📄 extractorcss.html
字号:
<a name="93" href="#93">93</a> <em>/**<em>*</em></em><a name="94" href="#94">94</a> <em> * @param curi Crawl URI to process.</em><a name="95" href="#95">95</a> <em> */</em><a name="96" href="#96">96</a> <strong>public</strong> <strong>void</strong> extract(<a href="../../../../org/archive/crawler/datamodel/CrawlURI.html">CrawlURI</a> curi) {<a name="97" href="#97">97</a> <strong>if</strong> (!isHttpTransactionContentToProcess(curi)) {<a name="98" href="#98">98</a> <strong>return</strong>;<a name="99" href="#99">99</a> }<a name="100" href="#100">100</a> String mimeType = curi.getContentType();<a name="101" href="#101">101</a> <strong>if</strong> (mimeType == <strong>null</strong>) {<a name="102" href="#102">102</a> <strong>return</strong>;<a name="103" href="#103">103</a> }<a name="104" href="#104">104</a> <strong>if</strong> ((mimeType.toLowerCase().indexOf(<span class="string">"css"</span>) < 0) &&<a name="105" href="#105">105</a> (!curi.toString().toLowerCase().endsWith(<span class="string">".css"</span>))) {<a name="106" href="#106">106</a> <strong>return</strong>;<a name="107" href="#107">107</a> }<a name="108" href="#108">108</a> <strong>this</strong>.numberOfCURIsHandled++;<a name="109" href="#109">109</a> <a name="110" href="#110">110</a> <a href="../../../../org/archive/io/ReplayCharSequence.html">ReplayCharSequence</a> cs = <strong>null</strong>;<a name="111" href="#111">111</a> <strong>try</strong> {<a name="112" href="#112">112</a> cs = curi.getHttpRecorder().getReplayCharSequence();<a name="113" href="#113">113</a> } <strong>catch</strong> (IOException e) {<a name="114" href="#114">114</a> logger.severe(<span class="string">"Failed getting ReplayCharSequence: "</span> + e.getMessage());<a name="115" href="#115">115</a> }<a name="116" href="#116">116</a> <strong>if</strong> (cs == <strong>null</strong>) {<a name="117" href="#117">117</a> logger.warning(<span class="string">"Failed getting ReplayCharSequence: "</span> +<a name="118" href="#118">118</a> curi.toString());<a name="119" href="#119">119</a> <strong>return</strong>;<a name="120" href="#120">120</a> }<a name="121" href="#121">121</a> <a name="122" href="#122">122</a> <em class="comment">// We have a ReplayCharSequence open. Wrap all in finally so we</em><a name="123" href="#123">123</a> <em class="comment">// for sure close it before we leave.</em><a name="124" href="#124">124</a> <strong>try</strong> {<a name="125" href="#125">125</a> <strong>this</strong>.numberOfLinksExtracted +=<a name="126" href="#126">126</a> processStyleCode(curi, cs, getController());<a name="127" href="#127">127</a> <em class="comment">// Set flag to indicate that link extraction is completed.</em><a name="128" href="#128">128</a> curi.linkExtractorFinished();<a name="129" href="#129">129</a> } <strong>finally</strong> {<a name="130" href="#130">130</a> <strong>if</strong> (cs != <strong>null</strong>) {<a name="131" href="#131">131</a> <strong>try</strong> {<a name="132" href="#132">132</a> cs.close();<a name="133" href="#133">133</a> } <strong>catch</strong> (IOException ioe) {<a name="134" href="#134">134</a> logger.warning(TextUtils.exceptionToString(<a name="135" href="#135">135</a> <span class="string">"Failed close of ReplayCharSequence."</span>, ioe));<a name="136" href="#136">136</a> }<a name="137" href="#137">137</a> }<a name="138" href="#138">138</a> }<a name="139" href="#139">139</a> }<a name="140" href="#140">140</a> <a name="141" href="#141">141</a> <strong>public</strong> <strong>static</strong> <strong>long</strong> processStyleCode(<a href="../../../../org/archive/crawler/datamodel/CrawlURI.html">CrawlURI</a> curi, CharSequence cs,<a name="142" href="#142">142</a> <a href="../../../../org/archive/crawler/framework/CrawlController.html">CrawlController</a> controller) {<a name="143" href="#143">143</a> <strong>long</strong> foundLinks = 0;<a name="144" href="#144">144</a> Matcher uris = <strong>null</strong>;<a name="145" href="#145">145</a> String cssUri;<a name="146" href="#146">146</a> <strong>try</strong> {<a name="147" href="#147">147</a> uris = TextUtils.getMatcher(CSS_URI_EXTRACTOR, cs);<a name="148" href="#148">148</a> <strong>while</strong> (uris.find()) {<a name="149" href="#149">149</a> cssUri = uris.group(2);<a name="150" href="#150">150</a> <em class="comment">// TODO: Escape more HTML Entities.</em><a name="151" href="#151">151</a> cssUri = TextUtils.replaceAll(ESCAPED_AMP, cssUri, <span class="string">"&"</span>);<a name="152" href="#152">152</a> <em class="comment">// Remove backslashes when used as escape character in CSS URL</em><a name="153" href="#153">153</a> cssUri = TextUtils.replaceAll(CSS_BACKSLASH_ESCAPE, cssUri,<a name="154" href="#154">154</a> <span class="string">"$1"</span>);<a name="155" href="#155">155</a> foundLinks++;<a name="156" href="#156">156</a> <strong>try</strong> {<a name="157" href="#157">157</a> curi.createAndAddLinkRelativeToBase(cssUri,Link.EMBED_MISC,<a name="158" href="#158">158</a> Link.EMBED_HOP);<a name="159" href="#159">159</a> } <strong>catch</strong> (URIException e) {<a name="160" href="#160">160</a> <em class="comment">// There may not be a controller (e.g. If we're being run</em><a name="161" href="#161">161</a> <em class="comment">// by the extractor tool).</em><a name="162" href="#162">162</a> <strong>if</strong> (controller != <strong>null</strong>) {<a name="163" href="#163">163</a> controller.logUriError(e, curi.getUURI(), cssUri);<a name="164" href="#164">164</a> } <strong>else</strong> {<a name="165" href="#165">165</a> logger.info(curi + <span class="string">", "</span> + cssUri + <span class="string">": "</span> +<a name="166" href="#166">166</a> e.getMessage());<a name="167" href="#167">167</a> }<a name="168" href="#168">168</a> }<a name="169" href="#169">169</a> }<a name="170" href="#170">170</a> } <strong>catch</strong> (StackOverflowError e) {<a name="171" href="#171">171</a> DevUtils.warnHandle(e, <span class="string">"ExtractorCSS StackOverflowError"</span>);<a name="172" href="#172">172</a> } <strong>finally</strong> {<a name="173" href="#173">173</a> TextUtils.recycleMatcher(uris);<a name="174" href="#174">174</a> }<a name="175" href="#175">175</a> <strong>return</strong> foundLinks;<a name="176" href="#176">176</a> }<a name="177" href="#177">177</a> <a name="178" href="#178">178</a> <strong>public</strong> String report() {<a name="179" href="#179">179</a> StringBuffer ret = <strong>new</strong> StringBuffer();<a name="180" href="#180">180</a> ret.append(<span class="string">"Processor: org.archive.crawler.extractor.ExtractorCSS\n"</span>);<a name="181" href="#181">181</a> ret.append(<span class="string">" Function: Link extraction on Cascading Style Sheets (.css)\n"</span>);<a name="182" href="#182">182</a> ret.append(<span class="string">" CrawlURIs handled: "</span> + numberOfCURIsHandled + <span class="string">"\n"</span>);<a name="183" href="#183">183</a> ret.append(<span class="string">" Links extracted: "</span> + numberOfLinksExtracted + <span class="string">"\n\n"</span>);<a name="184" href="#184">184</a> <a name="185" href="#185">185</a> <strong>return</strong> ret.toString();<a name="186" href="#186">186</a> }<a name="187" href="#187">187</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 + -