⭐ 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

📄 charsequencelinkextractor.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="97" href="#97">97</a>      <strong>public</strong> <a href="../../../org/archive/crawler/extractor/Link.html">Link</a> nextLink() {<a name="98" href="#98">98</a>          <strong>if</strong>(!hasNext()) {<a name="99" href="#99">99</a>              <strong>throw</strong> <strong>new</strong> NoSuchElementException();<a name="100" href="#100">100</a>         }<a name="101" href="#101">101</a>         <em class="comment">// next will have been filled with at least one item</em><a name="102" href="#102">102</a>         <strong>return</strong> (Link) next.removeFirst();<a name="103" href="#103">103</a>     }<a name="104" href="#104">104</a> <a name="105" href="#105">105</a>     <em>/**<em>*</em></em><a name="106" href="#106">106</a> <em>     * Discard all state. Another setup() is required to use again.</em><a name="107" href="#107">107</a> <em>     */</em><a name="108" href="#108">108</a>     <strong>public</strong> <strong>void</strong> reset() {<a name="109" href="#109">109</a>         base = <strong>null</strong>;<a name="110" href="#110">110</a>         source = <strong>null</strong>;<a name="111" href="#111">111</a>         sourceContent = <strong>null</strong>; <em class="comment">// TODO: discard other resources</em><a name="112" href="#112">112</a>     }<a name="113" href="#113">113</a> <a name="114" href="#114">114</a>     <em class="comment">/*<em class="comment"> (non-Javadoc)</em></em><a name="115" href="#115">115</a> <em class="comment">     * @see java.util.Iterator#hasNext()</em><a name="116" href="#116">116</a> <em class="comment">     */</em><a name="117" href="#117">117</a>     <strong>public</strong> <strong>boolean</strong> hasNext() {<a name="118" href="#118">118</a>         <strong>if</strong> (!next.isEmpty()) {<a name="119" href="#119">119</a>             <strong>return</strong> <strong>true</strong>;<a name="120" href="#120">120</a>         }<a name="121" href="#121">121</a>         <strong>return</strong> findNextLink();<a name="122" href="#122">122</a>     }<a name="123" href="#123">123</a> <a name="124" href="#124">124</a>     <em>/**<em>*</em></em><a name="125" href="#125">125</a> <em>     * Scan to the next link(s), if any, loading it into the next buffer.</em><a name="126" href="#126">126</a> <em>     *</em><a name="127" href="#127">127</a> <em>     * @return true if any links are found/available, false otherwise</em><a name="128" href="#128">128</a> <em>     */</em><a name="129" href="#129">129</a>     <strong>abstract</strong> <strong>protected</strong> <strong>boolean</strong> findNextLink();<a name="130" href="#130">130</a> <a name="131" href="#131">131</a>     <em class="comment">/*<em class="comment"> (non-Javadoc)</em></em><a name="132" href="#132">132</a> <em class="comment">     * @see java.util.Iterator#next()</em><a name="133" href="#133">133</a> <em class="comment">     */</em><a name="134" href="#134">134</a>     <strong>public</strong> Object next() {<a name="135" href="#135">135</a>         <strong>return</strong> nextLink();<a name="136" href="#136">136</a>     }<a name="137" href="#137">137</a> <a name="138" href="#138">138</a>     <em class="comment">/*<em class="comment"> (non-Javadoc)</em></em><a name="139" href="#139">139</a> <em class="comment">     * @see java.util.Iterator#remove()</em><a name="140" href="#140">140</a> <em class="comment">     */</em><a name="141" href="#141">141</a>     <strong>public</strong> <strong>void</strong> remove() {<a name="142" href="#142">142</a>         <strong>throw</strong> <strong>new</strong> UnsupportedOperationException();<a name="143" href="#143">143</a>     }<a name="144" href="#144">144</a> <a name="145" href="#145">145</a>     <em>/**<em>*</em></em><a name="146" href="#146">146</a> <em>     * @param content</em><a name="147" href="#147">147</a> <em>     * @param charset</em><a name="148" href="#148">148</a> <em>     * @return CharSequence obtained from stream in given charset</em><a name="149" href="#149">149</a> <em>     */</em><a name="150" href="#150">150</a>     <strong>protected</strong> CharSequence charSequenceFrom(InputStream content, Charset charset) {<a name="151" href="#151">151</a>         <em class="comment">// See if content InputStream can provide</em><a name="152" href="#152">152</a>         <strong>if</strong>(content instanceof <a href="../../../org/archive/extractor/CharSequenceProvider.html">CharSequenceProvider</a>) {<a name="153" href="#153">153</a>             <strong>return</strong> ((CharSequenceProvider)content).getCharSequence();<a name="154" href="#154">154</a>         }<a name="155" href="#155">155</a>         <em class="comment">// otherwise, create one</em><a name="156" href="#156">156</a>         <strong>return</strong> createCharSequenceFrom(content, charset);<a name="157" href="#157">157</a>     }<a name="158" href="#158">158</a> <a name="159" href="#159">159</a>     <em>/**<em>*</em></em><a name="160" href="#160">160</a> <em>     * @param content</em><a name="161" href="#161">161</a> <em>     * @param charset</em><a name="162" href="#162">162</a> <em>     * @return CharSequence built over given stream in given charset</em><a name="163" href="#163">163</a> <em>     */</em><a name="164" href="#164">164</a>     <strong>protected</strong> CharSequence createCharSequenceFrom(InputStream content, Charset charset) {<a name="165" href="#165">165</a>         <em class="comment">// TODO: implement</em><a name="166" href="#166">166</a>         <strong>return</strong> <strong>null</strong>;<a name="167" href="#167">167</a>         <em class="comment">// TODO: consider cleanup in reset()</em><a name="168" href="#168">168</a>     }<a name="169" href="#169">169</a> <a name="170" href="#170">170</a>     <em>/**<em>*</em></em><a name="171" href="#171">171</a> <em>     * Convenience method to do default extraction.</em><a name="172" href="#172">172</a> <em>     *</em><a name="173" href="#173">173</a> <em>     * @param content</em><a name="174" href="#174">174</a> <em>     * @param source</em><a name="175" href="#175">175</a> <em>     * @param base</em><a name="176" href="#176">176</a> <em>     * @param collector</em><a name="177" href="#177">177</a> <em>     * @param extractErrorListener</em><a name="178" href="#178">178</a> <em>     */</em><a name="179" href="#179">179</a>     <strong>public</strong> <strong>static</strong> <strong>void</strong> extract(CharSequence content, <a href="../../../org/archive/net/UURI.html">UURI</a> source, <a href="../../../org/archive/net/UURI.html">UURI</a> base,<a name="180" href="#180">180</a>             List collector, <a href="../../../org/archive/extractor/ExtractErrorListener.html">ExtractErrorListener</a> extractErrorListener) {<a name="181" href="#181">181</a>         <em class="comment">// TODO: arrange for inheritance of prefs... eg when HTML includes JS</em><a name="182" href="#182">182</a>         <em class="comment">// includes HTML, have inner HTML follow robots, etc from outer</em><a name="183" href="#183">183</a>         <a href="../../../org/archive/extractor/CharSequenceLinkExtractor.html">CharSequenceLinkExtractor</a> extractor = newDefaultInstance();<a name="184" href="#184">184</a>         extractor.setup(source, base, content, extractErrorListener);<a name="185" href="#185">185</a>         <strong>while</strong> (extractor.hasNext()) {<a name="186" href="#186">186</a>             collector.add(extractor.nextLink());<a name="187" href="#187">187</a>         }<a name="188" href="#188">188</a>         extractor.reset();<a name="189" href="#189">189</a>     }<a name="190" href="#190">190</a> <a name="191" href="#191">191</a>     <strong>protected</strong> <strong>static</strong> <a href="../../../org/archive/extractor/CharSequenceLinkExtractor.html">CharSequenceLinkExtractor</a> newDefaultInstance() {<a name="192" href="#192">192</a>         <em class="comment">// override in subclasses</em><a name="193" href="#193">193</a>         <strong>return</strong> <strong>null</strong>;<a name="194" href="#194">194</a>     }<a name="195" href="#195">195</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 + -