preconditionenforcer.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="120" href="#120">120</a> 
<a name="121" href="#121">121</a>         <strong>if</strong> (considerRobotsPreconditions(curi)) {
<a name="122" href="#122">122</a>             <strong>return</strong>;
<a name="123" href="#123">123</a>         }
<a name="124" href="#124">124</a> 
<a name="125" href="#125">125</a>         <strong>if</strong> (!curi.isPrerequisite() &amp;&amp; credentialPrecondition(curi)) {
<a name="126" href="#126">126</a>             <strong>return</strong>;
<a name="127" href="#127">127</a>         }
<a name="128" href="#128">128</a> 
<a name="129" href="#129">129</a>         <em class="comment">// OK, it's allowed</em>
<a name="130" href="#130">130</a> 
<a name="131" href="#131">131</a>         <em class="comment">// For all curis that will in fact be fetched, set appropriate delays.</em>
<a name="132" href="#132">132</a>         <em class="comment">// TODO: SOMEDAY: allow per-host, per-protocol, etc. factors</em>
<a name="133" href="#133">133</a>         <em class="comment">// curi.setDelayFactor(getDelayFactorFor(curi));</em>
<a name="134" href="#134">134</a>         <em class="comment">// curi.setMinimumDelay(getMinimumDelayFor(curi));</em>
<a name="135" href="#135">135</a> 
<a name="136" href="#136">136</a>         <strong>return</strong>;
<a name="137" href="#137">137</a>     }
<a name="138" href="#138">138</a> 
<a name="139" href="#139">139</a>     <em>/**<em>*</em></em>
<a name="140" href="#140">140</a> <em>     * Consider the robots precondition.</em>
<a name="141" href="#141">141</a> <em>     *</em>
<a name="142" href="#142">142</a> <em>     * @param curi CrawlURI we're checking for any required preconditions.</em>
<a name="143" href="#143">143</a> <em>     * @return True, if this &lt;code>curi&lt;/code> has a precondition or processing</em>
<a name="144" href="#144">144</a> <em>     *         should be terminated for some other reason.  False if</em>
<a name="145" href="#145">145</a> <em>     *         we can precede to process this url.</em>
<a name="146" href="#146">146</a> <em>     */</em>
<a name="147" href="#147">147</a>     <strong>private</strong> <strong>boolean</strong> considerRobotsPreconditions(<a href="../../../../org/archive/crawler/datamodel/CrawlURI.html">CrawlURI</a> curi) {
<a name="148" href="#148">148</a>         <em class="comment">// treat /robots.txt fetches specially</em>
<a name="149" href="#149">149</a>         <a href="../../../../org/archive/net/UURI.html">UURI</a> uuri = curi.getUURI();
<a name="150" href="#150">150</a>         <strong>try</strong> {
<a name="151" href="#151">151</a>             <strong>if</strong> (uuri != <strong>null</strong> &amp;&amp; uuri.getPath() != <strong>null</strong> &amp;&amp;
<a name="152" href="#152">152</a>                     curi.getUURI().getPath().equals(<span class="string">"/robots.txt"</span>)) {
<a name="153" href="#153">153</a>                 <em class="comment">// allow processing to continue</em>
<a name="154" href="#154">154</a>                 curi.setPrerequisite(<strong>true</strong>);
<a name="155" href="#155">155</a>                 <strong>return</strong> false;
<a name="156" href="#156">156</a>             }
<a name="157" href="#157">157</a>         }
<a name="158" href="#158">158</a>         <strong>catch</strong> (URIException e) {
<a name="159" href="#159">159</a>             logger.severe(<span class="string">"Failed get of path for "</span> + curi);
<a name="160" href="#160">160</a>         }
<a name="161" href="#161">161</a>         <em class="comment">// require /robots.txt if not present</em>
<a name="162" href="#162">162</a>         <strong>if</strong> (isRobotsExpired(curi)) {
<a name="163" href="#163">163</a>         	<em class="comment">// Need to get robots</em>
<a name="164" href="#164">164</a>             <strong>if</strong> (logger.isLoggable(Level.FINE)) {
<a name="165" href="#165">165</a>                 logger.fine( <span class="string">"No valid robots for "</span> +
<a name="166" href="#166">166</a>                     getController().getServerCache().getServerFor(curi) +
<a name="167" href="#167">167</a>                     <span class="string">"; deferring "</span> + curi);
<a name="168" href="#168">168</a>             }
<a name="169" href="#169">169</a> 
<a name="170" href="#170">170</a>             <em class="comment">// Robots expired - should be refetched even though its already</em>
<a name="171" href="#171">171</a>             <em class="comment">// crawled.</em>
<a name="172" href="#172">172</a>             <strong>try</strong> {
<a name="173" href="#173">173</a>                 String prereq = curi.getUURI().resolve(<span class="string">"/robots.txt"</span>).toString();
<a name="174" href="#174">174</a>                 curi.markPrerequisite(prereq,
<a name="175" href="#175">175</a>                     getController().getPostprocessorChain());
<a name="176" href="#176">176</a>             }
<a name="177" href="#177">177</a>             <strong>catch</strong> (URIException e1) {
<a name="178" href="#178">178</a>                 logger.severe(<span class="string">"Failed resolve using "</span> + curi);
<a name="179" href="#179">179</a>                 <strong>throw</strong> <strong>new</strong> RuntimeException(e1); <em class="comment">// shouldn't ever happen</em>
<a name="180" href="#180">180</a>             }
<a name="181" href="#181">181</a>             <strong>return</strong> <strong>true</strong>;
<a name="182" href="#182">182</a>         }
<a name="183" href="#183">183</a>         <em class="comment">// test against robots.txt if available</em>
<a name="184" href="#184">184</a>         <a href="../../../../org/archive/crawler/datamodel/CrawlServer.html">CrawlServer</a> cs = getController().getServerCache().getServerFor(curi);
<a name="185" href="#185">185</a>         <strong>if</strong>(cs.isValidRobots()){
<a name="186" href="#186">186</a>             String ua = getController().getOrder().getUserAgent(curi);
<a name="187" href="#187">187</a>             <strong>if</strong>(cs.getRobots().disallows(curi, ua)) {
<a name="188" href="#188">188</a>                 <strong>if</strong>(((Boolean)getUncheckedAttribute(curi,ATTR_CALCULATE_ROBOTS_ONLY)).booleanValue() == <strong>true</strong>) {
<a name="189" href="#189">189</a>                     <em class="comment">// annotate URI as excluded, but continue to process normally</em>
<a name="190" href="#190">190</a>                     curi.addAnnotation(<span class="string">"robotExcluded"</span>);
<a name="191" href="#191">191</a>                     <strong>return</strong> false; 
<a name="192" href="#192">192</a>                 }
<a name="193" href="#193">193</a>                 <em class="comment">// mark as precluded; in FetchHTTP, this will</em>
<a name="194" href="#194">194</a>                 <em class="comment">// prevent fetching and cause a skip to the end</em>
<a name="195" href="#195">195</a>                 <em class="comment">// of processing (unless an intervening processor</em>
<a name="196" href="#196">196</a>                 <em class="comment">// overrules)</em>
<a name="197" href="#197">197</a>                 curi.setFetchStatus(S_ROBOTS_PRECLUDED);
<a name="198" href="#198">198</a>                 curi.putString(<span class="string">"error"</span>,<span class="string">"robots.txt exclusion"</span>);
<a name="199" href="#199">199</a>                 logger.fine(<span class="string">"robots.txt precluded "</span> + curi);
<a name="200" href="#200">200</a>                 <strong>return</strong> <strong>true</strong>;
<a name="201" href="#201">201</a>             }
<a name="202" href="#202">202</a>             <strong>return</strong> false;
<a name="203" href="#203">203</a>         }
<a name="204" href="#204">204</a>         <em class="comment">// No valid robots found => Attempt to get robots.txt failed</em>
<a name="205" href="#205">205</a>         curi.skipToProcessorChain(getController().getPostprocessorChain());
<a name="206" href="#206">206</a>         curi.setFetchStatus(S_ROBOTS_PREREQUISITE_FAILURE);
<a name="207" href="#207">207</a>         curi.putString(<span class="string">"error"</span>,<span class="string">"robots.txt prerequisite failed"</span>);
<a name="208" href="#208">208</a>         <strong>if</strong> (logger.isLoggable(Level.FINE)) {
<a name="209" href="#209">209</a>             logger.fine(<span class="string">"robots.txt prerequisite failed "</span> + curi);
<a name="210" href="#210">210</a>         }
<a name="211" href="#211">211</a>         <strong>return</strong> <strong>true</strong>;
<a name="212" href="#212">212</a>     }
<a name="213" href="#213">213</a> 
<a name="214" href="#214">214</a>     <em>/**<em>*</em></em>
<a name="215" href="#215">215</a> <em>     * @param curi CrawlURI whose dns prerequisite we're to check.</em>
<a name="216" href="#216">216</a> <em>     * @return true if no further processing in this module should occur</em>
<a name="217" href="#217">217</a> <em>     */</em>
<a name="218" href="#218">218</a>     <strong>private</strong> <strong>boolean</strong> considerDnsPreconditions(<a href="../../../../org/archive/crawler/datamodel/CrawlURI.html">CrawlURI</a> curi) {
<a name="219" href="#219">219</a>         <strong>if</strong>(curi.getUURI().getScheme().equals(<span class="string">"dns"</span>)){
<a name="220" href="#220">220</a>             <em class="comment">// DNS URIs never have a DNS precondition</em>
<a name="221" href="#221">221</a>             curi.setPrerequisite(<strong>true</strong>);
<a name="222" href="#222">222</a>             <strong>return</strong> false; 
<a name="223" href="#223">223</a>         }
<a name="224" href="#224">224</a>         
<a name="225" href="#225">225</a>         <a href="../../../../org/archive/crawler/datamodel/CrawlServer.html">CrawlServer</a> cs = getController().getServerCache().getServerFor(curi);
<a name="226" href="#226">226</a>         <strong>if</strong>(cs == <strong>null</strong>) {
<a name="227" href="#227">227</a>             curi.setFetchStatus(S_UNFETCHABLE_URI);
<a name="228" href="#228">228</a>             curi.skipToProcessorChain(getController().getPostprocessorChain());
<a name="229" href="#229">229</a>             <strong>return</strong> <strong>true</strong>;
<a name="230" href="#230">230</a>         }
<a name="231" href="#231">231</a> 
<a name="232" href="#232">232</a>         <em class="comment">// If we've done a dns lookup and it didn't resolve a host</em>
<a name="233" href="#233">233</a>         <em class="comment">// cancel further fetch-processing of this URI, because</em>
<a name="234" href="#234">234</a>         <em class="comment">// the domain is unresolvable</em>
<a name="235" href="#235">235</a>         <a href="../../../../org/archive/crawler/datamodel/CrawlHost.html">CrawlHost</a> ch = getController().getServerCache().getHostFor(curi);
<a name="236" href="#236">236</a>         <strong>if</strong> (ch == <strong>null</strong> || ch.hasBeenLookedUp() &amp;&amp; ch.getIP() == <strong>null</strong>) {
<a name="237" href="#237">237</a>             <strong>if</strong> (logger.isLoggable(Level.FINE)) {
<a name="238" href="#238">238</a>                 logger.fine( <span class="string">"no dns for "</span> + ch +
<a name="239" href="#239">239</a>                     <span class="string">" cancelling processing for CrawlURI "</span> + curi.toString());
<a name="240" href="#240">240</a>             }
<a name="241" href="#241">241</a>             curi.setFetchStatus(S_DOMAIN_PREREQUISITE_FAILURE);
<a name="242" href="#242">242</a>             curi.skipToProcessorChain(getController().getPostprocessorChain());
<a name="243" href="#243">243</a>             <strong>return</strong> <strong>true</strong>;
<a name="244" href="#244">244</a>         }
<a name="245" href="#245">245</a> 
<a name="246" href="#246">246</a>         <em class="comment">// If we haven't done a dns lookup  and this isn't a dns uri</em>
<a name="247" href="#247">247</a>         <em class="comment">// shoot that off and defer further processing</em>