Access数据库中怎么批量删除html标记

我在网上找到一个access数据库,可是里面每一个记录里都有大量的HTML标记,而且记录很多,用空白批量替换也只能替换一小部分.请问怎么能方便快捷的删除这些html标记.... 我在网上找到一个access数据库,可是里面每一个记录里都有大量的HTML标记,而且记录很多,用空白批量替换也只能替换一小部分.请问怎么能方便快捷的删除这些html标记.
另外,这个数据库为什么有的内容不显示,好像隐藏了.有什么办法可以查看完整的数据记录么?
追加50分，能不能给我说具体点，比如正则怎么替换掉＜/B＞或者更长的代码。如果真的实现。再追加一百分。展开

 我来答

6个回答

#热议# 为什么说不要把裤子提到肚脐眼？

百度网友3ff78df
2010-01-13 · 超过19用户采纳过TA的回答

知道答主

回答量：93

采纳率：0%

帮助的人：51.4万

我也去答题访问个人页

关注

展开全部

读取后用正则表达式全部替换
例如：
HTML相关的正则表达式2007-07-15 00:04#region 相关正则表达式

/// <summary>
/// 去掉所有html标签
/// </summary>
private static readonly Regex FilterAll = new Regex(
@"(\[([^=]*)(=[^\]]*)?\][\s\S]*?\[/\1\])|(?<lj>(?=[^\u4E00-\u9FA5\uFE30-\uFFA0,."");])<a\s+[^>]*>[^<]{2,}</a>(?=[^\u4E00-\u9FA5\uFE30-\uFFA0,."");]))|(?<Style><style[\s\S]+?/style>)|(?<select><select[\s\S]+?/select>)|(?<Script><script[\s\S]*?/script>)|(?<Explein><\!\-\-[\s\S]*?\-\->)|(?<li><li(\s+[^>]+)?>[\s\S]*?/li>)|(?<Html></?\s*[^> ]+(\s*[^=>]+?=['""]?[^""']+?['""]?)*?[^\[<]*>)|(?<Other>&[a-zA-Z]+;)|(?<Other2>\#[a-z0-9]{6})|(?<Space>\s+)|(\&\#\d+\;)",
RegexOptions.ExplicitCapture
| RegexOptions.Multiline
| RegexOptions.IgnoreCase); //(?<Link><a[\s\S]*?</a>)|
//(?<Style><style[\s\S]+?/style>)|(?<select><select[\s\S]+?/select>)|(?<Script><script[\s\S]*?/script>)|(?<Explein><\!\-\-[\s\S]*?\-\->)|(?<li><li(\s+[^>]+)?>[\s\S]*?/li>)|(?<Html></?\s*[^> ]+(\s*[^=>]+?=['""]?[^""']+?['""]?)*?[^\[<]*>)|(?<Other>&[a-zA-Z]+;)|(?<Other2>\#[a-z0-9]{6})|(?<Space>\s+)

/// <summary>
/// 找出title标签
/// </summary>
private static readonly Regex FindTitle = new Regex(
@"<\s*/?title\s*>",
RegexOptions.ExplicitCapture
| RegexOptions.Multiline
| RegexOptions.IgnoreCase);

/// <summary>
/// 找出title标签内容
/// </summary>
private static readonly Regex FindTitleContent = new Regex(
@"<\s*/?title\s*>(?<Content>[\s\S]*?)<\s*/?title\s*>",
RegexOptions.ExplicitCapture
| RegexOptions.Multiline
| RegexOptions.IgnoreCase);

/// <summary>
/// 找出h 和Strong标签
/// </summary>
private static readonly Regex FindHStrong = new Regex(
@"<\s*/?h\s*>|<\s*/?strong\s*>",
RegexOptions.ExplicitCapture
| RegexOptions.Multiline
| RegexOptions.IgnoreCase);

/// <summary>
/// 找出p 和br标签
/// </summary>
private static readonly Regex FindPB = new Regex(
@"<\s*/?p\s*>|<\s*br\s*/?>|<\s*/?tr\s*>",
RegexOptions.ExplicitCapture
| RegexOptions.Multiline
| RegexOptions.IgnoreCase);

/// <summary>
/// 找出nbsp标签
/// </summary>
private static readonly Regex FindNbsp = new Regex(
@" ",
RegexOptions.ExplicitCapture
| RegexOptions.Multiline
| RegexOptions.IgnoreCase);

/// <summary>
/// 找出结尾标签
/// </summary>
private static readonly Regex FindS = new Regex(
@"(?<Content>[\s\S]*?)\$",
RegexOptions.ExplicitCapture
| RegexOptions.Multiline
| RegexOptions.IgnoreCase);

/// <summary>
/// 找出是否为标准句
/// </summary>
private static readonly Regex IsSen = new Regex(
@"[,.，。!！;；:：……？?《》“”""]",
RegexOptions.ExplicitCapture
| RegexOptions.Multiline
| RegexOptions.IgnoreCase);

/// <summary>
/// 找出是否为垃圾句[strong][h]标签过多的
/// </summary>
private static readonly Regex IsWs = new Regex(
@"\[$h$\]",
RegexOptions.ExplicitCapture
| RegexOptions.Multiline
| RegexOptions.IgnoreCase);

/// <summary>
/// 找出是否为垃圾句冒号和·-过多的
/// </summary>
private static readonly Regex IsWsM = new Regex(
@"\[·]|[－]|[：:]",
RegexOptions.ExplicitCapture
| RegexOptions.Multiline
| RegexOptions.IgnoreCase);

/// <summary>
/// 找出是否为BBS特征
/// </summary>
private static readonly Regex IsBbsInfo = new Regex(
@"第[^楼]{1,50}楼|Powered\s*/?by[\s\S]*?Dvbbs|Powered\s*/?by[\s\S]*?Discuz",
RegexOptions.ExplicitCapture
| RegexOptions.Multiline
| RegexOptions.IgnoreCase);

/// <summary>
/// 取KEYWORD
/// </summary>
private static readonly Regex mKeyWord = new Regex(
@"<meta\s*name\s*=\s*['""]?keywords['""]?\s*content\s*=\s*['""]?(?<KeyWords>[^'"">]*)['""]?[^>]*>|<meta\s*content\s*=\s*['""]?(?<KeyWords>[^'"">]*)['""]?\s*name\s*=\s*['""]?keywords['""]?\s*[^>]*>
",RegexOptions.ExplicitCapture| RegexOptions.Multiline| RegexOptions.IgnoreCase);

/// <summary>
/// 取DESCRIPTION
/// </summary>
private static readonly Regex mDescription = new Regex(
@"<meta\s*name\s*=\s*['""]?description['""]?\s*content\s*=\s*['""]?(?<description>[^'"">]*)['""]?[^>]*>|<meta\s*content\s*=\s*['""]?(?<description>[^'"">]*)['""]?\s*name\s*=\s*['""]?description['""]?\s*[^>]*>
",RegexOptions.ExplicitCapture| RegexOptions.Multiline| RegexOptions.IgnoreCase);

/// <summary>
/// 取Tags
/// </summary>
private static readonly Regex mTag = new Regex(
@"<meta\s*name\s*=\s*['""]?tagwords['""]?\s*content\s*=\s*['""]?(?<tagwords>[^'"">]*)['""]?[^>]*>|<meta\s*content\s*=\s*['""]?(?<tagwords>[^'"">]*)['""]?\s*name\s*=\s*['""]?tagwords['""]?\s*[^>]*>
", RegexOptions.ExplicitCapture | RegexOptions.Multiline | RegexOptions.IgnoreCase);

/// <summary>
/// 找出是否为垃圾句:后字符号过少，：号前无“说”字,:号后无"关于"
/// </summary>
private static readonly Regex IsWsMM = new Regex(
@"^[^说\s]{0,8}?[:：].{0,10}$",
RegexOptions.ExplicitCapture
| RegexOptions.Multiline
| RegexOptions.IgnoreCase);

/// <summary>
/// 找出spider写入的url标记
/// </summary>
private static readonly Regex txtUrl = new Regex(
@"当前URL为:http://(?<URL>.*)",
RegexOptions.ExplicitCapture
| RegexOptions.Multiline
| RegexOptions.IgnoreCase);

/// <summary>
/// 找出spider写入的锚点描述标记
/// </summary>
private static readonly Regex txtDescription = new Regex(
@"当前链接描述为:(?<Describe>.*)",
RegexOptions.ExplicitCapture
| RegexOptions.Multiline
| RegexOptions.IgnoreCase);

///// <summary>
///// 取需要a标签
///// </summary>
//private static readonly Regex cleanFirst = new Regex(
// @"([\u4E00-\u9FA5]|[\uFE30-\uFFA0]|[,."");])(?<Robbish1><a\s+[^>]*>)[^<]{1,6}(?<Robbish2></a>)([\u4E00-\u9FA5]|[\uFE30-\uFFA0]|[,."");])", RegexOptions.ExplicitCapture | RegexOptions.Multiline | RegexOptions.IgnoreCase);

#endregion

参考资料： http://hi.baidu.com/ganyu21/blog/item/75000a23d75c354c9258073a.html

本回答由提问者推荐