辦公OA--正文提取中用到的正則表達式
瀏覽量：2645
CRM定制 辦公OA
#region 相關正則表達式
/// <summary>
/// 去掉所有html標簽
/// </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標簽
/// </summary>
private static readonly Regex FindTitle = new Regex(
@"<\s*/?title\s*>",
RegexOptions.ExplicitCapture
| RegexOptions.Multiline
| RegexOptions.IgnoreCase);
/// <summary>
/// 找出title標簽內容
/// </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標簽
/// </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標簽
/// </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標簽
/// </summary>
private static readonly Regex FindNbsp = new Regex(
@" ",
RegexOptions.ExplicitCapture
| RegexOptions.Multiline
| RegexOptions.IgnoreCase);
/// <summary>
/// 找出結尾標簽
/// </summary>
private static readonly Regex FindS = new Regex(
@"(?<Content>[\s\S]*?)\$",
RegexOptions.ExplicitCapture
| RegexOptions.Multiline
| RegexOptions.IgnoreCase);
/// <summary>
/// 找出是否為標準句
/// </summary>
private static readonly Regex IsSen = new Regex(
@"[,.，。!！;；:：……？?《》“”""]",
RegexOptions.ExplicitCapture
| RegexOptions.Multiline
| RegexOptions.IgnoreCase);
/// <summary>
/// 找出是否為垃圾句[strong][h]標簽過多的
/// </summary>
private static readonly Regex IsWs = new Regex(
@"\[\(h\)\]",
RegexOptions.ExplicitCapture
| RegexOptions.Multiline
| RegexOptions.IgnoreCase);
/// <summary>
/// 找出是否為垃圾句冒號和·-過多的
/// </summary>
private static readonly Regex IsWsM = new Regex(
@"\[·]|[－]|[：:]",
RegexOptions.ExplicitCapture
| RegexOptions.Multiline
| RegexOptions.IgnoreCase);
/// <summary>
/// 找出是否為BBS特征
/// </summary>
private static readonly Regex IsBbsInfo = new Regex(
@"第[^樓]{1,50}樓|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>
/// 找出是否為垃圾句:后字符號過少，：號前無“說”字,:號后無"關于"
/// </summary>
private static readonly Regex IsWsMM = new Regex(
@"^[^說\s]{0,8}?[:：].{0,10}$",
RegexOptions.ExplicitCapture
| RegexOptions.Multiline
| RegexOptions.IgnoreCase);
/// <summary>
/// 找出spider寫入的url標記
/// </summary>
private static readonly Regex txtUrl = new Regex(
@"當前URL為:http://(?<URL>.*)",
RegexOptions.ExplicitCapture
| RegexOptions.Multiline
| RegexOptions.IgnoreCase);
/// <summary>
/// 找出spider寫入的錨點描述標記
/// </summary>
private static readonly Regex txtDescription = new Regex(
@"當前鏈接描述為:(?<Describe>.*)",
RegexOptions.ExplicitCapture
| RegexOptions.Multiline
| RegexOptions.IgnoreCase);
///// <summary>
///// 取需要a標簽
///// </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