📄 robotsexclusionpolicy.html
字号:
<a name="128" href="#128">128</a> String ua = (String)iter.next();<a name="129" href="#129">129</a> <strong>if</strong> (userAgent.indexOf(ua)>-1) {<a name="130" href="#130">130</a> userAgentsToTest.add(ua);<a name="131" href="#131">131</a> <strong>break</strong>;<a name="132" href="#132">132</a> }<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> }<a name="137" href="#137">137</a> <a name="138" href="#138">138</a> <strong>public</strong> <a href="../../../../org/archive/crawler/datamodel/RobotsExclusionPolicy.html">RobotsExclusionPolicy</a>(<strong>int</strong> type) {<a name="139" href="#139">139</a> <strong>this</strong>(<strong>null</strong>, <strong>null</strong>, <strong>null</strong>, <strong>null</strong>);<a name="140" href="#140">140</a> <strong>this</strong>.type = type;<a name="141" href="#141">141</a> }<a name="142" href="#142">142</a> <a name="143" href="#143">143</a> <strong>public</strong> <strong>boolean</strong> disallows(<a href="../../../../org/archive/crawler/datamodel/CrawlURI.html">CrawlURI</a> curi, String userAgent) {<a name="144" href="#144">144</a> <strong>if</strong> (<strong>this</strong> == ALLOWALL)<a name="145" href="#145">145</a> <strong>return</strong> false;<a name="146" href="#146">146</a> <strong>if</strong> (<strong>this</strong> == DENYALL)<a name="147" href="#147">147</a> <strong>return</strong> <strong>true</strong>;<a name="148" href="#148">148</a> <a name="149" href="#149">149</a> <em class="comment">// In the common case with policy=Classic, the useragent is remembered from uri to uri on</em><a name="150" href="#150">150</a> <em class="comment">// the same server</em><a name="151" href="#151">151</a> <strong>if</strong>((honoringPolicy.isType(curi, RobotsHonoringPolicy.CLASSIC) <a name="152" href="#152">152</a> || honoringPolicy.isType(curi, RobotsHonoringPolicy.CUSTOM))<a name="153" href="#153">153</a> && (lastUsedUserAgent == <strong>null</strong><a name="154" href="#154">154</a> || !lastUsedUserAgent.equals(userAgent))) {<a name="155" href="#155">155</a> <a name="156" href="#156">156</a> lastUsedUserAgent = userAgent;<a name="157" href="#157">157</a> userAgentsToTest = <strong>new</strong> ArrayList();<a name="158" href="#158">158</a> Iterator iter = userAgents.iterator();<a name="159" href="#159">159</a> <strong>while</strong> ( iter.hasNext() ) {<a name="160" href="#160">160</a> String ua = (String)iter.next();<a name="161" href="#161">161</a> <strong>if</strong> (userAgent.indexOf(ua)>-1) {<a name="162" href="#162">162</a> userAgentsToTest.add(ua);<a name="163" href="#163">163</a> <strong>break</strong>; <em class="comment">// consider no more sections</em><a name="164" href="#164">164</a> }<a name="165" href="#165">165</a> }<a name="166" href="#166">166</a> }<a name="167" href="#167">167</a> <a name="168" href="#168">168</a> <strong>boolean</strong> disallow = false;<a name="169" href="#169">169</a> <strong>boolean</strong> examined = false;<a name="170" href="#170">170</a> String ua = <strong>null</strong>;<a name="171" href="#171">171</a> <a name="172" href="#172">172</a> <em class="comment">// Go thru list of all user agents we might act as</em><a name="173" href="#173">173</a> Iterator uas = userAgentsToTest.iterator();<a name="174" href="#174">174</a> <strong>while</strong>(uas.hasNext() && examined == false) {<a name="175" href="#175">175</a> disallow = false;<a name="176" href="#176">176</a> ua = (String) uas.next();<a name="177" href="#177">177</a> Iterator dis = ((List) disallows.get(ua)).iterator();<a name="178" href="#178">178</a> <a name="179" href="#179">179</a> <em class="comment">// Check if the current user agent is allowed to crawl</em><a name="180" href="#180">180</a> <strong>while</strong>(dis.hasNext() && examined == false && disallow == false) {<a name="181" href="#181">181</a> String disallowedPath = (String) dis.next();<a name="182" href="#182">182</a> <strong>if</strong>(disallowedPath.length() == 0) {<a name="183" href="#183">183</a> <em class="comment">// blanket allow</em><a name="184" href="#184">184</a> examined = <strong>true</strong>;<a name="185" href="#185">185</a> disallow = false;<a name="186" href="#186">186</a> <strong>break</strong>;<a name="187" href="#187">187</a> }<a name="188" href="#188">188</a> <strong>try</strong> {<a name="189" href="#189">189</a> String p = curi.getUURI().getPathQuery();<a name="190" href="#190">190</a> <strong>if</strong> (p != <strong>null</strong> && p.startsWith(disallowedPath) ) {<a name="191" href="#191">191</a> <em class="comment">// the user agent tested isn't allowed to get this uri</em><a name="192" href="#192">192</a> disallow = <strong>true</strong>;<a name="193" href="#193">193</a> }<a name="194" href="#194">194</a> }<a name="195" href="#195">195</a> <strong>catch</strong> (URIException e) {<a name="196" href="#196">196</a> logger.log(Level.SEVERE,<span class="string">"Failed getPathQuery from "</span> + curi, e);<a name="197" href="#197">197</a> }<a name="198" href="#198">198</a> }<a name="199" href="#199">199</a> <strong>if</strong>(disallow == false) {<a name="200" href="#200">200</a> <em class="comment">// the user agent tested is allowed</em><a name="201" href="#201">201</a> examined = <strong>true</strong>;<a name="202" href="#202">202</a> }<a name="203" href="#203">203</a> }<a name="204" href="#204">204</a> <a name="205" href="#205">205</a> <em class="comment">// Are we supposed to masquerade as the user agent to which restrictions</em><a name="206" href="#206">206</a> <em class="comment">// we follow?</em><a name="207" href="#207">207</a> <strong>if</strong>(honoringPolicy.shouldMasquerade(curi) && ua != <strong>null</strong> && !ua.equals(<span class="string">""</span>)) {<a name="208" href="#208">208</a> curi.setUserAgent(ua);<a name="209" href="#209">209</a> }<a name="210" href="#210">210</a> <strong>return</strong> disallow;<a name="211" href="#211">211</a> }<a name="212" href="#212">212</a> <a name="213" href="#213">213</a> <em class="comment">// Methods for object serialization.</em><a name="214" href="#214">214</a> <a name="215" href="#215">215</a> <em>/**<em>* If object is DENYALL or ALLOWALL, only the object identity and type</em></em><a name="216" href="#216">216</a> <em> * is written in the serialization stream.</em><a name="217" href="#217">217</a> <em> *</em><a name="218" href="#218">218</a> <em> * @param stream the serialization stream.</em><a name="219" href="#219">219</a> <em> * @throws IOException </em><a name="220" href="#220">220</a> <em> */</em><a name="221" href="#221">221</a> <strong>private</strong> <strong>void</strong> writeObject(ObjectOutputStream stream) throws IOException {<a name="222" href="#222">222</a> stream.writeInt(type);<a name="223" href="#223">223</a> <strong>if</strong> (type == NORMAL_TYPE) {<a name="224" href="#224">224</a> stream.defaultWriteObject();<a name="225" href="#225">225</a> }<a name="226" href="#226">226</a> }<a name="227" href="#227">227</a> <a name="228" href="#228">228</a> <em>/**<em>* If object is DENYALL or ALLOWALL, only the object identity and type</em></em><a name="229" href="#229">229</a> <em> * is read from the serialization stream.</em><a name="230" href="#230">230</a> <em> *</em><a name="231" href="#231">231</a> <em> * @param stream the serialization stream.</em><a name="232" href="#232">232</a> <em> * @throws IOException </em><a name="233" href="#233">233</a> <em> * @throws ClassNotFoundException </em><a name="234" href="#234">234</a> <em> */</em><a name="235" href="#235">235</a> <strong>private</strong> <strong>void</strong> readObject(ObjectInputStream stream)<a name="236" href="#236">236</a> throws IOException, ClassNotFoundException {<a name="237" href="#237">237</a> type = stream.readInt();<a name="238" href="#238">238</a> <strong>if</strong> (type == NORMAL_TYPE) {<a name="239" href="#239">239</a> stream.defaultReadObject();<a name="240" href="#240">240</a> }<a name="241" href="#241">241</a> }<a name="242" href="#242">242</a> <a name="243" href="#243">243</a> <em>/**<em>* If object is DENYALL or ALLOWALL, the object is replaced by constants</em></em><a name="244" href="#244">244</a> <em> * so that check for object equality works.</em><a name="245" href="#245">245</a> <em> * @return Object.</em><a name="246" href="#246">246</a> <em> */</em><a name="247" href="#247">247</a> <strong>private</strong> Object readResolve() {<a name="248" href="#248">248</a> <strong>if</strong> (type == NORMAL_TYPE) {<a name="249" href="#249">249</a> <strong>return</strong> <strong>this</strong>;<a name="250" href="#250">250</a> } <strong>else</strong> <strong>if</strong> (type == ALLOWALL_TYPE) {<a name="251" href="#251">251</a> <strong>return</strong> ALLOWALL;<a name="252" href="#252">252</a> } <strong>else</strong> <strong>if</strong> (type == DENYALL_TYPE) {<a name="253" href="#253">253</a> <strong>return</strong> DENYALL;<a name="254" href="#254">254</a> }<a name="255" href="#255">255</a> <strong>return</strong> <strong>null</strong>;<a name="256" href="#256">256</a> }<a name="257" href="#257">257</a> <a name="258" href="#258">258</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 + -