修改

很抱歉，如果不清楚，正则表达式只匹配城市的第二个名称，而不是整个城市名称。如果不清楚，我道歉，谢谢。

我在玩弄

 @"(?<city>[a-zA-Z]+\s*){1,3},\s+(?<state>\w\w)\s+(?<zip>\d+)

对于这个城市但无济于事。

非常感谢任何帮助。

守则

private void ReadPdfFile(string filePath)
{
    var res = GetTextFromAllPages(filePath);
    Regex typ = new Regex(@"\s\n(?<llctype>[\w\s\(\)]+)?---------[\-\s]+", RegexOptions.Compiled | RegexOptions.IgnoreCase | RegexOptions.Singleline);
    Regex city = new Regex(@"(?<city>\w+?),\s+(?<state>\w\w)\s+(?<zip>\d+)", RegexOptions.Compiled | RegexOptions.IgnoreCase | RegexOptions.Singleline);
    Regex data = new Regex(@"(?<filling>\d{8,})\s+(?<name>[^\n\r]*).*?law\s+:\s+203.*?county\s+:\s*(?<county>[\w]+)\s+(?<fileraddress>[^\n\r]+).*?EFF\..*?:\s(?<effdate>([\d/]+|\s+))\s(?<address2>[^\r\n]*).*?:\s(\s+|\w+)(?<zip>[^\r\n]+)\s+(?<processaddress>[^\r\n]+)\s+(?<processaddress2>[^\r\n]+)\s+(?<processzip>[^\r\n]+)\s", RegexOptions.Compiled | RegexOptions.IgnoreCase | RegexOptions.Singleline);            
    foreach (var page in res)
    {
        if (typ.IsMatch(page))
        {
            var mtchTitle = typ.Match(page);
            var title = mtchTitle.Groups["llctype"] != null ? mtchTitle.Groups["llctype"].Value : "";
            var matchData = data.Matches(page);
            foreach (Match m in matchData)
            {
                var fileradd2 = m.Groups["address2"] != null ? m.Groups["address2"].Value : "";
                var processadd2 = m.Groups["processaddress2"] != null ? m.Groups["processaddress2"].Value : "";
                var address = m.Groups["fileraddress"] != null ? m.Groups["fileraddress"].Value : "" + (fileradd2.IndexOf("            ") > -1 ? " " + fileradd2.Split(new string[] { "            " }, StringSplitOptions.None)[0] : "");
                var processaddress = m.Groups["processaddress"] != null ? m.Groups["processaddress"].Value : "" + (processadd2.IndexOf("            ") > -1 ? " " + processadd2.Split(new string[] { "            " }, StringSplitOptions.None)[0] : "");
                var filerstreet = (fileradd2.IndexOf("            ") > -1 ? " " + fileradd2.Split(new string[] { "            " }, StringSplitOptions.RemoveEmptyEntries)[1] : fileradd2);
                var processstreet = (processadd2.IndexOf("            ") > -1 ? " " + processadd2.Split(new string[] { "            " }, StringSplitOptions.RemoveEmptyEntries)[1] : processadd2);
                var cityMatchFiler = city.Match(m.Groups["zip"] != null ? m.Groups["zip"].Value : "");
                var cityMatchProcess = city.Match(m.Groups["processzip"] != null ? m.Groups["processzip"].Value : "");

                var d = new DocEntity
                {
                    County = m.Groups["county"] != null ? m.Groups["county"].Value.Trim() : "",
                    EFFDate = m.Groups["effdate"] != null && !string.IsNullOrWhiteSpace(m.Groups["effdate"].Value) ? DateTime.Parse(m.Groups["effdate"].Value) : DateTime.MinValue,
                    FILER_ADDRESS = address.Trim(),
                    FILER_CITY = cityMatchFiler.Groups["city"] != null ? cityMatchFiler.Groups["city"].Value.Trim() : "",
                    FILER_STATE = cityMatchFiler.Groups["state"] != null ? cityMatchFiler.Groups["state"].Value.Trim() : "",
                    FILER_STREET = filerstreet.Trim(),
                    FILER_ZIP = cityMatchFiler.Groups["zip"] != null && !string.IsNullOrWhiteSpace(cityMatchFiler.Groups["zip"].Value) ? int.Parse(cityMatchFiler.Groups["zip"].Value) : 0,
                    FillingNumber = m.Groups["filling"] != null ? m.Groups["filling"].Value.Trim() : "",
                    LLC_NAME = m.Groups["name"] != null ? m.Groups["name"].Value.Trim() : "",
                    LLCType = title.Trim(),
                    ProcessAddress = processaddress.Trim(),
                    ProcessCity = cityMatchProcess.Groups["city"] != null ? cityMatchProcess.Groups["city"].Value.Trim() : "",
                    ProcessState = cityMatchProcess.Groups["state"] != null ? cityMatchProcess.Groups["state"].Value.Trim() : "",
                    ProcessStreet = processstreet.Trim(),
                    ProcessZIP = cityMatchProcess.Groups["zip"] != null && !string.IsNullOrWhiteSpace(cityMatchProcess.Groups["zip"].Value) ? int.Parse(cityMatchProcess.Groups["zip"].Value) : 0,
               };
               results.Add(d);
           }
       }
   }           
   dataGridView1.DataSource = results;
}

以下是文字示例：

 170914000673 FRESH TRESSES LLC
 LAW : 206 LLC *FILER ADDRESS / PROCESS ADDRESS*
 COUNTY : QUEE EZ LEGAL PUBLISHING LLC
 EFF. DATE: 09/14/2017 244 FIFTH AVENUE SUITE 2503
 DUR. DATE: NEW YORK, NY 10001
170914000215 FYATIKTK, LLC
 LAW : 206 LLC *FILER ADDRESS / PROCESS ADDRESS*
 COUNTY : KING PABLO G. VELEZ, ESQ.
 EFF. DATE: 09/14/2017 VELEZ & CIPRIANO, PLLC 347 5TH AVENUE STE 810
 DUR. DATE: NEW YORK, NY 10016
170914000676 GLOBAL PROPERTY GROUP LLC
 LAW : 206 LLC *FILER ADDRESS / PROCESS ADDRESS*
 COUNTY : ROCK ALLSTATE CORPORATE SERVICES CORP.
 EFF. DATE: 09/14/2017 ONE COMMERCE PLAZA 99 WASHINGTON AVENUE, SUITE 1008
 DUR. DATE: ALBANY, NY 12260
170914000075 GNU SECURITIES LLC
 LAW : 206 LLC *FILER ADDRESS / PROCESS ADDRESS*
 COUNTY : ALBA INTEGRATED MANAGEMENT
 EFF. DATE: 09/14/2017 SOLUTIONS USA LLC 39 BROADWAY, STE 3300
 DUR. DATE: NEW YORK, NY 10006
170914000129 HIGH HILL ASSOCIATES LLC
 LAW : 206 LLC *FILER ADDRESS / PROCESS ADDRESS*
 COUNTY : WEST JOHN MORELLO
 EFF. DATE: 09/14/2017 3 HIGH HILL FARM PL
 DUR. DATE: THORNWOOD, NY 10594
170914000151 HOLLY SLEPT OVER, LLC
 LAW : 206 LLC *FILER ADDRESS / PROCESS ADDRESS*
 COUNTY : ONON GERMAIN & GERMAIN
 EFF. DATE: 09/14/2017 314 E FAYETTE STREET
 DUR. DATE: SYRACUSE, NY 13202

Answer 1

尝试(?<city>[^,]+),

这将捕获任何不是逗号的内容并将其保存为命名捕获“city”

你也可以尝试类似于负面前瞻的东西：

(?<city>(?!,\s+).+)

不是c＃程序员，但我涉猎正则表达式：D

正确的城市正则表达

修改

1 个答案: