提取网页中的内容（提取纯文字VB）

 

' **************************************************
' 函数名：distill
' 作     用：提取网页中的内容
' 参     数：content ---- 要提取的内容，length ---- 从开头数要提取的字符数
' 返回值：提取的内容
' **************************************************
function  distill(content,length)
     ON   ERROR   RESUME   NEXT
     dim  isWord,okContent,i
    i = 1
    isWord = false
    content = replace (content, "   " , "" )
     do   while   len (okContent) < length
      if   mid (content,i, 1 ) <> " < "   then
         isWord = true
      else
         i = i + 1
          do   while   mid (content,i, 1 ) <> " > "
             i = i + 1
          loop
         i = i + 1
          if   mid (content,i, 1 ) <> " < "   then
             isWord = true
          else
             isWord = false
          end   if
      end   if
      if  i > len (content)  then
         distill = okContent
          exit   function
      end   if
      if  isWord  then
         okContent = okContent + mid (content,i, 1 )
         i = i + 1
      end   if
     loop
    distill = okContent
     if  err.number <> 0   then  err.clear
end function

转载于:https://www.cnblogs.com/breezeblew/archive/2009/03/25/1421589.html