使用 C# 从 HTML 页面中提取一些内容及其对应的 Xpath

Question

我有一个 HTML 文件，其内容如下：

</div><div class="\"more-detail-caption\"">More Numbers :</div><div id="\"moreHLNumbers\"" title="\"HSBC" bank="" helpline="" number\"="" class="\"more-detail-text\""><a href='tel:18605002277'>1860 500 2277 </a><a class='cchlOtherNoDescription'>( Credit Card - From India )</a><br><a href='tel:18602662667'>1860 266 2667 </a><a class='cchlOtherNoDescription'>( Personal Banking - From India )</a><br><a href='tel:18605002255'>1860 500 2255 </a><a class='cchlOtherNoDescription'>( Personal Banking - From India )</a><br><a href='tel:18004192266'>1800 419 2266 </a><a class='cchlOtherNoDescription'>( Corporate Cards - From India )</a><br><a href='tel:18001026922'>1800 102 6922 </a><a class='cchlOtherNoDescription'>( Corporate Cards - From India )</a><br><a href='tel:18002673456'>1800 267 3456 </a><a class='cchlOtherNoDescription'>( HSBC Advance - From India )</a><br><a href='tel:18001022208'>1800 102 2208 </a><a class='cchlOtherNoDescription'>( HSBC Advance - From India )</a><br><a href='tel:18002663456'>1800 266 3456 </a><a class='cchlOtherNoDescription'>( HSBC Premier - From India )</a><br><a href='tel:18001034722'>1800 103 4722 </a><a class='cchlOtherNoDescription'>( HSBC Premier - From India )</a><br><a href='tel:+912266800001'>022 66800001 </a><a class='cchlOtherNoDescription'>( Credit Card - From Overseas )

我想使用正则表达式及其描述来提取这些数字。例如： “1860 266 2667（个人银行业务 - 来自印度）”。除了它对应的xpath，使用c#。 到目前为止，我已经弄清楚了以下代码，它只是删除了额外的标签，并定义了用于提取数字的正则表达式。

    using System.IO;
using System.Linq;
using HtmlAgilityPack;
using System.Text.RegularExpressions;

namespace ConsoleApp1
{

    public class Program
    {

        private static string phoneReg = @"[\+]{0,1}(\d{10,13}|[\(][\+]{0,1}\d{2,}[\13)]*\d{5,13}|\d{2,6}[\-]{1}\d{2,13}[\-]*\d{3,13})";
        private static Regex phoneRegex = new Regex(phoneReg, RegexOptions.IgnoreCase);
        public static void Main()
        {

            HtmlDocument doc = new HtmlDocument();
            doc.Load(@"C:\htmldoc\htmlsample.html");
            doc.DocumentNode.Descendants()
                            .Where(n => n.Name == "script" || n.Name == "style" || n.Name == "svg" || n.Name == "button"
                                  || n.Name == "li" || n.Name == "link" || n.Name == "img" || n.Name == "head" || n.Name == "header" || n.Name == "input")
                            .ToList()
                            .ForEach(n => n.Remove());
            var phoneMatches = phoneRegex.Matches(doc.DocumentNode.InnerText);
            File.WriteAllText(@"C:\htmldoc\new.html", doc.DocumentNode.InnerHtml.Replace(@"\t", ""));
        }
    }
}

但是，我也面临一些提取数字的问题。 有人可以帮我解决这个问题吗？

提前致谢。

Answer 1

我不确定我的解决方案是否符合您的确切需求，但我认为应该很接近...

如果您愿意，可以使用在 MoreLinq 中定义的“ForEach”（而不是我的 ApplyForEachItem）。

作为参考，我使用https://regex101.com/ 进行我的reges 测试，这看起来很棒。

using System.IO;
using System.Linq;
using HtmlAgilityPack;
using System.Text.RegularExpressions;
using System.Diagnostics;
using System.Collections.Generic;
using System;

namespace SoQuestion
{
    class Program
    {
        // private static string phoneReg = @"[\+]{0,1}(\d{10,13}|[\(][\+]{0,1}\d{2,}[\13)]*\d{5,13}|\d{2,6}[\-]{1}\d{2,13}[\-]*\d{3,13})";

        private static string phoneReg = @"\s+\d[ \d]+\r\n.+\r\n";

        private static Regex phoneRegex = new Regex(phoneReg, RegexOptions.IgnoreCase);
        public static void Main(string[] args)
        {
            HtmlDocument doc = new HtmlDocument();
            doc.Load(@"C:\temp\HTMLPage1.html");
            doc.DocumentNode.Descendants()
                            .Where(n => n.Name == "script" || n.Name == "style" || n.Name == "svg" || n.Name == "button"
                                  || n.Name == "li" || n.Name == "link" || n.Name == "img" || n.Name == "head" || n.Name == "header" || n.Name == "input")
                            .ToList()
                            .ForEach(n => n.Remove());
            var phoneMatches = phoneRegex.Matches(doc.DocumentNode.InnerText);

            List<Tuple<string, string>> data = new List<Tuple<string, string>>();

            ApplyForEachItem(phoneMatches, match =>
            {
                int indexFirstDigit = match.Value.IndexOfAny(new char[]{'1', '2', '3', '4', '5', '6', '7', '8', '9', '0' });

                string[] phoneAndDesc = match.Value.Substring(indexFirstDigit).Split("\r\n");
                data.Add(new Tuple<string, string>(phoneAndDesc[0].Trim(), phoneAndDesc[1].Trim()));
            });

            ApplyForEachItem(data, item => Debug.Print($"Phone: '{item.Item1}', Desc = '{item.Item2}' \r\n"));
        }

        public static void ApplyForEachItem<T>(IEnumerable<T> enumerable, Action<T> action)
        {
            if (enumerable == null)
            {
                return;
            }

            foreach (T t in enumerable)
            {
                action(t);
            }
        }
    }
}

结果：

Phone: '1860 500 2277', Desc = '( Credit Card - From India )' 
Phone: '1860 266 2667', Desc = '( Personal Banking - From India )' 
Phone: '1860 500 2255', Desc = '( Personal Banking - From India )' 
Phone: '1800 419 2266', Desc = '( Corporate Cards - From India )' 
Phone: '1800 102 6922', Desc = '( Corporate Cards - From India )' 
Phone: '1800 267 3456', Desc = '( HSBC Advance - From India )' 
Phone: '1800 102 2208', Desc = '( HSBC Advance - From India )' 
Phone: '1800 266 3456', Desc = '( HSBC Premier - From India )' 
Phone: '1800 103 4722', Desc = '( HSBC Premier - From India )' 
Phone: '022 66800001', Desc = '( Credit Card - From Overseas )'