Question

班级ParserWorker
WorkerHTMLFile()方法遍历列表。
列表ListUrlActive包含4行。

ParsingPage(string source)方法将稀疏页面发送到SiteParser类。

班级SiteParser
执行Parsing(IHtmlDocument document)，break之后的方法case "Type_2"：中断代码的执行。

如果我理解正确，则代码的执行应返回到ParserWorker类，返回到WorkerHTMLFile()循环中的for方法。

并执行“ ListUrlActive”列表的下一行，但这不会发生。该代码仅处理第一行，并终止break case "Type_2"

上代码的执行

问题。
在执行break和case "Type_2"之后，如何使代码继续工作？

class ParserWorker
        {
            public void WorkerHTMLFile()
            {
                for (int i = 0; i <= ListUrlActive.Count; i++)
                {
                    string source = File.ReadAllText(ListUrlActive[i]);                
                    ParsingPage(source);
                }
            }

            public async void ParsingPage(string source)
            {
                var domParser = new HtmlParser();

                IHtmlDocument document = await domParser.ParseAsync(source);

                siteParser.Parsing(document);
            }
        }

        public class SiteParser
        {
            public async void Parsing(IHtmlDocument document)
            {
                switch (objectParsing)
                {
                    case "Type_1":
                        /// ...
                        /// ... Code
                        /// ...

                        break;

                    case "Type_2":                    
                        var domParserAnnounc = new HtmlParser();
                        var htmlBlockAnnounc = document.QuerySelectorAll("div.flexRoot > div.view.main");

                        foreach (var item in htmlBlockAnnounc)
                        {
    string s = item.OuterHtml;
                            IHtmlDocument documentCur = await domParserAnnounc.ParseAsync(s);

                            ParsingPoster(documentCur);
                        }
                        break;
                }
            }
        }

public async void ParsingPoster(IHtmlDocument document)
        {

            try
            {

             try
                {
                     email = document.QuerySelectorAll("#start_widget > div:nth-child(3) > div.form-line.view-form-line > div.adv-point.view-adv-point > script:nth-child(3)")[0].TextContent.Trim();

                    email = wordProcessing.FindRegularExpression(email, @"(?<=eval\(unescape\(').*(?='\)\))");
                    email = wordProcessing.DecodeResult(email);

                    IHtmlDocument htmlDocumentEmail = await domParser.ParseAsync(email);                 
                    var itemsAttr = htmlDocumentEmail.QuerySelectorAll("a"); 
                    email = itemsAttr[0].TextContent.Trim();

                }
                catch (Exception ex)
                {
                    InfoMessageErrorEvent?.Invoke("Поле: 'email'. Error !!!" + ex.Message);
                }
            }
            catch (Exception ex)
            {
                string s1 = ex.Message;
                string s2 = ex.StackTrace;
                // throw;
            }


        }

更新_1
ParserWorker类

WorkerHTMLFile ()方法
它是：public void WorkerHTMLFile ()
它变成了：public async void WorkerHTMLFile ()
更改了方法的组成。

ParsingPage (string source)方法
它是：public async void ParsingPage (string source)
它变成了：public async Task <IHtmlDocument> ParsingPage (string source)
更改了方法的组成。

班级SiteParser
方法Parsing (IHtmlDocument document)
它是：public async void Parsing (IHtmlDocument document)
发件人：public async Task Parsing (IHtmlDocument document)

原来是：ParsingPoster (documentCur);
现在：await ParsingPoster (documentCur);

代码

class ParserWorker
{
    public async void WorkerHTMLFile()
    {
        for (int i = 0; i <= ListUrlActive.Count; i++)
        {
            string source = File.ReadAllText(ListUrlActive[i]);                

            IHtmlDocument document = await ParsingPage(source);

            await siteParser.Parsing(document);

        }
    }

    public async Task<IHtmlDocument> ParsingPage(string source)
    {
        IHtmlDocument document = null;
        try
        {
            var domParser = new HtmlParser();

            IHtmlDocument document = await domParser.ParseAsync(source);

            document = await siteParser.Parsing(document);      
        }
        catch (Exception ex)
        {
                string s = ex.Message;
                string s1 = ex.StackTrace;
                // throw;
        }
        return document;
    }
}

public class SiteParser
{
    public async Task Parsing(IHtmlDocument document)
    {
        switch (settingOper.objectParsing)
        {
            case "Type_1":
                /// ...
                /// ... Code
                /// ...

                break;

            case "Type_2":                    
                var domParserAnnounc = new HtmlParser();
                var htmlBlockAnnounc = document.QuerySelectorAll("div.flexRoot > div.view.main");

                foreach (var item in htmlBlockAnnounc)
                {
                    string s = item.OuterHtml;
                    IHtmlDocument documentCur = await domParserAnnounc.ParseAsync(s);

                    await ParsingPoster(documentCur);
                }
                break;
        }
    }
}

public async void ParsingPoster(IHtmlDocument document)
        {

            try
            {

             try
                {
                     email = document.QuerySelectorAll("#start_widget > div:nth-child(3) > div.form-line.view-form-line > div.adv-point.view-adv-point > script:nth-child(3)")[0].TextContent.Trim();

                    email = wordProcessing.FindRegularExpression(email, @"(?<=eval\(unescape\(').*(?='\)\))");
                    email = wordProcessing.DecodeResult(email);

                    IHtmlDocument htmlDocumentEmail = await domParser.ParseAsync(email);                 
                    var itemsAttr = htmlDocumentEmail.QuerySelectorAll("a"); 
                    email = itemsAttr[0].TextContent.Trim();

                }
                catch (Exception ex)
                {
                    InfoMessageErrorEvent?.Invoke("Поле: 'email'. Error !!!" + ex.Message);
                }

                //...
                // ... Parsing additional fields ...
                //...
            }
            catch (Exception ex)
            {
                string s1 = ex.Message;
                string s2 = ex.StackTrace;
                // throw;
            }
        }

Answer 1

这是可以帮助您的更新代码：

class ParserWorker
{
    public void WorkerHTMLFile()
    {
        for (int i = 0; i <= ListUrlActive.Count; i++)
        {
            string source = File.ReadAllText(ListUrlActive[i]);
            ParsingPage(source);
        }
    }

    public async void ParsingPage(string source)
    {
        var domParser = new HtmlParser();

        IHtmlDocument document = await domParser.ParseAsync(source);

        siteParser.Parsing(document);
    }
}

public class SiteParser
{
    public async void Parsing(IHtmlDocument document)
    {
        switch (settingOper.objectParsing)
        {
            case "Type_1":
                /// ...
                /// ... Code
                /// ...

                break;

            case "Type_2":
                var domParserAnnounc = new HtmlParser();
                var htmlBlockAnnounc = document.QuerySelectorAll("div.flexRoot > div.view.main");

                foreach (var item in htmlBlockAnnounc)
                {
                    string s = item.OuterHtml;
                    IHtmlDocument documentCur = await domParserAnnounc.ParseAsync(s);

                    await ParsingPoster(documentCur);
                }
                break;
        }
    }
}

public async void ParsingPoster(IHtmlDocument document)
{

    try
    {

        try
        {
            settingOper.email = document.QuerySelectorAll("#start_widget > div:nth-child(3) > div.form-line.view-form-line > div.adv-point.view-adv-point > script:nth-child(3)")[0].TextContent.Trim();

            if (settingOper.email == null)
            {
                settingOper.email = document.QuerySelectorAll("div[class='adv-point view-adv-point']>script[type*='text/javascript']")[0].TextContent.Trim();
            }
            settingOper.email = wordProcessing.FindRegularExpression(settingOper.email, @"(?<=eval\(unescape\(').*(?='\)\))");
            settingOper.email = wordProcessing.DecodeResult(settingOper.email);

            IHtmlDocument htmlDocumentEmail = await domParser.ParseAsync(settingOper.email);
            var itemsAttr = htmlDocumentEmail.QuerySelectorAll("a");
            settingOper.email = itemsAttr[0].TextContent.Trim();

        }
        catch (Exception ex)
        {
            InfoMessageErrorEvent?.Invoke("Поле: 'email'. Error !!!" + ex.Message);
        }
    }
    catch (Exception ex)
    {
        string s1 = ex.Message;
        string s2 = ex.StackTrace;
        // throw;
    }


}

我主要在某些地方为您解决了异步等待问题。

执行完“ switch”-“ break”代码后如何继续工作？

1 个答案: