mathematica抓取网页

2017年08月07日 18:14:15

阅读数：400

一个简易的获取网页.nb程序

list = List[];
url = "http://blog.csdn.net/gl486546/article/category/6389727/";
catchPageElem[n_] := Block[{xml, len, d, i, temp},
  xml = Import[url <> ToString[n], "XMLObject"];
  d = Cases[xml,
    XMLElement[
      "span", {"class" -> "link_title"}, {XMLElement[
        "a", {"shape" -> "rect", 
         "href" -> 
          href_}, {title_}], __}] :> {"http://blog.csdn.net" <> href, 
      StringTrim[title]}, {0, Infinity}];
  len = Length[d];
  Do[AppendTo[list, d[[i]]], {i, 1, len}]
  ]
Do[catchPageElem[i], {i, 1, 13}];
list