.net使用abot爬蟲簡單例子

abot是.net爬蟲架構中的一種，Abot是一個開源的.net爬蟲，速度快，易于使用和擴充。項目的位址是https://code.google.com/p/abot/。

爬取的html解析，我們使用AngleSharp,項目的位址：https://github.com/AngleSharp/AngleSharp

首先我們需要配置abot

private static readonly Uri FeedUrl = new Uri("https://www.jd.com/allSort.aspx");//定義一個爬取的url，這裡以京東商品的分類為例子      

public static IWebCrawler GetManuallyConfiguredWebCrawler()
        {
            //這裡進行配置，具體的含義自己看源代碼了解
            CrawlConfiguration config = new CrawlConfiguration();
            config.MaxConcurrentThreads = System.Environment.ProcessorCount;
            config.MaxPagesToCrawl = 1000;
            config.IsExternalPageCrawlingEnabled = false;
            config.IsUriRecrawlingEnabled = false;
            config.IsExternalPageLinksCrawlingEnabled = false;
            config.IsRespectRobotsDotTextEnabled = false;
            config.DownloadableContentTypes = "text/html, text/plain";
            config.MinCrawlDelayPerDomainMilliSeconds = 1000;
            config.CrawlTimeoutSeconds = 0;
            config.MaxPagesToCrawlPerDomain = 0;

            var crawler = new PoliteWebCrawler(config, null, null, null, null, null, null, null, null);

            //爬取頁面前的判斷
            crawler.ShouldCrawlPage(ShouldCrawlPage);
            crawler.ShouldDownloadPageContent(ShouldDownloadPageContent);
            crawler.ShouldCrawlPageLinks(ShouldCrawlPageLinks);

            //下面是爬取的四個事件
            crawler.PageCrawlStartingAsync += crawler_ProcessPageCrawlStarting;//單個頁面爬取開始 
            crawler.PageCrawlCompletedAsync += crawler_ProcessPageCrawlCompletedAsync;//單個頁面爬取結束 
            // crawler.PageCrawlDisallowedAsync += crawler_PageCrawlDisallowed;// 頁面連結不允許爬取事件
            //crawler.PageLinksCrawlDisallowedAsync += crawler_PageLinksCrawlDisallowed;//頁面不允許爬取事件 
            return crawler;
        }      

爬蟲中主要是4個事件, 頁面爬取開始、頁面爬取失敗、頁面不允許爬取事件、頁面中的連結不允許爬取事件.

以下是示例

//單個頁面爬取開始 
        public static void crawler_ProcessPageCrawlStarting(object sender, PageCrawlStartingArgs e)
        {
            PageToCrawl pageToCrawl = e.PageToCrawl;

        }
        //單個頁面爬取結束 
        public static void crawler_ProcessPageCrawlCompletedAsync(object sender, PageCrawlCompletedArgs e)
        {
            if (e.CrawledPage.Uri == FeedUrl)
            {
                StringBuilder sb=new StringBuilder();
               //這裡使用AngleSharp解析html
                var all=e.CrawledPage.AngleSharpHtmlDocument.QuerySelector(".category-items").Children;
                foreach (var col in all)
                {
                    var categorys=col.QuerySelectorAll(".category-item");
                    foreach (var category in categorys)
                    {
                        var first=category.QuerySelector(".item-title span").Text();
                        sb.Append("\r\n" + first + "\r\n");
                        var seconds = category.QuerySelector(".items").Children;
                        foreach (var second in seconds)
                        {
                            var secondtext=second.QuerySelector("dt a").Text();
                            sb.Append(secondtext + "\t");
                            var thireds = second.QuerySelector("dd").Children;
                            foreach (var thired in thireds)
                            {
                                var thiredtext = thired.Text();
                                sb.Append(thiredtext + ",");
                            }
                            sb.Remove(sb.Length - 1, 1);
                        }
                    }
                }
                //爬取的資料儲存到C:\Program Files (x86)\IIS Express下面。注意這裡儲存可能需要以管理者的身份運作VS
                System.IO.File.AppendAllText("fake.txt", sb.ToString());
            }
        }

        #region
        /// <summary>
        /// 同步方法注冊一個委托，以确定是否應該抓取一個頁面
        /// </summary>
        /// <param name="pageToCrawl"></param>
        /// <param name="crawlContext"></param>
        /// <returns></returns>
        public static CrawlDecision ShouldCrawlPage(PageToCrawl pageToCrawl, CrawlContext crawlContext)
        {
            if (pageToCrawl.IsRetry || pageToCrawl.IsRoot || FeedUrl == pageToCrawl.Uri )//判斷是否為根Url,爬取的Url是否為我們指定的
            {
                return new CrawlDecision() { Allow = true };
            }
            else
            {
                return new CrawlDecision { Allow = false, Reason = "Not match uri" };//如果為false,就不爬取頁面
            }
        }

        /// <summary>
        /// 同步方法注冊一個委托，以确定頁面的内容是否應該被加載
        /// </summary>
        /// <param name="pageToCrawl"></param>
        /// <param name="crawlContext"></param>
        /// <returns></returns>
        private static CrawlDecision ShouldDownloadPageContent(PageToCrawl pageToCrawl, CrawlContext crawlContext)
        {
            if (pageToCrawl.IsRoot || pageToCrawl.IsRetry || FeedUrl == pageToCrawl.Uri)
            {
                return new CrawlDecision
                {
                    Allow = true
                };
            }

            return new CrawlDecision { Allow = false, Reason = "Not match uri" };
        }
        /// <summary>
        /// 同步方法注冊一個委托，以确定是否應該抓取一個頁面的連結
        /// </summary>
        /// <param name="crawledPage"></param>
        /// <param name="crawlContext"></param>
        /// <returns></returns>
        private static CrawlDecision ShouldCrawlPageLinks(CrawledPage crawledPage, CrawlContext crawlContext)
        {
            if (!crawledPage.IsInternal)
                return new CrawlDecision { Allow = false, Reason = "We dont crawl links of external pages" };

            if (crawledPage.IsRoot || crawledPage.IsRetry || crawledPage.Uri == FeedUrl)
            {
                return new CrawlDecision { Allow = true };
            }
            else
            {
                return new CrawlDecision { Allow = false, Reason = "We only crawl links of pagination pages" };
            }
        }
        #endregion      

 接下來就是測試

public ActionResult Index()
        {
            var crawler = GetManuallyConfiguredWebCrawler();
            var reuslt = crawler.Crawl(FeedUrl);
            Response.Write(reuslt.ErrorException);
            return View();
        }