java Pattern与Matcher获取字符串内容

zhuailhw123 2018-08-21 11:38:52
<script type="text/javascript">var _width = 313; var _height = 201;var text_height = 22;var flash_height = _height + text_height;var pic_arr = new Array();var link_arr = new Array();var text_arr = new Array();var i = 0;pic_arr[i] = "/picture/-1/180801144101642688.jpg";link_arr[i] = "/art/2018/8/1/art_12785_226285.html";text_arr[i] = "公司举办“鲁碧事业红歌颂 党员尽责当...";i++;pic_arr[i] = "/picture/-1/180801142025833333.jpg";link_arr[i] = "/art/2018/8/1/art_12785_226283.html";text_arr[i] = "半年工作会议吹响了加速奋进的冲锋号";i++;pic_arr[i] = "/picture/-1/180723160836305496.jpg";link_arr[i] = "/art/2018/7/23/art_12785_225336.html";text_arr[i] = "市委书记梅建华到公司绿建产业基地观摩";i++;pic_arr[i] = "/picture/-1/180507152231943274.jpg";link_arr[i] = "/art/2018/5/7/art_12785_211050.html";text_arr[i] = "鲁碧公司召开庆“五四”暨鲁碧工匠表彰...";i++;pic_arr[i] = "/picture/-1/180503181609968483.jpg";link_arr[i] = "/art/2018/5/3/art_12785_210716.html";text_arr[i] = "劳动最光荣 公司领导慰问坚持节日生产...";
i++;var p = pic_arr.join("|");var l = link_arr.join("|");var t = text_arr.join("|");var f = "/flash/-1/slideshow.swf";document.write('<object ID="focus_flash" classid="clsid:d27cdb6e-ae6d-11cf-96b8-444553540000" codebase="http://fpdownload.macromedia.com/pub/shockwave/cabs/flash/swflash.cab#version=6,0,0,0" width="'+ _width +'" height="'+ flash_height +'">');document.write('<param name="allowScriptAccess" value="sameDomain"><param name="movie" value="'+f+'"><param name="quality" value="high"><param name="bgcolor">');document.write('<param name="menu" value="false"><param name=wmode value="transparent">');document.write('<param name="FlashVars" value="pics='+p+'&links='+l+'&texts='+t+'&borderwidth='+_width+'&borderheight='+_height+'&textheight='+text_height+'">');document.write('<embed ID="focus_flash" src="'+f+'" wmode="opaque" FlashVars="pics='+p+'&links='+l+'&texts='+t+'&borderwidth='+_width+'&borderheight='+_height+'&textheight='+text_height+'" menu="false" quality="high" width="'+ _width +'" height="'+ flash_height +'" allowScriptAccess="sameDomain" type="application/x-shockwave-flash" pluginspage="http://www.macromedia.com/go/getflashplayer" />');document.write('</object>');</script>


这是一个网页的中的内容,我想获得:

"公司举办“鲁碧事业红歌颂 党员尽责当..."
"/picture/-1/180801144101642688.jpg"
"/art/2018/8/1/art_12785_226285.html"

这些字符串 用Pattern与Matcher该怎么写?
...全文
499 2 打赏 收藏 转发到动态 举报
写回复
用AI写文章
2 条回复
切换为时间正序
请发表友善的回复…
发表回复
Braska 2018-08-21
  • 打赏
  • 举报
回复

public static void main(String[] args) throws InterruptedException {
String html = "<script type=\"text/javascript\">var _width = 313; var _height = 201;var text_height = 22;var flash_height = _height + text_height;var pic_arr = new Array();var link_arr = new Array();var text_arr = new Array();var i = 0;pic_arr[i] = \"/picture/-1/180801144101642688.jpg\";link_arr[i] = \"/art/2018/8/1/art_12785_226285.html\";text_arr[i] = \"公司举办“鲁碧事业红歌颂 党员尽责当...\";i++;pic_arr[i] = \"/picture/-1/180801142025833333.jpg\";link_arr[i] = \"/art/2018/8/1/art_12785_226283.html\";text_arr[i] = \"半年工作会议吹响了加速奋进的冲锋号\";i++;pic_arr[i] = \"/picture/-1/180723160836305496.jpg\";link_arr[i] = \"/art/2018/7/23/art_12785_225336.html\";text_arr[i] = \"市委书记梅建华到公司绿建产业基地观摩\";i++;pic_arr[i] = \"/picture/-1/180507152231943274.jpg\";link_arr[i] = \"/art/2018/5/7/art_12785_211050.html\";text_arr[i] = \"鲁碧公司召开庆“五四”暨鲁碧工匠表彰...\";i++;pic_arr[i] = \"/picture/-1/180503181609968483.jpg\";link_arr[i] = \"/art/2018/5/3/art_12785_210716.html\";text_arr[i] = \"劳动最光荣 公司领导慰问坚持节日生产...\";\n" +
"i++;var p = pic_arr.join(\"|\");var l = link_arr.join(\"|\");var t = text_arr.join(\"|\");var f = \"/flash/-1/slideshow.swf\";document.write('<object ID=\"focus_flash\" classid=\"clsid:d27cdb6e-ae6d-11cf-96b8-444553540000\" codebase=\"http://fpdownload.macromedia.com/pub/shockwave/cabs/flash/swflash.cab#version=6,0,0,0\" width=\"'+ _width +'\" height=\"'+ flash_height +'\">');document.write('<param name=\"allowScriptAccess\" value=\"sameDomain\"><param name=\"movie\" value=\"'+f+'\"><param name=\"quality\" value=\"high\"><param name=\"bgcolor\">');document.write('<param name=\"menu\" value=\"false\"><param name=wmode value=\"transparent\">');document.write('<param name=\"FlashVars\" value=\"pics='+p+'&links='+l+'&texts='+t+'&borderwidth='+_width+'&borderheight='+_height+'&textheight='+text_height+'\">');document.write('<embed ID=\"focus_flash\" src=\"'+f+'\" wmode=\"opaque\" FlashVars=\"pics='+p+'&links='+l+'&texts='+t+'&borderwidth='+_width+'&borderheight='+_height+'&textheight='+text_height+'\" menu=\"false\" quality=\"high\" width=\"'+ _width +'\" height=\"'+ flash_height +'\" allowScriptAccess=\"sameDomain\" type=\"application/x-shockwave-flash\" pluginspage=\"http://www.macromedia.com/go/getflashplayer\" />');document.write('</object>');</script>";

String regex = "(?<=(text_arr\\[i\\]\\s=\\s\"))[^\"]+(?=\")";

Matcher matcher = Pattern.compile(regex).matcher(html);
while (matcher.find()) {
System.out.println(matcher.group());
}

regex = "(?<=(pic_arr\\[i\\]\\s=\\s\"))[^\"]+(?=\")";
matcher = Pattern.compile(regex).matcher(html);
while (matcher.find()) {
System.out.println(matcher.group());
}

regex = "(?<=(link_arr\\[i\\]\\s=\\s\"))[^\"]+(?=\")";
matcher = Pattern.compile(regex).matcher(html);
while (matcher.find()) {
System.out.println(matcher.group());
}
}

62,621

社区成员

发帖
与我相关
我的任务
社区描述
Java 2 Standard Edition
社区管理员
  • Java SE
加入社区
  • 近7日
  • 近30日
  • 至今
社区公告
暂无公告

试试用AI创作助手写篇文章吧