📄 robotshonoringpolicy.html
字号:
<a name="108" href="#108">108</a> <strong>new</strong> Boolean(false)));<a name="109" href="#109">109</a> addElementToDefinition(<strong>new</strong> <a href="../../../../org/archive/crawler/settings/SimpleType.html">SimpleType</a>(ATTR_CUSTOM_ROBOTS,<a name="110" href="#110">110</a> <span class="string">"Custom robots to use if policy type is 'custom'. "</span> +<a name="111" href="#111">111</a> <span class="string">"Compose as if an actual robots.txt file."</span>, <a name="112" href="#112">112</a> <strong>new</strong> <a href="../../../../org/archive/crawler/settings/TextField.html">TextField</a>(<span class="string">""</span>)));<a name="113" href="#113">113</a> addElementToDefinition(<strong>new</strong> <a href="../../../../org/archive/crawler/settings/StringList.html">StringList</a>(ATTR_USER_AGENTS, <a name="114" href="#114">114</a> <span class="string">"Alternate user-agent values to consider using for "</span> +<a name="115" href="#115">115</a> <span class="string">"the 'most-favored-set' policy."</span>));<a name="116" href="#116">116</a> }<a name="117" href="#117">117</a> <a name="118" href="#118">118</a> <strong>public</strong> <a href="../../../../org/archive/crawler/datamodel/RobotsHonoringPolicy.html">RobotsHonoringPolicy</a>() {<a name="119" href="#119">119</a> <strong>this</strong>(ATTR_NAME);<a name="120" href="#120">120</a> }<a name="121" href="#121">121</a> <a name="122" href="#122">122</a> <em>/**<em>*</em></em><a name="123" href="#123">123</a> <em> * If policy-type is most favored crawler of set, then this method</em><a name="124" href="#124">124</a> <em> * gets a list of all useragents in that set.</em><a name="125" href="#125">125</a> <em> *</em><a name="126" href="#126">126</a> <em> * @return List of Strings with user agents</em><a name="127" href="#127">127</a> <em> */</em><a name="128" href="#128">128</a> <strong>public</strong> <a href="../../../../org/archive/crawler/settings/StringList.html">StringList</a> getUserAgents(<a href="../../../../org/archive/crawler/settings/CrawlerSettings.html">CrawlerSettings</a> settings) {<a name="129" href="#129">129</a> <strong>if</strong> (isType(settings, RobotsHonoringPolicy.MOST_FAVORED_SET)) {<a name="130" href="#130">130</a> <strong>try</strong> {<a name="131" href="#131">131</a> <strong>return</strong> (StringList) getAttribute(settings, ATTR_USER_AGENTS);<a name="132" href="#132">132</a> } <strong>catch</strong> (AttributeNotFoundException e) {<a name="133" href="#133">133</a> logger.severe(e.getMessage());<a name="134" href="#134">134</a> }<a name="135" href="#135">135</a> }<a name="136" href="#136">136</a> <strong>return</strong> <strong>null</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> * This method returns true if the crawler should masquerade as the user agent</em><a name="141" href="#141">141</a> <em> * which restrictions it opted to use.</em><a name="142" href="#142">142</a> <em> *</em><a name="143" href="#143">143</a> <em> * (Only relevant for policy-types: most-favored and most-favored-set).</em><a name="144" href="#144">144</a> <em> *</em><a name="145" href="#145">145</a> <em> * @return true if we should masquerade</em><a name="146" href="#146">146</a> <em> */</em><a name="147" href="#147">147</a> <strong>public</strong> <strong>boolean</strong> shouldMasquerade(<a href="../../../../org/archive/crawler/datamodel/CrawlURI.html">CrawlURI</a> curi) {<a name="148" href="#148">148</a> <strong>try</strong> {<a name="149" href="#149">149</a> <strong>return</strong> ((Boolean) getAttribute(curi, ATTR_MASQUERADE)).booleanValue();<a name="150" href="#150">150</a> } <strong>catch</strong> (AttributeNotFoundException e) {<a name="151" href="#151">151</a> logger.severe(e.getMessage());<a name="152" href="#152">152</a> <strong>return</strong> false;<a name="153" href="#153">153</a> }<a name="154" href="#154">154</a> }<a name="155" href="#155">155</a> <a name="156" href="#156">156</a> <em>/**<em>*</em></em><a name="157" href="#157">157</a> <em> * Get the supplied custom robots.txt</em><a name="158" href="#158">158</a> <em> *</em><a name="159" href="#159">159</a> <em> * @return String with content of alternate robots.txt</em><a name="160" href="#160">160</a> <em> */</em><a name="161" href="#161">161</a> <strong>public</strong> String getCustomRobots(<a href="../../../../org/archive/crawler/settings/CrawlerSettings.html">CrawlerSettings</a> settings) {<a name="162" href="#162">162</a> <strong>if</strong>(isType(settings, RobotsHonoringPolicy.CUSTOM)) {<a name="163" href="#163">163</a> <strong>try</strong> {<a name="164" href="#164">164</a> <strong>return</strong> getAttribute(settings, ATTR_CUSTOM_ROBOTS).toString();<a name="165" href="#165">165</a> } <strong>catch</strong> (AttributeNotFoundException e) {<a name="166" href="#166">166</a> logger.severe(e.getMessage());<a name="167" href="#167">167</a> }<a name="168" href="#168">168</a> }<a name="169" href="#169">169</a> <strong>return</strong> <strong>null</strong>;<a name="170" href="#170">170</a> }<a name="171" href="#171">171</a> <a name="172" href="#172">172</a> <em>/**<em>*</em></em><a name="173" href="#173">173</a> <em> * Get the policy-type.</em><a name="174" href="#174">174</a> <em> *</em><a name="175" href="#175">175</a> <em> * @see #CLASSIC</em><a name="176" href="#176">176</a> <em> * @see #IGNORE</em><a name="177" href="#177">177</a> <em> * @see #CUSTOM</em><a name="178" href="#178">178</a> <em> * @see #MOST_FAVORED</em><a name="179" href="#179">179</a> <em> * @see #MOST_FAVORED_SET</em><a name="180" href="#180">180</a> <em> *</em><a name="181" href="#181">181</a> <em> * @return policy type</em><a name="182" href="#182">182</a> <em> */</em><a name="183" href="#183">183</a> <strong>public</strong> <strong>int</strong> getType(Object context) {<a name="184" href="#184">184</a> <strong>int</strong> type = CLASSIC;<a name="185" href="#185">185</a> <strong>try</strong> {<a name="186" href="#186">186</a> String typeName = (String) getAttribute(context, <span class="string">"type"</span>);<a name="187" href="#187">187</a> <strong>if</strong>(typeName.equals(<span class="string">"classic"</span>)) {<a name="188" href="#188">188</a> type = RobotsHonoringPolicy.CLASSIC;<a name="189" href="#189">189</a> } <strong>else</strong> <strong>if</strong>(typeName.equals(<span class="string">"ignore"</span>)) {<a name="190" href="#190">190</a> type = RobotsHonoringPolicy.IGNORE;<a name="191" href="#191">191</a> } <strong>else</strong> <strong>if</strong>(typeName.equals(<span class="string">"custom"</span>)) {<a name="192" href="#192">192</a> type = RobotsHonoringPolicy.CUSTOM;<a name="193" href="#193">193</a> } <strong>else</strong> <strong>if</strong>(typeName.equals(<span class="string">"most-favored"</span>)) {<a name="194" href="#194">194</a> type = RobotsHonoringPolicy.MOST_FAVORED;<a name="195" href="#195">195</a> } <strong>else</strong> <strong>if</strong>(typeName.equals(<span class="string">"most-favored-set"</span>)) {<a name="196" href="#196">196</a> type = RobotsHonoringPolicy.MOST_FAVORED_SET;<a name="197" href="#197">197</a> } <strong>else</strong> {<a name="198" href="#198">198</a> <strong>throw</strong> <strong>new</strong> IllegalArgumentException();<a name="199" href="#199">199</a> }<a name="200" href="#200">200</a> } <strong>catch</strong> (AttributeNotFoundException e) {<a name="201" href="#201">201</a> logger.severe(e.getMessage());<a name="202" href="#202">202</a> }<a name="203" href="#203">203</a> <strong>return</strong> type;<a name="204" href="#204">204</a> }<a name="205" href="#205">205</a> <a name="206" href="#206">206</a> <em>/**<em>*</em></em><a name="207" href="#207">207</a> <em> * Check if policy is of a certain type.</em><a name="208" href="#208">208</a> <em> *</em><a name="209" href="#209">209</a> <em> * @param o An object that can be resolved into a settings object.</em><a name="210" href="#210">210</a> <em> * @param type the type to check against.</em><a name="211" href="#211">211</a> <em> * @return true if the policy is of the submitted type</em><a name="212" href="#212">212</a> <em> */</em><a name="213" href="#213">213</a> <strong>public</strong> <strong>boolean</strong> isType(Object o, <strong>int</strong> type) {<a name="214" href="#214">214</a> <strong>return</strong> type == getType(o);<a name="215" href="#215">215</a> }<a name="216" href="#216">216</a> <a name="217" href="#217">217</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 + -