Question

我正在将HTML表格行解析为文本文件。我只需要前两列，在我的情况下td[1]和td[2]。我希望输出格式如下，以便我以后可以将它们插入到MySQL数据库中。

Mon, Monday
Tue, Tuesday
Wed, Wednesday

但我目前的文本文件输出如下，我仍然不知道如何在互联网上搜索解决方案后修复它。我想保留下面的格式，但我根本不知道如何在MySQL数据库的每个数据库行中将“Mon”插入column1和“Monday”到column2。

Mon,
Monday
Tue,
Tuesday
Wed,
Wednesday

这是我的代码：

private void btn_parse_Click(object sender, EventArgs e)
{
    string FileName = @"..\..\bin\Debug\htm\allaim.htm";

    HtmlAgilityPack.HtmlDocument doc = new HtmlAgilityPack.HtmlDocument();
    doc.Load(FileName);

        HtmlNodeCollection tables = doc.DocumentNode.SelectNodes("//table");

        HtmlNodeCollection rows = tables[3].SelectNodes(".//tr");
        for (int i = 0; i < rows.Count; ++i)
        {
            HtmlNodeCollection cols = rows[i].SelectNodes(".//td[1]");
            for (int j = 0; j < cols.Count; ++j)
            {
                string value = cols[j].InnerText;
                FileStream fs = new FileStream(@"..\..\bin\Debug\txt\" + "allaim.txt", FileMode.Append);
                StreamWriter sw = new StreamWriter(fs);
                sw.WriteLine(value + ",");
                sw.Flush();
                sw.Close();
                fs.Close();
            }

            HtmlNodeCollection cols2 = rows[i].SelectNodes(".//td[2]");
            for (int j = 0; j < cols2.Count; ++j)
            {
                string value = cols2[j].InnerText;
                FileStream fs = new FileStream(@"..\..\bin\Debug\txt\" + "allaim.txt", FileMode.Append);
                StreamWriter sw = new StreamWriter(fs);
                sw.WriteLine(value);
                sw.Flush();
                sw.Close();
                fs.Close();
            }   
        }
        MessageBox.Show("Done writing!");
    }

也许我这样做的方式不对，我是C＃winforms的新手。任何帮助将不胜感激，谢谢你提前！：）

Answer 1

在StreamWriter.Write()中使用for loop而不是StreamWriter.WriteLine()。

试试这个：

private void btn_parse_Click(object sender, EventArgs e)
{
    string FileName = @"..\..\bin\Debug\htm\allaim.htm";

    HtmlAgilityPack.HtmlDocument doc = new HtmlAgilityPack.HtmlDocument();
    doc.Load(FileName);

        HtmlNodeCollection tables = doc.DocumentNode.SelectNodes("//table");

        HtmlNodeCollection rows = tables[3].SelectNodes(".//tr");
        for (int i = 0; i < rows.Count; ++i)
        {
            HtmlNodeCollection cols = rows[i].SelectNodes(".//td[1]");
            for (int j = 0; j < cols.Count; ++j)
            {
                string value = cols[j].InnerText;
                FileStream fs = new FileStream(@"..\..\bin\Debug\txt\" + "allaim.txt", FileMode.Append);
                StreamWriter sw = new StreamWriter(fs);
                sw.Write(value + ",");//use Write() instead of WriteLine()
                sw.Flush();
                sw.Close();
                fs.Close();
            }

            HtmlNodeCollection cols2 = rows[i].SelectNodes(".//td[2]");
            for (int j = 0; j < cols2.Count; ++j)
            {
                string value = cols2[j].InnerText;
                FileStream fs = new FileStream(@"..\..\bin\Debug\txt\" + "allaim.txt", FileMode.Append);
                StreamWriter sw = new StreamWriter(fs);
                sw.WriteLine(value);
                sw.Flush();
                sw.Close();
                fs.Close();
            }   
        }
        MessageBox.Show("Done writing!");
    }

Answer 2

最好准备要写的整个字符串。并且还只打开一次文件。并对using个对象使用IDisposable关键字。试试这个：

private void btn_parse_Click(object sender, EventArgs e)
{
    string FileName = @"..\..\bin\Debug\htm\allaim.htm";

    HtmlAgilityPack.HtmlDocument doc = new HtmlAgilityPack.HtmlDocument();
    doc.Load(FileName);

    HtmlNodeCollection tables = doc.DocumentNode.SelectNodes("//table");

    using(FileStream fs = new FileStream(@"..\..\bin\Debug\txt\" + "allaim.txt", FileMode.Append))
    using(StreamWriter sw = new StreamWriter(fs))
    {
        HtmlNodeCollection rows = tables[3].SelectNodes(".//tr");
        for (int i = 0; i < rows.Count; ++i)
        {
            HtmlNodeCollection cols = rows[i].SelectNodes(".//td[1]");
            HtmlNodeCollection cols2 = rows[i].SelectNodes(".//td[2]");
            for (int j = 0; j < cols.Count; ++j)
                sw.WriteLine("'" + cols[j].InnerText + "','" + cols2[j].InnerText + "'");
        }
        sw.Flush();
        sw.Close();
        fs.Close();
        MessageBox.Show("Done writing!");
    }
}

如果不是您正在寻找的答案，那么我道歉。

将文本附加到右侧而不是新行

2 个答案: