实用软件资讯

火车头采集器：手动设置链接格式

未知佚名 / 2010-04-07

手动设置链接格式

手动连接格式是将需要的网址用参数来获得并组合成我们需要的网址。这个好处是处理网址那块有规律的网址很好处理，但要是没规律，和周围的一样的话，就不好处理了。我们以http://www.admin5.com/browse/9/index.shtml 为例. 看图里的设置:

这样设置就可以获得真实网址了,这个网址是从摘要那块获得的，那一块的代码都是一个样式，所以可以。可以看下规则。下载

你看上图的话，会发现在参数那里有个缩略图，因为有的文章是将缩略图放在列表里的。现在我们举个例子。看这个 http://www.llsh.net/dz/，这个是电影的，有小图的，我们看一下怎么获得这个图片。注意，这里是同时获得网址和缩略图的。

因为网址和缩略图那块的样子就是下边的，是有规律的，所以可以获得网址

<div class="film_block"> <a href="../dz/2939/" class="img"><img id="img_movie_120x168_19" src="http://pic.bokecc.com/mspecials/jpgs/20080801572040.jpg" onerror="src='../template/xunlei/images/nopic.gif'" alt="双旗镇刀客" /></a>

这个规则下载

　如果我们遇到那些用脚本做栏目列表时怎么办呢？用自动识别是不行的了。这时，该使用手动设置链接格式这个功能起作用了，这也是针对脚本类网址最好的解决办法。下边我们以腾讯Flash频道_作品列表为例来讲一下

http://flash.qq.com/classlist/listwork_1000130000_1.shtml

你用自动获取网址是得不到什么地址的.

我们仔细分析源码后就会发现，这个是这个样子的网址　 http://flash.qq.com/cgi-bin/viewwork?id=727749　，只有最后的数字是不同的，而这数字就包含在脚本里边，我们看一下源码：

<script language="javascript"> var WorkList = new Array ( new Array("727749", "515691264", "小虫", "奥运英雄金牌榜", "http://data1.flash.qq.com/0/0/727/749-1215631240.jpg", "20278", "110", "1", "0", "0") , new Array("720075", "276382390", "石头猫", "悟空先生", "http://data1.flash.qq.com/0/0/720/75-1214305756.gif", "16419", "167", "1", "0", "0") , new Array("717047", "429383035", "`", "追捕", "http://data1.flash.qq.com/0/0/717/47-1213796675.jpg", "8982", "97", "1", "0", "0") , new Array("704794", "401320741", "饭饭㊣", "靓靓超人之决战喇嘛", "http://data1.flash.qq.com/0/0/704/794-1211878682.jpg", "4386", "57", "0", "0", "0") , new Array("696019", "751352265", "庐山制作", "功夫", "http://data1.flash.qq.com/0/0/696/19-1210555821.jpg", "16276", "159", "1", "0", "0") , new Array("692447", "401320741", "饭饭㊣", "黑客红蜘蛛", "http://data1.flash.qq.com/0/0/692/447-1209977138.jpg", "26868", "87", "1", "0", "0") , new Array("675527", "351864717", "闪客动漫堂", "FLASH也奥运", "http://data1.flash.qq.com/0/0/675/527-1207619068.gif", "21260", "204", "1", "0", "0") , new Array("668835", "752822778", "A流浪猫动画", "太阳", "http://data1.flash.qq.com/0/0/668/835-1206586517.gif", "3136", "6", "0", "0", "0") , new Array("668665", "707094092", "大熊宁宁", "火柴头玩花式篮球", "http://data1.flash.qq.com/0/0/668/665-1206589560.gif", "4095", "22", "0", "0", "0") , new Array("663480", "81849901", "我自鬼来也", "鬼斗BOS-Part1", "http://data1.flash.qq.com/0/0/663/480-1205903695.jpg", "7713", "22", "1", "0", "0") , new Array("663379", "24786829", "内野外", "火柴头玩花式篮球", "http://data1.flash.qq.com/0/0/663/379-1205891111.gif", "15944", "31", "1", "0", "0") , new Array("663377", "24786829", "内野外", "铭三国", "http://data1.flash.qq.com/0/0/663/377-1205890883.gif", "7256", "9", "0", "0", "0") , new Array("661538", "24786829", "内野外", "杀手广告片", "http://data1.flash.qq.com/0/0/661/538-1205638699.gif", "5371", "3", "1", "0", "0") , new Array("655066", "752822778", "A流浪猫动画", "apple force cartoon", "http://data1.flash.qq.com/0/0/655/66-1204683513.gif", "5124", "78", "1", "0", "0") , new Array("650967", "282417873", "Toice", "拳皇之黑夜任务2下集", "http://data1.flash.qq.com/0/0/650/967-1204252390.gif", "80180", "186", "1", "0", "0") , new Array("645923", "56616462", "电动画", "果酱军团—秘密实验室", "http://data1.flash.qq.com/0/0/645/923-1203674703.gif", "23738", "462", "1", "0", "0") , new Array("643579", "406391994", "命运冷笑", "三侠五义之锦玉良缘", "http://data1.flash.qq.com/0/0/643/579-1203474373.jpg", "7887", "12", "1", "0", "0") , new Array("643259", "282417873", "Toice", "拳皇之黑夜任务", "http://data1.flash.qq.com/0/0/643/259-1203477735.jpg", "23889", "92", "1", "0", "0") , new Array("642502", "752822778", "A流浪猫动画", "BLACKMAMBA", "http://data1.flash.qq.com/0/0/642/502-1203347374.gif", "3583", "100", "1", "0", "0") , new Array("624730", "56616462", "电动画", "惠普-红包飞", "http://data1.flash.qq.com/0/0/624/730-1201931430.gif", "15861", "374", "1", "0", "0") , new Array("620200", "86472322", "妙动数码", "妙动狗过年猫狗大战", "http://data1.flash.qq.com/0/0/620/200-1201717730.gif", "6020", "25", "0", "0", "0") , new Array("619916", "332015746", "梁火龙", "踢馆式讨红包", "http://data1.flash.qq.com/0/0/619/916-1201702663.gif", "5955", "7", "0", "0", "0") , new Array("597789", "798565629", "炎の漩濄", "The Miss World", "http://data1.flash.qq.com/0/0/597/789-1200880000.gif", "9105", "264", "1", "0", "0") , new Array("568681", "32211633", "神创动漫", "AZONE猎人", "http://data1.flash.qq.com/0/0/568/681-1199877523.gif", "50732", "652", "1", "0", "0") , new Array("543478", "403102962", "lysaaaaa", "西游记未说故事", "http://data1.flash.qq.com/0/0/543/478-1199235218.gif", "7062", "8", "0", "0", "0") , new Array("528962", "304505715", "jikali", "圣诞节的礼物", "http://data1.flash.qq.com/0/0/528/962-1198631233.gif", "9026", "417", "1", "0", "0") , new Array("522378", "562390841", "lyl88", "天下无贼", "http://data1.flash.qq.com/0/0/522/378-1198459143.gif", "12472", "208", "1", "0", "0") , new Array("510191", "24786829", "内野外", "血战长坂", "http://data1.flash.qq.com/0/0/510/191-1198027652.gif", "29703", "203", "0", "0", "0") , new Array("492883", "279583073", "奇利动画", "舞者vs武者", "http://data1.flash.qq.com/0/0/492/883-1197600642.gif", "19849", "505", "1", "0", "0") , new Array("477711", "616553383", "尘埃之外", "乱世豪侠传", "http://data1.flash.qq.com/0/0/477/711-1197174316.gif", "7359", "222", "0", "0", "0") , new Array("476248", "24786829", "内野外", "超智能足球样片", "http://data1.flash.qq.com/0/0/476/248-1196993623.gif", "6816", "342", "1", "0", "0") , new Array("467950", "694247688", "comtech", "曹操来袭击", "http://data1.flash.qq.com/0/0/467/950-1196730978.gif", "50692", "473", "1", "0", "0") , new Array("453316", "24786829", "内野外", "stupid man 3", "http://data1.flash.qq.com/0/0/453/316-1196216975.gif", "11991", "245", "0", "0", "0") , new Array("450816", "155383007", "星辰动画", "龙宫借宝", "http://data1.flash.qq.com/0/0/450/816-1196105423.gif", "30767", "1220", "1", "0", "0") , new Array("446293", "155383007", "星辰动画", "三打白骨精", "http://data1.flash.qq.com/0/0/446/293-1195964863.gif", "72777", "2048", "1", "0", "0") , new Array("431492", "369384067", "IZSW", "心之云", "http://data1.flash.qq.com/0/0/431/492-1195522707.gif", "9141", "467", "1", "0", "0") ) <p align="center" class="pageLink"><a title="Page"> <b>1</b>/<b>2</b> </a> <b>1</b> <a href="/a/201004/2960_2.html">2</a> <a href="/a/201004/2960_2.html">下一页</a> <a href="/a/201004/2960_2.html">尾页</a></p> </div> </div> <div class="share-wrap clearfix align-center"> <div class="share-text h5"> </div> <div class="about-author-wrap"> <div id="mini-wrapper"><img src="https://www.techsir.com/d/88.jpg" width=120px /></div> </div>  </div> <div class="prev-next-wrap has-next has-prev"> <div class="row is-flex"> </div> </div> <div class="comment-wrap"> <section id="comments"> <div class="pl-520am" data-id="2960" data-classid="12"></div> <script type="text/javascript" src="/e/extend/lgyPl/api.js"></script> </section> </div> </div> </div> </div> </article> </div>   <footer class="site-footer"> <div class="footer-top"> <div class="container"> <div class="row"> <div class="col-sm-4">  <div class="widget"> <h4 class="widget-title h5">热门标签</h4> <div class="content tagcloud"> <a href="https://www.techsir.com/tag/%E5%85%83%E5%AE%87%E5%AE%99">元宇宙</a><a href="https://www.techsir.com/chanye/fadian/">新能源</a><a href="hhttps://techsir.com/chanye/robot/">机器人</a> <a href="https://techsir.com/chanye/bio/">生物医疗</a><a href="https://techsir.com/chanye/uav/">无人机</a><a href="https://techsir.com/chanye/edu/">在线教育</a><a href="https://techsir.com/ebiz/">零售科技</a> <a href="https://techsir.com/cloud/">云计算</a><a href="https://techsir.com/sw/">软件天堂</a></div> </div>  </div> <div class="col-sm-4">  <div class="widget"> <h4 class="widget-title h5">推荐栏目</h4> <div class="content tagcloud"> <a href="https://www.techsir.com/shuma/">手机数码</a><a href="https://www.techsir.com/chanye/jinrong/">金融科技</a><a href="https://www.techsir.com/chanye/car/">智能汽车</a> <a href="https://www.techsir.com/ebiz/">电商O2O</a><a href="https://www.techsir.com/club/events/">活动沙龙</a><a href="https://www.techsir.com/chanye/house/">智能家居</a><a href="https://www.techsir.com/vc/">投资故事</a> <a href="https://www.techsir.com/blockchain/">区块链</a><a href="https://www.techsir.com/chanye/ai/">人工智能</a> </div> </div>  <div class="widget"> <h4 class="widget-title h5">订阅关注</h4> <div class="content tagcloud"> <section class="gh-subscribe"> <p><img src="https://www.techsir.com/club/itechsir.jpg" width=320px /></p> </section> </div> </div>  </div> <div class="col-sm-4">  <div class="widget"> <h4 class="widget-title h5">德正仁和</h4> <div class="content about"> <p> 主编直通车：rocky(#)techsir.com 把#换成@ </p> <p> 媒体合作：wechat ：kerwinji </p> <p><a href="https://www.techsir.com/links.html" target="_blank">友情链接</a> | <a href="https://www.techsir.com/contact.html" target="_blank">联系我们</a></p> </div> </div>  </div> </div> </div> </div> <div class="footer-bottom"> <div class="container"> <div class="footer-bottom-wrap clearfix"> <div class="social-links-wrap"> <ul class="social-links"> <a href="#" target="_blank">京ICP备14029665号-1 </a> </ul> </div> <div class="copyright-info"> © 2007-2019 科技先生<a href="https://techsir.com">TechSir.com</a>. </div> </div> </div> </div> </footer>  <span class="back-to-top pull-right" id="back-to-top"><i class="fa fa-angle-up"></i></span>  <div class="modal" id="searchmodal" tabindex="-1" role="dialog" aria-labelledby="myModalLabel"> <div class="modal-dialog" role="document"> <div class="modal-content"> <div class="modal-header"> <button type="button" class="close" data-dismiss="modal" aria-label="Close"><span aria-hidden="true">×</span></button> <h4 class="modal-title align-center" id="myModalLabel">搜索</h4> </div> <div class="modal-body"> <form id="search-form" action="https://www.techsir.com/e/search/index.php" method="post" name="search_news" onsubmit='return search_check(document.search_news);' target="_blank"> <div class="input-group url-wrap"> <input type="text" id="search-input" class="form-control" name="keyboard" spellcheck="false" placeholder="关键词 ..."><input type="hidden" name="show" value="title" />  <div class="input-group-btn"> <button type="submit" class="btn btn-primary"><i class="fa fa-search"></i></button> </div> </div> </form> <div id="search-results"> <ul class=""></ul> </div> </div> <div class="modal-footer"> <button type="button" class="btn btn-default" data-dismiss="modal"></button> </div> </div> </div> </div>  <script src="https://www.techsir.com/b/js2018/jquery.min.js"></script> <script src="https://www.techsir.com/b/js2018/bootstrap.min.js?v=9b2db1d42c"></script> <script src="https://www.techsir.com/b/js2018/plugins.js?v=9b2db1d42c"></script> <script src="https://www.techsir.com/b/js2018/main.js?v=9b2db1d42c"></script> <script language="javascript"> function changetype() { if($('searchtxt').value == '标题') { $('searchname').value = 'subject'; }else if($('searchtxt').value == '内容') { $('searchname').value = 'message'; }else if($('searchtxt').value == '作者') { $('searchname').value = 'author'; } } </script> <script type="text/javascript" src="https://www.techsir.com/b/share/needsharebutton.js"></script> <script> new needShareButton(document.getElementById('i-share')); </script> <style> /* Bubble */ @media screen and (max-width: 1024px){ #wpd-bubble-wrapper > div { width: 40px; height: 40px; }} @media screen and (max-width: 1024px) #wpd-bubble-wrapper.wpd-left-corner > #wpd-bubble #wpd-bubble-add-message, #wpd-bubble-wrapper.wpd-left-content > #wpd-bubble #wpd-bubble-add-message { left: 53px; } #wpd-bubble-wrapper > #wpd-bubble #wpd-bubble-add-message { background-color: #1DB99A; } @media screen and (max-width: 1024px){ #wpd-bubble-wrapper > #wpd-bubble #wpd-bubble-add-message { height: auto; padding: 7px 14px; justify-content: flex-start; font-size: 14px; } } #wpd-bubble-wrapper > #wpd-bubble #wpd-bubble-add-message { width: 400px; height: 46px; position: absolute; top: 50%; left: 75px; border-radius: 5px; padding: 7px; transform: translateY(-50%); display: flex; align-items: center; justify-content: center; font-size: 16px; } #wpd-bubble-wrapper{display:none;position:fixed;z-index:99;text-align:center;opacity:0.9;bottom:80px;} #wpd-bubble-wrapper.wpd-bubble-hover{opacity:1;} #wpd-bubble-wrapper #wpd-bubble-all-comments-count , #wpd-bubble-all-comments-count a{font-size: 15px;font-weight: 600;font-family: sans-serif;} #wpd-bubble-wrapper > div{ background-color: #1DB99A;display:none;border:1px solid #fff;box-shadow:0px 0px 15px #aaa;width:64px;height:64px;border-radius:50%;color:#fff;align-items:center;justify-content:center;position:relative;} #wpd-bubble-wrapper svg{width:60%;height:60%;} #wpd-bubble-wrapper #wpd-bubble-count svg,#wpd-bubble-wrapper #wpd-bubble-notification svg{margin-left:3px;margin-top:3px;} #wpd-bubble-wrapper #wpd-bubble svg{margin-left:2px;} #wpd-bubble-wrapper path.wpd-bubble-count-first{fill:#fff;} #wpd-bubble-wrapper path.wpd-bubble-count-second{fill:transparent;} #wpd-bubble-wrapper path.wpd-bubble-plus-first{fill:#fff;} #wpd-bubble-wrapper path.wpd-bubble-plus-second{fill:transparent;} #wpd-bubble-wrapper > #wpd-bubble-count{display:flex;cursor:pointer;} #wpd-bubble-wrapper > #wpd-bubble{cursor:pointer;} #wpd-bubble-wrapper > #wpd-bubble #wpd-bubble-add-message{width:400px;height:46px;position:absolute;top:50%;left:75px;border-radius:5px;padding:7px;transform:translateY(-50%);display:flex;align-items:center;justify-content:center; font-size: 16px;} #wpd-bubble-wrapper.wpd-right-corner > #wpd-bubble #wpd-bubble-add-message{left:-412px;} #wpd-bubble-wrapper > #wpd-bubble #wpd-bubble-add-message::before{content:'';border:9px solid transparent;position:absolute;top:50%;left:-9px;transform:translateY(-50%);border-left:none;} #wpd-bubble-wrapper.wpd-right-corner > #wpd-bubble #wpd-bubble-add-message::before{left:400px;border-left:9px solid;border-right:none;} #wpd-bubble-wrapper > #wpd-bubble-count .wpd-new-comments-count{display:none;} #wpd-bubble-wrapper > #wpd-bubble-count.wpd-new-comments .wpd-new-comments-count{display:flex;border-radius:50%;width:25px;height:25px;background-color:#ff842a;position:absolute;top:38px;left:38px;font-size:15px;align-items:center;justify-content:center;border:1px solid #fff;} #wpd-bubble-wrapper.wpd-bubble-hover > #wpd-bubble-count:not(.wpd-new-comments) + #wpd-bubble{display:flex;} #wpd-bubble-wrapper.wpd-bubble-hover > #wpd-bubble-count:not(.wpd-new-comments){display:none;} #wpd-bubble-wrapper > #wpd-bubble-notification{background-color:#fe7617;} #wpd-bubble-wrapper > #wpd-bubble-notification path.wpd-bubble-notification-first{fill:#fff;} #wpd-bubble-wrapper > #wpd-bubble-notification path.wpd-bubble-notification-second{fill:transparent;} #wpd-bubble-wrapper.wpd-new-comment-added{opacity:1;} #wpd-bubble-wrapper.wpd-new-comment-added #wpd-bubble-count{display:none;} #wpd-bubble-wrapper.wpd-new-comment-added #wpd-bubble-notification{display:flex;} #wpd-bubble-wrapper.wpd-new-comment-added #wpd-bubble-all-comments-count{color:#b9501d;} #wpd-bubble-wrapper #wpd-bubble-notification-message{display:none;width:430px;height:100%;position:absolute;background-color:#fbfbfb;top:0;left:75px;border:1px solid #b2b2b2;box-shadow:0px 0px 10px #bbb;border-radius:5px;padding:7px;} #wpd-bubble-wrapper.wpd-right-corner #wpd-bubble-notification-message{left:-446px;} #wpd-bubble-wrapper #wpd-bubble-notification-message #wpd-bubble-author,#wpd-bubble-wrapper #wpd-bubble-notification-message #wpd-bubble-comment{display:flex;align-items:center;height:50%;} #wpd-bubble-wrapper #wpd-bubble-notification-message #wpd-bubble-author{justify-content:space-between;} #wpd-bubble-wrapper #wpd-bubble-notification-message #wpd-bubble-author > div{display:flex;align-items:center;} #wpd-bubble-wrapper #wpd-bubble-notification-message #wpd-bubble-comment{font-size:12px;} #wpd-bubble-wrapper #wpd-bubble-notification-message span:not(.wpd-bubble-spans){display:inline-block;margin:5px;} #wpd-bubble-wrapper #wpd-bubble-notification-message #wpd-bubble-author-avatar{width:20px;height:20px;line-height:16px;} #wpd-bubble-wrapper #wpd-bubble-notification-message #wpd-bubble-author-avatar img{border-radius:50%; width: 100%;} #wpd-bubble-wrapper #wpd-bubble-notification-message #wpd-bubble-author-name{color:#4e9f93;font-size:14px;font-weight: 600;} #wpd-bubble-wrapper #wpd-bubble-notification-message #wpd-bubble-comment-date{color:#fe7617;font-size:10px;} #wpd-bubble-wrapper #wpd-bubble-notification-message #wpd-bubble-comment,#wpd-bubble-wrapper #wpd-bubble-notification-message #wpd-bubble-comment-reply-link a{color:#333;} #wpd-bubble-wrapper #wpd-bubble-notification-message #wpd-bubble-comment-reply-link a{color:#777;} #wpd-bubble-wrapper #wpd-bubble-notification-message #wpd-bubble-comment-text{font-size:12px;margin-left:7px;} #wpd-bubble-wrapper #wpd-bubble-notification-message::before{content:'';border:9px solid transparent;position:absolute;top:20px;left:-10px;border-left:none;padding:0;border-right-color:#b2b2b2;} #wpd-bubble-wrapper #wpd-bubble-notification-message::after{content:'';border:9px solid transparent;position:absolute;top:20px;left:-9px;border-left:none;border-right-color:#fbfbfb;} #wpd-bubble-wrapper.wpd-right-corner #wpd-bubble-notification-message::before{left:429px;border-right:none;border-left:9px solid #b2b2b2;} #wpd-bubble-wrapper.wpd-right-corner #wpd-bubble-notification-message::after{left:428px;border-right:none;border-left:9px solid #fbfbfb;} #wpd-bubble-wrapper #wpd-bubble-comment-close a{color:#333;text-decoration:none;} #wpd-bubble-wrapper #wpd-bubble-add-message-close{display: inline-block;top: 0px;right: 10px;position: absolute;} #wpd-bubble-wrapper #wpd-bubble-add-message-close a{color:#fff;text-decoration:none;display:inline-block;} #mini-wrapper img{ border-radius: 4px; border: 0; box-shadow: 0px 0px 20px 0px rgb(76 87 125 / 2%); background-color: #fff; border-width: 1px; border-color: #eff2f5; border-radius: 0.625rem; background: #FFF; border-radius: calc(0.625rem - 1px); } </style> <div id="wpd-bubble-wrapper" class="wpd-left-content" style="left: 25px; display: block;"> <span id="wpd-bubble-all-comments-count" ><a href="#comments"><em id="pl2-totalnum"></em></a></span> <div id="wpd-bubble-count"><svg xmlns="https://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24"> <path class="wpd-bubble-count-first" d="M20 2H4c-1.1 0-1.99.9-1.99 2L2 22l4-4h14c1.1 0 2-.9 2-2V4c0-1.1-.9-2-2-2zm-2 12H6v-2h12v2zm0-3H6V9h12v2zm0-3H6V6h12v2z"></path> <path class="wpd-bubble-count-second" d="M0 0h24v24H0z"></path></svg> </div> <div id="wpd-bubble"> <svg xmlns="https://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24"><path class="wpd-bubble-plus-first" d="M19 13h-6v6h-2v-6H5v-2h6V5h2v6h6v2z"></path><path class="wpd-bubble-plus-second" d="M0 0h24v24H0z"></path></svg> <div id="wpd-bubble-add-message">希望看到您的想法，请您发表评论<span id="wpd-bubble-add-message-close"><a href="#">x</a></span></div></div> </body> </html>