
<a name="227" href="#227">227</a>                 Iterator objectList = arrayObjects.iterator();
<a name="228" href="#228">228</a> 
<a name="229" href="#229">229</a>                 <strong>while</strong>(objectList.hasNext()){
<a name="230" href="#230">230</a>                     <strong>this</strong>.extractURIs( (PdfObject)objectList.next());
<a name="231" href="#231">231</a>                 }
<a name="232" href="#232">232</a> 
<a name="233" href="#233">233</a>             <em class="comment">// deal with indirect references</em>
<a name="234" href="#234">234</a>             }<strong>else</strong> <strong>if</strong>(entity.getClass() == PRIndirectReference.<strong>class</strong>){
<a name="235" href="#235">235</a> 
<a name="236" href="#236">236</a>                     PRIndirectReference indirect = (PRIndirectReference)entity;
<a name="237" href="#237">237</a> 
<a name="238" href="#238">238</a>                     <em class="comment">// if we've already seen a reference to this object</em>
<a name="239" href="#239">239</a>                     <strong>if</strong>( haveSeen( indirect.getGeneration(), indirect.getNumber()) ){
<a name="240" href="#240">240</a>                         <strong>return</strong>;
<a name="241" href="#241">241</a> 
<a name="242" href="#242">242</a>                     <em class="comment">// note that we've seen it if it's new</em>
<a name="243" href="#243">243</a>                     }<strong>else</strong>{
<a name="244" href="#244">244</a>                         markAsSeen(indirect.getGeneration(), indirect.getNumber() );
<a name="245" href="#245">245</a>                     }
<a name="246" href="#246">246</a> 
<a name="247" href="#247">247</a>                     <em class="comment">// dereference the "pointer" and process the object</em>
<a name="248" href="#248">248</a>                     PdfReader reader = indirect.getReader();
<a name="249" href="#249">249</a>                     PdfObject direct = PdfReader.getPdfObject(indirect);
<a name="250" href="#250">250</a> 
<a name="251" href="#251">251</a>                     <strong>this</strong>.extractURIs(direct);
<a name="252" href="#252">252</a>             }
<a name="253" href="#253">253</a>     }
<a name="254" href="#254">254</a> 
<a name="255" href="#255">255</a>     <strong>public</strong> <strong>static</strong> <strong>void</strong> main(String[] argv){
<a name="256" href="#256">256</a> 
<a name="257" href="#257">257</a>         <strong>try</strong>{
<a name="258" href="#258">258</a>             <a href="../../../../org/archive/crawler/extractor/PDFParser.html">PDFParser</a> parser = <strong>new</strong> <a href="../../../../org/archive/crawler/extractor/PDFParser.html">PDFParser</a>(<span class="string">"/home/parkert/files/pdfspec.pdf"</span>);
<a name="259" href="#259">259</a> 
<a name="260" href="#260">260</a>             ArrayList uris = parser.extractURIs();
<a name="261" href="#261">261</a> 
<a name="262" href="#262">262</a>             Iterator i = uris.iterator();
<a name="263" href="#263">263</a> 
<a name="264" href="#264">264</a>             <strong>while</strong>(i.hasNext()){
<a name="265" href="#265">265</a>                 String uri = (String)i.next();
<a name="266" href="#266">266</a>                 System.out.println(<span class="string">"got uri: "</span> + uri);
<a name="267" href="#267">267</a>             }
<a name="268" href="#268">268</a> 
<a name="269" href="#269">269</a>         }<strong>catch</strong>(IOException e){
<a name="270" href="#270">270</a>             e.printStackTrace();
<a name="271" href="#271">271</a>         }
<a name="272" href="#272">272</a>     }
<a name="273" href="#273">273</a> }
</pre>
<hr/><div id="footer">This page was automatically generated by <a href="http://maven.apache.org/">Maven</a></div></body>
</html>