⭐ 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

📄 extractorswf.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 2 页
字号:
<a name="116" href="#116">116</a>                     <strong>int</strong>  length = header &amp; 0x3F;  <em class="comment">//only want the bottom 6 bits</em><a name="117" href="#117">117</a>                     <strong>boolean</strong> longTag = (length == 0x3F);<a name="118" href="#118">118</a>                     <strong>if</strong>(longTag) {<a name="119" href="#119">119</a>                         length = (<strong>int</strong>)mIn.readUI32();<a name="120" href="#120">120</a>                     }<a name="121" href="#121">121</a>                     <em class="comment">// Below test added for Heritrix use.</em><a name="122" href="#122">122</a>                     <strong>if</strong> (length > MAX_READ_SIZE) {<a name="123" href="#123">123</a>                         <em class="comment">// skip to next, rather than throw IOException ending</em><a name="124" href="#124">124</a>                         <em class="comment">// processing</em><a name="125" href="#125">125</a>                         mIn.skipBytes(length);<a name="126" href="#126">126</a>                         logger.info(<span class="string">"oversized SWF tag (type="</span> + type<a name="127" href="#127">127</a>                                 + <span class="string">";length="</span> + length + <span class="string">") skipped"</span>);<a name="128" href="#128">128</a>                     } <strong>else</strong> {<a name="129" href="#129">129</a>                         byte[] contents = mIn.read(length);<a name="130" href="#130">130</a>                         mConsumer.tag(type, longTag, contents);<a name="131" href="#131">131</a>                     }<a name="132" href="#132">132</a>                     <strong>return</strong> type;<a name="133" href="#133">133</a>                 }<a name="134" href="#134">134</a>             };<a name="135" href="#135">135</a>             <a name="136" href="#136">136</a>             reader.readFile();<a name="137" href="#137">137</a>             numberOfLinksExtracted += curiAction.getLinkCount();<a name="138" href="#138">138</a>         } <strong>catch</strong> (IOException e) {<a name="139" href="#139">139</a>             curi.addLocalizedError(getName(), e, <span class="string">"Fail reading."</span>);<a name="140" href="#140">140</a>         } <strong>finally</strong> {<a name="141" href="#141">141</a>             <strong>try</strong> {<a name="142" href="#142">142</a>                 documentStream.close();<a name="143" href="#143">143</a>             } <strong>catch</strong> (IOException e) {<a name="144" href="#144">144</a>                 curi.addLocalizedError(getName(), e, <span class="string">"Fail on close."</span>);<a name="145" href="#145">145</a>             }<a name="146" href="#146">146</a>         }<a name="147" href="#147">147</a> <a name="148" href="#148">148</a>         <em class="comment">// Set flag to indicate that link extraction is completed.</em><a name="149" href="#149">149</a>         curi.linkExtractorFinished();<a name="150" href="#150">150</a>         logger.fine(curi + <span class="string">" has "</span> + numberOfLinksExtracted + <span class="string">" links."</span>);<a name="151" href="#151">151</a>     }<a name="152" href="#152">152</a>     <a name="153" href="#153">153</a>     <strong>public</strong> String report() {<a name="154" href="#154">154</a>         StringBuffer ret = <strong>new</strong> StringBuffer();<a name="155" href="#155">155</a>         ret.append(<span class="string">"Processor: org.archive.crawler.extractor.ExtractorSWF\n"</span>);<a name="156" href="#156">156</a>         ret.append(<span class="string">"  Function:          Link extraction on Shockwave Flash "</span> +<a name="157" href="#157">157</a>             <span class="string">"documents (.swf)\n"</span>);<a name="158" href="#158">158</a> <a name="159" href="#159">159</a>         ret.append(<span class="string">"  CrawlURIs handled: "</span> + numberOfCURIsHandled + <span class="string">"\n"</span>);<a name="160" href="#160">160</a>         ret.append(<span class="string">"  Links extracted:   "</span> + numberOfLinksExtracted + <span class="string">"\n\n"</span>);<a name="161" href="#161">161</a>         <strong>return</strong> ret.toString();<a name="162" href="#162">162</a>     }<a name="163" href="#163">163</a>     <a name="164" href="#164">164</a>     <a name="165" href="#165">165</a>     <em>/**<em>*</em></em><a name="166" href="#166">166</a> <em>     * Get a TagParser</em><a name="167" href="#167">167</a> <em>     * </em><a name="168" href="#168">168</a> <em>     * A custom ExtractorTagParser which ignores all the big binary image/</em><a name="169" href="#169">169</a> <em>     * sound/font types which don't carry URLs is used, to avoid the </em><a name="170" href="#170">170</a> <em>     * occasionally fatal (OutOfMemoryError) memory bloat caused by the</em><a name="171" href="#171">171</a> <em>     * all-in-memory SWF library handling. </em><a name="172" href="#172">172</a> <em>     * </em><a name="173" href="#173">173</a> <em>     * @param customTags A custom tag parser.</em><a name="174" href="#174">174</a> <em>     * @return An SWFReader.</em><a name="175" href="#175">175</a> <em>     */</em><a name="176" href="#176">176</a>     <strong>private</strong> TagParser getTagParser(<a href="../../../../org/archive/crawler/extractor/CustomSWFTags.html">CustomSWFTags</a> customTags) {<a name="177" href="#177">177</a>         <strong>return</strong> <strong>new</strong> ExtractorTagParser(customTags);<a name="178" href="#178">178</a>     }<a name="179" href="#179">179</a>     <a name="180" href="#180">180</a>     <em>/**<em>*</em></em><a name="181" href="#181">181</a> <em>     * TagParser customized to ignore SWFTags that </em><a name="182" href="#182">182</a> <em>     * will never contain extractable URIs. </em><a name="183" href="#183">183</a> <em>     */</em><a name="184" href="#184">184</a>     <strong>protected</strong> <strong>class</strong> ExtractorTagParser <strong>extends</strong> TagParser {<a name="185" href="#185">185</a> <a name="186" href="#186">186</a>         <strong>protected</strong> ExtractorTagParser(SWFTagTypes tagtypes) {<a name="187" href="#187">187</a>             <strong>super</strong>(tagtypes);<a name="188" href="#188">188</a>         }<a name="189" href="#189">189</a> <a name="190" href="#190">190</a>         <strong>protected</strong> <strong>void</strong> parseDefineBits(InStream in) throws IOException {<a name="191" href="#191">191</a>             <em class="comment">// DO NOTHING - no URLs to be found in bits</em><a name="192" href="#192">192</a>         }<a name="193" href="#193">193</a> <a name="194" href="#194">194</a>         <strong>protected</strong> <strong>void</strong> parseDefineBitsJPEG3(InStream in) throws IOException {<a name="195" href="#195">195</a>             <em class="comment">// DO NOTHING - no URLs to be found in bits</em><a name="196" href="#196">196</a>         }<a name="197" href="#197">197</a> <a name="198" href="#198">198</a>         <strong>protected</strong> <strong>void</strong> parseDefineBitsLossless(InStream in, <strong>int</strong> length, <strong>boolean</strong> hasAlpha) throws IOException {<a name="199" href="#199">199</a>             <em class="comment">// DO NOTHING - no URLs to be found in bits</em><a name="200" href="#200">200</a>         }<a name="201" href="#201">201</a> <a name="202" href="#202">202</a>         <strong>protected</strong> <strong>void</strong> parseDefineButtonSound(InStream in) throws IOException {<a name="203" href="#203">203</a>             <em class="comment">// DO NOTHING - no URLs to be found in sound</em><a name="204" href="#204">204</a>         }<a name="205" href="#205">205</a> <a name="206" href="#206">206</a>         <strong>protected</strong> <strong>void</strong> parseDefineFont(InStream in) throws IOException {<a name="207" href="#207">207</a>             <em class="comment">// DO NOTHING - no URLs to be found in font</em><a name="208" href="#208">208</a>         }<a name="209" href="#209">209</a> <a name="210" href="#210">210</a>         <strong>protected</strong> <strong>void</strong> parseDefineJPEG2(InStream in, <strong>int</strong> length) throws IOException {<a name="211" href="#211">211</a>             <em class="comment">// DO NOTHING - no URLs to be found in jpeg</em><a name="212" href="#212">212</a>         }<a name="213" href="#213">213</a> <a name="214" href="#214">214</a>         <strong>protected</strong> <strong>void</strong> parseDefineJPEGTables(InStream in) throws IOException {<a name="215" href="#215">215</a>             <em class="comment">// DO NOTHING - no URLs to be found in jpeg</em><a name="216" href="#216">216</a>         }<a name="217" href="#217">217</a> <a name="218" href="#218">218</a>         <strong>protected</strong> <strong>void</strong> parseDefineShape(<strong>int</strong> type, InStream in) throws IOException {<a name="219" href="#219">219</a>             <em class="comment">// DO NOTHING - no URLs to be found in shape</em><a name="220" href="#220">220</a>         }<a name="221" href="#221">221</a> <a name="222" href="#222">222</a>         <strong>protected</strong> <strong>void</strong> parseDefineSound(InStream in) throws IOException {<a name="223" href="#223">223</a>             <em class="comment">// DO NOTHING - no URLs to be found in sound</em><a name="224" href="#224">224</a>         }<a name="225" href="#225">225</a> <a name="226" href="#226">226</a>         <strong>protected</strong> <strong>void</strong> parseFontInfo(InStream in, <strong>int</strong> length, <strong>boolean</strong> isFI2) throws IOException {<a name="227" href="#227">227</a>             <em class="comment">// DO NOTHING - no URLs to be found in font info</em><a name="228" href="#228">228</a>         }<a name="229" href="#229">229</a> <a name="230" href="#230">230</a>         <strong>protected</strong> <strong>void</strong> parseDefineFont2(InStream in) throws IOException {<a name="231" href="#231">231</a>             <em class="comment">// DO NOTHING - no URLs to be found in bits</em><a name="232" href="#232">232</a>         }<a name="233" href="#233">233</a>     }<a name="234" href="#234">234</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 + -