新浪微博源码不是普通html代码，如何解析？

Question

我现在需要根据关键字爬取新浪微博内容，并且只能通过网页渠道（不能走wap），得到的htm代码如下，并不是普通html，都是通过js调用的。其中把汉字全部转换成uft-8编码，标签之类的也做过处理，求大神指教如何解析！谢谢了！

<script>STK && STK.pageletM && STK.pageletM.view({"pid":"pl_common_searchTop","js":["apps/search/js/pl/common/searchTop.js?version=201209071710"],"css":[],"html":"<a href="/" class="logo_img"><div class="search_logo"></div></a>n<div class="search_head_formbox">n <ul class="formbox_tab clearfix" node-type="searchItems">n  <li><a action-type="searchItem" href="/weibo/%25E4%25BF%259D%25E9%2592%2593&Refer=weibo_weibo" class="cur" >u5faeu535a</a><a action-type="searchItem" href="/user/%25E4%25BF%259D%25E9%2592%2593&Refer=weibo_user" >u627eu4eba</a><a action-type="searchItem" href="/pic/%25E4%25BF%259D%25E9%2592%2593&Refer=weibo_pic" >u56feu7247</a></li><li class="hidden_li" node-type="moreItems"><a action-type="searchItem" href="/q/%25E4%25BF%259D%25E9%2592%2593&Refer=weibo_q" >u5faeu7fa4</a><a action-type="searchItem" href="/event/%25E4%25BF%259D%25E9%2592%2593&Refer=weibo_event" >u6d3bu52a8</a><a action-type="searchItem" href="/apps/%25E4%25BF%259D%25E9%2592%2593&Refer=weibo_apps" >u5e94u7528</a><a action-type="searchItem" href="/vote/%25E4%25BF%259D%25E9%2592%2593&Refer=weibo_vote" >u6295u7968</a></li><li><a href="javascript:void(0);" node-type="more" suda-data=key=tblog_search_v4.1&value=weibo_more>u66f4u591au00bb</a></li> </ul>n <!-- search_input -->n <div class="search_input">n  <div class="search_input_wrap">n <div class="searchBtn_box"><a href="/weibo/%25E4%25BF%259D%25E9%2592%2593" class="searchBtn" node-type="submit" suda-data=key=tblog_search_v4.1&value=nologin_search>u641cu7d22</a></div>n <div class="searchInp_box">n  <div class="searchInp_auto">n   <input class="searchInp_form" type="text" value="u4fddu9493" node-type="text" maxlength="40">n  </div>n </div>n  </div>n </div>n <!-- /search_input --> n</div>n<div class="search_head_action">n <p class="action_txt">n  <a href="javascript:void(0);" class="adv_settiong" node-type="advsearch" suda-data=key=tblog_search_v4.1&value=weibo_profes>u9ad8u7ea7u641cu7d22</a><em class="W_vline W_spetxtc">|</em><a href="/preferences" class="setting" suda-data=key=tblog_search_v4.1&value=weibo_custom>u8bbeu7f6e</a><em class="W_vline W_spetxtc">|</em><a href="/"suda-data=key=tblog_search_v4.1&value=return_index>u641cu7d22u9996u9875</a>n </p>n</div>n"})</script>
<script>STK && STK.pageletM && STK.pageletM.view({"pid":"plc_main","js":[],"css":[],"html":"  <div class="search_topcon clearfix" id="pl_common_totalshow"></div>n <div class="S_content clearfix">n  <div class="S_content_l">n  <div id="pl_common_pinyinerr"></div>n <div id="pl_weibo_livetips"></div>n <div id="pl_weibo_filtertab"></div>n <div id="pl_weibo_direct"></div>nt <div id="pl_weibo_extraTopic"></div>n <div id="pl_weibo_feedlist"></div>n <div id="pl_weibo_relation"></div>n <div id="pl_common_bottomInput" style="display:none;"></div>n  </div>n  <div class="S_content_r">n <div id="pl_weibo_directright"></div>n <div id="pl_weibo_hotband"></div>n <div class="module_history" id="pl_common_searchHistory"></div>n  </div>n </div>n "})</script>

Answer 1

额，我直接将unicode编码转成中文，然后截取需要的信息

Answer 2

我是用的C#，先用正则截取出里面我需要的部分，然后将里面的给置换掉。再用Regex.Unescape解析出中文。

Answer 3

同问，楼主解决没呢，交流下啊

Answer 4

直接用v8引擎

Answer 5

没有看过json啊，感觉这个就是在普通html上，对一些“之类的字符加上

Answer 6

STK.pageletM.view() 方法里，应该是json 数据，用json包解析出来就行了，fastjson包貌似会自动转换
u4fddu9493这样的编码。。。