dotnet下的采集

ゝ一纸荒年。 2022-07-14 03:11 142阅读 0赞

一、工具
    NCrawler
    http://ncrawler.codeplex.com/
    
    Html Agility Pack
    http://htmlagilitypack.codeplex.com/
    
    ScrapySharp
    https://bitbucket.org/rflechner/scrapysharp
    
    Quartz.NET
    http://www.quartz-scheduler.net/
    
    二、先看几个基本的
    //demo:基础案例
    using NCrawler;
    using NCrawler.Interfaces;
    using NCrawler.HtmlProcessor;
    
    public class DumperStep : IPipelineStep  
    {  
        public void Process(Crawler crawler, PropertyBag propertyBag)  
        {  
            Console.WriteLine(propertyBag.Step.Uri);  
        }  
    }
    
    class Program
    {  
        static void Main(string[] args)  
        {  
            Uri uri = new Uri("http://www.csdn.net/");  
            Crawler c = new Crawler(uri,new HtmlDocumentProcessor(),new DumperStep());  
            c.MaximumThreadCount = 3;//线程数量  
            c.MaximumCrawlDepth = 2;//爬行深度  
        c.BlackListedUriRegexMatchers = new [] { new Regex(@"(\.jpg|\.css|\.js|\.gif|\.jpeg|\.png)", RegexOptions.Compiled | RegexOptions.CultureInvariant | RegexOptions.IgnoreCase) }; 
            c.Crawl();//开始爬行  
        }  
    }  
    
    
    
    //demo:死链检查完整代码
    public class InvalidLinkDetector 
    { 
        private XmlDocument _writerDoc = null; 
        private Crawler _crawler = null; 
    
        public InvalidLinkDetector(string DetectUrl, int MaxThreadCount, int MaxCrawlDepth) 
        { 
            this._writerDoc = new XmlDocument(); 
            this._writerDoc.LoadXml("<invalidUrls></invalidUrls>"); 
    
            this._crawler = new Crawler(DetectUrl, new HtmlDocumentProcessor(), new ScanResultWriter(this._writerDoc)) 
            { 
                MaximumThreadCount = MaxThreadCount, 
                MaximumCrawlDepth = MaxCrawlDepth 
            }; 
    
            this._crawler.CrawlFinished += new EventHandler<NCrawler.Events.CrawlFinishedEventArgs>(CrawlFinished); 
            this._crawler.PipelineException += new EventHandler<NCrawler.Events.PipelineExceptionEventArgs>(PipelineException); 
        } 
    
        public void Run() 
        { 
            this._crawler.Crawl(); 
        } 
    
        private void PipelineException(object sender, NCrawler.Events.PipelineExceptionEventArgs e) 
        { 
            Console.WriteLine("Exception occurred in pipeline: {0}, message: {1}", e.PropertyBag.Step.GetType().Name, e.Exception.Message); 
        } 
    
        private void CrawlFinished(object sender, NCrawler.Events.CrawlFinishedEventArgs e) 
        { 
            this._writerDoc.Save(Environment.CurrentDirectory + @"\" + DateTime.Now.ToString("yyyyMMdd HHmmss") + ".xml"); 
            this._writerDoc = null; 
        } 
    } 
    
    public class ScanResultWriter : IPipelineStep 
    { 
        private XmlDocument _writerDoc = null; 
    
        public ScanResultWriter(XmlDocument doc) 
        { 
            this._writerDoc = doc; 
        } 
    
        public void Process(Crawler crawler, PropertyBag propertyBag) 
        { 
            if (propertyBag.StatusCode != HttpStatusCode.OK) 
            { 
                Console.WriteLine("Find a invalid link..."); 
    
                XmlNode node = this._writerDoc.CreateNode(XmlNodeType.Element, "invalidUrl", null); 
                XmlNode nodeUrl = this._writerDoc.CreateNode(XmlNodeType.Attribute, "url", null); 
                XmlNode nodeReferUrl = this._writerDoc.CreateNode(XmlNodeType.Attribute, "refer", null); 
                XmlNode nodeReason = this._writerDoc.CreateNode(XmlNodeType.Attribute, "reason", null); 
    
                nodeUrl.Value = propertyBag.OriginalUrl; 
                nodeReferUrl.Value = propertyBag.OriginalReferrerUrl; 
                nodeReason.Value = ((int)propertyBag.StatusCode).ToString(); 
    
                node.Attributes.SetNamedItem(nodeUrl); 
                node.Attributes.SetNamedItem(nodeReferUrl); 
                node.Attributes.SetNamedItem(nodeReason); 
    
                this._writerDoc.DocumentElement.AppendChild(node); 
            } 
        } 
    }
    
    
    static void Main(string[] args) 
    { 
        Console.WriteLine("Scanning..."); 
        InvalidLinkDetector detector = new InvalidLinkDetector("http://msdn.microsoft.com", 10, 4); 
        detector.Run(); 
    }
    
    三、html解析
    
    demo：基本使用方法
    static void Main(string[] args) 
            { 
                var uri = new Uri("http://www.cnblogs.com/shanyou/archive/2012/05/20/2509435.html"); 
                var browser1 = new ScrapingBrowser(); 
                var html1 = browser1.DownloadString(uri); 
                var htmlDocument = new HtmlDocument(); 
                htmlDocument.LoadHtml(html1); 
                var html = htmlDocument.DocumentNode;
    
                var title = html.CssSelect("title"); 
                foreach (var htmlNode in title) 
                { 
                    Console.WriteLine(htmlNode.InnerHtml); 
                } 
                var divs = html.CssSelect("div.postBody");
    
                foreach (var htmlNode in divs) 
                { 
                    Console.WriteLine(htmlNode.InnerHtml); 
                }
    
                divs = html.CssSelect("#cnblogs_post_body"); 
                foreach (var htmlNode in divs) 
                { 
                    Console.WriteLine(htmlNode.InnerHtml); 
                } 
            } 
    
    
    
    示例：像一个浏览器一样
    ScrapingBrowser browser = new ScrapingBrowser();
    
    //set UseDefaultCookiesParser as false if a website returns invalid cookies format
    //browser.UseDefaultCookiesParser = false;
    
    WebPage homePage = browser.NavigateToPage(new Uri("http://www.bing.com/"));
    
    PageWebForm form = homePage.FindFormById("sb_form");
    form["q"] = "scrapysharp";
    form.Method = HttpVerb.Get;
    WebPage resultsPage = form.Submit();
    
    HtmlNode[] resultsLinks = resultsPage.Html.CssSelect("div.sb_tlst h3 a").ToArray();
    
    WebPage blogPage = resultsPage.FindLinks(By.Text("romcyber blog | Just another WordPress site")).Single().Click();
    
    
    参考：
    https://msdn.microsoft.com/zh-tw/ee939355
    http://ncrawler.codeplex.com