简介:新闻网页正文抽取,可提取互联网上99% 已上文章,智能识别包含的标题及正文内容。 互联网上几百万个站点,每个站点还有N个不同的文章页面模版,您只需要接入我们的接口,就无需再为编写获取文章内容的正则而苦恼了,直接提取标题及正文内容。
已连接应用数:2305
ASP调用网页提取接口示例:
<%@LANGUAGE="VBSCRIPT" CODEPAGE="936"%> <% Option Explicit '========================================================= ' File : .asp ' Version : 1.0.0.0 ' Create : ' Modify : '========================================================= ' 1.0.0.0 : '========================================================= %> <% Dim url,datatype,token,queryurl url = "http%3a%2f%2fwww.sina.com.cn%2f" token = "00d5cb1fac5dc5cbfe2ff218292a2dfd33" '用户中心查看您的token queryurl = "https://api.ip138.com/text/?url="&url&"&type="&1&"&token="&token Response.Write (GetURL(queryurl)) Function GetURL(queryurl) on error resume next dim Retrieval Set Retrieval = Server.CreateObject("MSXML2.ServerXMLHTTP") Retrieval.setTimeouts 600000, 600000, 600000, 600000 Retrieval.Open "GET", queryurl, false Retrieval.Send GetURL = Retrieval.ResponseBody Set Retrieval = Nothing GetURL=BytesToBstr(GetURL,"utf-8") End Function Function BytesToBstr(strBody,CodeBase) dim objStream set objStream = Server.CreateObject("Adodb.Stream") objStream.Type = 1 objStream.Mode =3 objStream.Open objStream.Write strBody objStream.Position = 0 objStream.Type = 2 objStream.Charset = CodeBase BytesToBstr = objStream.ReadText objStream.Close set objStream = nothing End Function %>