当前位置: 首页>>代码示例>>C#>>正文


C# HtmlWeb.Load方法代码示例

本文整理汇总了C#中HtmlAgilityPack.HtmlWeb.Load方法的典型用法代码示例。如果您正苦于以下问题:C# HtmlWeb.Load方法的具体用法?C# HtmlWeb.Load怎么用?C# HtmlWeb.Load使用的例子?那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在HtmlAgilityPack.HtmlWeb的用法示例。


在下文中一共展示了HtmlWeb.Load方法的15个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的C#代码示例。

示例1: datascraper

        public datascraper()
        {
            string url = @"http://www.bbc.co.uk/sport/football/results/partial/competition-118996114";
            HtmlWeb htmlWeb = new HtmlWeb();
            HtmlDocument doc = new HtmlDocument{ OptionUseIdAttribute = true };

            doc = htmlWeb.Load(url);
            HtmlNodeCollection mtchrslts = doc.DocumentNode.SelectNodes("//tr[@id]");

            string date;
            string ateam;
            string hteam;
            string score;
            string idmess;
            string idnum;
            string[] teamscores;
            string teamscoreh;
            string teamscorea;

            foreach (HtmlNode matchresult in mtchrslts)
            {
                idmess = matchresult.SelectSingleNode("//tr[@id]").Id;
                idnum = idmess.Replace("match-row-", "");
                score = matchresult.SelectSingleNode("//abbr[@title='Score']").InnerText;
                teamscores = score.Split('-');
                teamscoreh = teamscores[0];
                teamscorea = teamscores[1];
                hteam = matchresult.SelectSingleNode("//p[(@class='team-home teams')]").InnerText;
                ateam = matchresult.SelectSingleNode("//p[(@class='team-away teams')]").InnerText;
                date = matchresult.SelectSingleNode("//td[(@class='match-date')]").InnerText;
            }

            return;
        }
开发者ID:mrwebed,项目名称:take1-minimumpoints4safety,代码行数:34,代码来源:datascraperController.cs

示例2: Download

        static void Download()
        {
            List<Vogel> voegel = new List<Vogel>();

            Directory.CreateDirectory(IMAGES_FOLDER);

            Uri baseUri = new Uri("http://www.vogelwarte.ch");

            HtmlWeb web = new HtmlWeb();

            Uri queryUri = new Uri(baseUri, "voegel-der-schweiz.html?keyword=&mode=name%2CnameL&showPage=0&length=0&lang=de&exampleSearch=0");
            Console.WriteLine(queryUri);
            var docQuery = web.Load(queryUri.ToString());
            foreach(var elEntry in docQuery.DocumentNode.SelectNodes("//table[@class=\"list\"]/tr[@class=\"listEntry\"]/td/h3/a"))
            {
                Uri uriEntry = new Uri(baseUri, Decode(elEntry.Attributes["href"].Value));
                Console.WriteLine(uriEntry);
                var docEntry = web.Load(uriEntry.ToString());

                var nodeDetail = docEntry.DocumentNode.SelectSingleNode("//div[@id=\"birdDetail\"]");

                Vogel vogel = new Vogel {
                    Name = Decode(elEntry.InnerText),
                    Gruppe =  Decode(nodeDetail.SelectSingleNode("//td[strong/text()=\"Vogelgruppe:\"]").LastChild.InnerText),
                    Lebensraum = Decode(nodeDetail.SelectSingleNode("//td[strong/text()=\"Lebensraum:\"]").LastChild.InnerText),
                    Laenge = Decode(nodeDetail.SelectSingleNode("//td[strong/text()=\"Länge (cm):\"]").LastChild.InnerText),
                    Bilder = nodeDetail.SelectNodes("//div[@id=\"gallery\"]/div/img").Select(nodeImg => new Bild
                                                                                                                {
                                                                                                                    Titel = Decode(nodeImg.Attributes["title"].Value),
                                                                                                                    Source = new Uri(baseUri, Decode(nodeImg.Attributes["src"].Value)).ToString()
                                                                                                                }).ToArray()
                };

                voegel.Add(vogel);

                foreach(var bild in vogel.Bilder)
                {
                    using(var client = new WebClient())
                    {
                        Console.WriteLine(bild.Source);

                        string strFile =  Path.GetFileName(bild.Source);
                        client.DownloadFile(bild.Source, IMAGES_FOLDER + "/" + strFile);
                        bild.Source = strFile;
                    }
                }
            }

            JavaScriptSerializer serializer = new JavaScriptSerializer();
            using(StreamWriter sr = File.CreateText("data.js"))
            {
                sr.Write("var Voegel = ");
                sr.Write(serializer.Serialize(voegel.OrderBy(v => v.Name)));
                sr.Write(";\r\nvar Gruppen = ");
                sr.Write(serializer.Serialize(voegel.Select(v => v.Gruppe).Distinct().OrderBy(g => g)));
                sr.Write(";\r\nvar Lebensraeume = ");
                sr.Write(serializer.Serialize(voegel.SelectMany(v => v.Lebensraum.Split(',').Select(l => l.Trim())).Distinct().OrderBy(l => l)));
                sr.Write(";");
            }
        }
开发者ID:haeberli,项目名称:BirdMobile,代码行数:60,代码来源:Program.cs

示例3: Run

        public void Run()
        {
            HtmlWeb htmlWeb = new HtmlWeb();

            HtmlDocument htmlDocument = htmlWeb.Load(WebConstants.BASE_URL + mCarBrand.Url);
            HtmlNode logoNode = HtmlNode.CreateNode(htmlDocument.DocumentNode.SelectSingleNode(WebConstants.BRAND_LOGO).OuterHtml);
            mCarBrand.LogoUrl = logoNode.SelectSingleNode(WebConstants.IMAGE_SRC).Attributes[WebConstants.SRC].Value;
            //new Thread(new BrandLogoDownloadTask(mCarBrand).Download).Start();

            HtmlNode officialSiteNode = HtmlNode.CreateNode(htmlDocument.DocumentNode.SelectSingleNode(WebConstants.BRAND_OFFICIAL_SITE).OuterHtml);
            mCarBrand.OfficialSite = officialSiteNode.SelectSingleNode(WebConstants.LINK_HREF).Attributes[WebConstants.HREF].Value;
            HtmlNode countryNode = HtmlNode.CreateNode(htmlDocument.DocumentNode.SelectSingleNode(WebConstants.BRAND_COUNTRY).OuterHtml);
            mCarBrand.Country = new Country(countryNode.InnerText.Substring(countryNode.SelectSingleNode(WebConstants.EM).InnerText.Length));
            mCarBrand.Country.LogoUrl = countryNode.SelectSingleNode(WebConstants.IMAGE_SRC).Attributes[WebConstants.SRC].Value;
            //new Thread(new CountryLogoDownloadTask(mCarBrand.Country).Download).Start();

            HtmlNode brandListNode = HtmlNode.CreateNode(htmlDocument.DocumentNode.SelectSingleNode(WebConstants.BRAND_LIST).OuterHtml);
            mCarBrand.ListUrl = brandListNode.SelectSingleNode(WebConstants.SCRIPT_SRC).Attributes[WebConstants.SRC].Value;
            htmlDocument = htmlWeb.Load(WebConstants.BASE_URL + mCarBrand.ListUrl);
            HtmlNodeCollection factoryNodes = htmlDocument.DocumentNode.SelectNodes(WebConstants.FACTORY_NODE);
            if (factoryNodes != null)
            {
                foreach (HtmlNode tempNode in factoryNodes)
                {
                    HtmlNode factoryNode = HtmlNode.CreateNode(tempNode.OuterHtml);
                    CarFactory carFactory = new CarFactory(mCarBrand);
                    carFactory.Url = factoryNode.SelectSingleNode(WebConstants.LINK_HREF).Attributes[WebConstants.HREF].Value;
                    carFactory.Name = factoryNode.InnerText.Replace("/", "");
                    mCarBrand.CarFactoryList.Add(carFactory);
                }
            }

            runFactoryTasks();
        }
开发者ID:SevanJoe,项目名称:CarImageDownloader,代码行数:34,代码来源:WebBrandTask.cs

示例4: getChapters

        public static ChapterData getChapters(Source source, string link)
        {
            ChapterData chapter = new ChapterData();
            var web = new HtmlAgilityPack.HtmlWeb();
            web.AutoDetectEncoding = true;
            var htmlpage1 = web.Load(link);
            var pages = new List<IObservable<HtmlDocument>>();
            pages.Add(Observable.Return(htmlpage1));
            var linksToPages = htmlpage1.DocumentNode.SelectNodes(@"/html/body/section[@class='readpage_top']/div[@class='go_page clearfix']/span[@class='right']/select[@class='wid60']/option");
            for (int i = 1; i < linksToPages.Count; i++)
            {
                var linkToPage=linksToPages[i].GetAttributeValue("value", "");
                pages.Add(Observable.Start<HtmlDocument>(
                    ()=>{
                        var web2 = new HtmlAgilityPack.HtmlWeb();
                        web.AutoDetectEncoding = true;
                        return htmlpage1 = web.Load(linkToPage);
                    }
                ));

            }
            foreach (IObservable<HtmlDocument> item in pages)
            {
                HtmlDocument pagehtml = item.Wait();
                chapter.Images.Add(pagehtml.DocumentNode.SelectSingleNode(@"/html/body/section[@id='viewer']/a/img[@id='image']/@src").GetAttributeValue("src","")) ;

            }
            return chapter;
        }
开发者ID:guipasmoi,项目名称:MangaTracker,代码行数:29,代码来源:MangaHere.cs

示例5: getChapters

        public static ChapterData getChapters(Source source, string link)
        {
            ChapterData chapter = new ChapterData();
            var web = new HtmlAgilityPack.HtmlWeb();
            web.AutoDetectEncoding = true;
            var htmlpage1 = web.Load(link);
            var pages = new List<IObservable<HtmlDocument>>();
            pages.Add(Observable.Return(htmlpage1));
            var linksToPages = htmlpage1.DocumentNode.SelectNodes(@"//*[@id='pageMenu']/option");
            for (int i = 1; i < linksToPages.Count; i++)
            {
                var linkToPage ="http://www.mangareader.net"+ linksToPages[i].GetAttributeValue("value", "");
                pages.Add(Observable.Start<HtmlDocument>(
                    () =>
                    {
                        var web2 = new HtmlAgilityPack.HtmlWeb();
                        web.AutoDetectEncoding = true;
                        return htmlpage1 = web.Load(linkToPage);
                    }
                ));

            }
            foreach (IObservable<HtmlDocument> item in pages)
            {
                HtmlDocument pagehtml = item.Wait();
                chapter.Images.Add(pagehtml.DocumentNode.SelectSingleNode(@"//*[@id='img']").GetAttributeValue("src", ""));

            }
            return chapter;
        }
开发者ID:guipasmoi,项目名称:MangaTracker,代码行数:30,代码来源:MangaReader.cs

示例6: GeneratePages

        public void GeneratePages()
        {
            HtmlWeb htmlWeb = new HtmlWeb();
            _htmlDoc = htmlWeb.Load(this.Url);

            int MAX_PAGE = this.GetMaxPage(_htmlDoc);

            this.Pages = new List<WattpadPage>();

            for (int i = 1; i <= MAX_PAGE; i++)
            {
                _htmlDoc = htmlWeb.Load(this.Url + "/page/" + i);

                IEnumerable<HtmlNode> bodyList = _htmlDoc.DocumentNode.SelectNodes("//div[@id='storyText']");

                string content = "";
                if (bodyList != null)
                {
                    HtmlNode body = bodyList.ToList().First();
                    content = body.InnerHtml;
                }

                this.Pages.Add(new WattpadPage
                {
                    PageNumber = i,
                    Content = content
                });

            }
        }
开发者ID:kimerran,项目名称:watt2pdflib,代码行数:30,代码来源:WattpadChapter.cs

示例7: ProcessIndex

        public void ProcessIndex(int index)
        {
            var novel = new Novel();
            HtmlWeb htmlWeb = new HtmlWeb();

            HtmlDocument htmlDocument = htmlWeb.Load(String.Format(MainUrlPattern, index));

            var mainboxes = htmlDocument.DocumentNode.Descendants("div").Where(w => w.HasClass("mainbox")).ToArray();

            var mainContent = mainboxes[0];
            ParseMainContent(mainContent, novel);

            var releasesNode = htmlDocument.DocumentNode.Descendants("div").FirstOrDefault(w => w.HasClass("releases"));
            if (releasesNode != null)
            {
                ParseReleasesContent(releasesNode, novel);
            }

            var screenshotsNode = htmlDocument.DocumentNode.Descendants("div").FirstOrDefault(w => w.HasId("screenshots"));
            if (screenshotsNode != null)
            {
                ParseImagesContent(screenshotsNode, novel);
            }
            //staff (extract artists)
            htmlDocument = htmlWeb.Load(String.Format(StaffPattern, index));
            var staffNode = htmlDocument.DocumentNode.Descendants("div").FirstOrDefault(w => w.HasClass("staff") && w.NotContainsClass("cast"));
            if (staffNode != null)
            {
                ParseStaffContent(staffNode, novel);
            }
            //characters
            htmlDocument = htmlWeb.Load(String.Format(CharacterPattern, index));
            mainboxes = htmlDocument.DocumentNode.Descendants("div").Where(w => w.HasClass("mainbox")).ToArray();
            if (mainboxes.Length > 1)
            {
                for (int i = 1; i < mainboxes.Length; i++)
                {
                    ParseCharactersContent(mainboxes[i], novel);
                }
            }

            using (var ctx = new VNContext("VNConnectionString"))
            {
                NovelManager.SaveNovel(novel, ctx);
                Logs.Debug([email protected]"Novel {index} finished");
            }

            Console.WriteLine(index + @" finished");
        }
开发者ID:codyfinalfight,项目名称:VN,代码行数:49,代码来源:VndbParser.cs

示例8: GetFromTerra

        public static string GetFromTerra(string artist, string title)
        {
            string rep = string.Empty;

            artist = (artist + "").ToLowerInvariant();
            title = (title + "").ToLowerInvariant();

            //Obter a letra da música
            HtmlWeb web = new HtmlWeb();
            HtmlDocument doc = web.Load(string.Format("http://letras.mus.br/winamp.php?t={0}-{1}", HttpUtility.UrlEncode(artist, ISOEncoding), HttpUtility.UrlEncode(title, ISOEncoding)));
            HtmlNode node = doc.DocumentNode.SelectSingleNode("//div[@id='letra']/p");

            //Se encontrar a letra, retorna
            if (node == null && (artist.Contains("&") || title.Contains("&"))) {
                artist = artist.Replace('&', 'e');
                title = title.Replace('&', 'e');

                return GetFromTerra(artist, title);
            }

            node.InnerHtml = node.InnerHtml.Replace("<br>", "\r\n");

            rep = WebUtility.HtmlDecode(node.InnerText);

            return rep;
        }
开发者ID:mrmarino,项目名称:lyricsthingie,代码行数:26,代码来源:Providers.cs

示例9: GetLatestPodcasts

        public IEnumerable<Podcast> GetLatestPodcasts(int pageNumber)
        {
            var hw = new HtmlWeb();
            hw.OverrideEncoding = Encoding.GetEncoding("ISO-8859-2");
            var doc = hw.Load("http://www.tok.fm/TOKFM/0,94037.html?str=" + pageNumber.ToString(CultureInfo.InvariantCulture));
            doc.OptionOutputAsXml = true;
            doc.OptionCheckSyntax = true;
            doc.OptionFixNestedTags = true;
            var sb = new StringBuilder();
            var stringWriter = new StringWriter(sb);

            doc.Save(stringWriter);
            var page = sb.ToString();
            var stringReader = new StringReader(page);
            doc.Load(stringReader);
            var result = new List<Podcast>();
            foreach(HtmlNode link in doc.DocumentNode.SelectNodes("//a[@class='tokfm_play']"))
            {
                var imgNode = link.SelectSingleNode("img");
                var imageURL = String.Empty;
                if (imgNode != null)
                    imageURL = imgNode.Attributes["src"].Value;
                result.Add(new Podcast { Href = link.Attributes["href"].Value, Title = link.Attributes["title"].Value, ImageURL = imageURL });
            }

            return result;
        }
开发者ID:LukLed,项目名称:tokfm-podcasty,代码行数:27,代码来源:PodcastService.cs

示例10: _GetSerieMiniatureUrl

 protected override string _GetSerieMiniatureUrl(Serie serie)
 {
     var web = new HtmlWeb();
     var doc = web.Load(serie.URL);
     var img = doc.DocumentNode.SelectSingleNode("//div[@id='series_info']/div[@class='cover']/img");
     return img.GetAttributeValue("src", "");
 }
开发者ID:tundy,项目名称:MangaCrawler,代码行数:7,代码来源:MangaFoxCrawler.cs

示例11: GetChapterUrls

        public static List<string> GetChapterUrls(string url)
        {
            HtmlAgilityPack.HtmlWeb htmlWeb = new HtmlWeb();
            HtmlAgilityPack.HtmlDocument htdoc = htmlWeb.Load(url);

            List<string> ret = new List<string>();

            IEnumerable<HtmlAgilityPack.HtmlNode> selectList = htdoc.DocumentNode.Descendants("select")
                                        .Where(x => x.Attributes["class"].Value == "selectBox");

            if (selectList.ToList().Count == 0) return null;
            if (selectList == null) return null;

            var selectElement = selectList.Single();

            foreach (var cNode in selectElement.ChildNodes)
            {
                if (cNode.Name == "option")
                {
                    ret.Add(cNode.GetAttributeValue("value", "NO_URL"));
                }
            }

            //cleanups
            ret.Remove("#");

            return ret;
        }
开发者ID:kimerran,项目名称:watt2pdflib,代码行数:28,代码来源:Watt2Pdf.cs

示例12: ExtractCity

        //find out all the plumber information in a city
        private void ExtractCity(string state, string city)
        {
            HtmlWeb web = new HtmlWeb();
            string cityUrl = RootUrl + @"/" + state + @"/" + city + @"?" + @"page=1&ipp=All";
            HtmlDocument doc = web.Load(cityUrl);

            var linksOnPage = from lnks in doc.DocumentNode.Descendants()
                              where lnks.Name == "a" &&
                                    lnks.Attributes["href"] != null &&
                                    lnks.InnerText.Trim().Length > 0
                              select lnks;

            foreach (var li in linksOnPage)
            {
                if (li.InnerText == "Phone")
                {
                    string phone, name, address;
                    phone = li.ParentNode.NextSibling.InnerText;
                    Console.WriteLine();
                    Console.WriteLine("phone: "+phone);
                    name = li.ParentNode.ParentNode.ParentNode.ParentNode.FirstChild.NextSibling.InnerText.Split('\n')[1].Trim();
                    address = li.ParentNode.ParentNode.ParentNode.ParentNode.FirstChild.NextSibling.InnerText.Split('\n')[2].Trim();
                    Console.WriteLine("name: "+ name);
                    Console.WriteLine("address: " + address);
                    file.WriteLine(name + "," + address + "," + city.Replace("-plumbers","") + "," + phone.Replace(" ", ""));
                }

            }
        }
开发者ID:xiaozh,项目名称:DentistExtractor,代码行数:30,代码来源:PlumberExtractor.cs

示例13: GetSuburb

 static HtmlNodeCollection GetSuburb(string URL)
 {
     HtmlWeb client = new HtmlWeb();
     string suburbURL = System.Net.WebUtility.HtmlDecode(BASE + URL);
     HtmlDocument doc = client.Load(suburbURL);
     return doc.DocumentNode.SelectNodes("//table[@id='myTable']/tbody/tr/td[4]/a");
 }
开发者ID:williamparry,项目名称:Food-Violations-NSW,代码行数:7,代码来源:Program.cs

示例14: GetJobListFromWeb

 public void GetJobListFromWeb()
 {
     try
     {
         var htmlWeb = new HtmlWeb { OverrideEncoding = Encoding.GetEncoding("UTF-8") };
         HtmlDocument htmlDoc =
             htmlWeb.Load(string.Format("http://sou.zhaopin.com/jobs/searchresult.ashx?jl={0}&kw={1}&p={2}",
                 DataClass.GetDic_zhilian(_pars.Addr), _pars.Key, _pars.Page));
         var nodeList =
             htmlDoc.DocumentNode.SelectNodes("//*[@id='newlist_list_content_table']/table[@class='newlist']")
                 .AsParallel()
                 .ToList();
         for (int i = 1; i < nodeList.Count; i++)
         {
             var node = nodeList[i];
             var job = new JobInfo();
             job.TitleName = node.SelectSingleNode(".//tr/td[@class='zwmc']/div/a").InnerText;
             job.InfoUrl = node.SelectSingleNode(".//tr/td[@class='zwmc']/div/a").Attributes["href"].Value;
             job.Company = node.SelectSingleNode(".//tr/td[@class='gsmc']/a").InnerText;
             job.Salary = node.SelectSingleNode(".//tr/td[@class='zwyx']").InnerText;
             job.City = node.SelectSingleNode(".//tr/td[@class='gzdd']").InnerText;
             job.Date = node.SelectSingleNode(".//tr/td[@class='gxsj']/span").InnerText;
             job.Source = "智联招聘";
             job.Method = "月薪";
             _jobList.Add(job);
         }
     }
     catch (Exception ex)
     {
         LogSave.ErrLogSave("错误【解析】", ex);
     }
 }
开发者ID:akaxiaok,项目名称:FindJob,代码行数:32,代码来源:Zlzp.cs

示例15: HentBilinformation

        public static Bilinformation HentBilinformation(string nummerplade)
        {
            try
            {
                Bilinformation bilinformation = new Bilinformation();

                string html = "http://www.nummerplade.net/soeg/?regnr=" + nummerplade;
                HtmlWeb web = new HtmlWeb();
                HtmlDocument page = web.Load(html);

                if (page.DocumentNode != null)
                {
                    bilinformation.Maerke = page.DocumentNode.SelectSingleNode("//td[@id='maerke']").InnerText;
                    bilinformation.Model = page.DocumentNode.SelectSingleNode("//td[@id='model']").InnerText;
                    bilinformation.Variant = page.DocumentNode.SelectSingleNode("//td[@id='variant']").InnerText;
                    bilinformation.Stelnummer = page.DocumentNode.SelectSingleNode("//td[@id='stelnr']").InnerText;
                    bilinformation.Aargang = page.DocumentNode.SelectSingleNode("//td[@id='model_aar']").InnerText;
                    bilinformation.Nummerplade = page.DocumentNode.SelectSingleNode("//td[@id='regnr']").InnerText;
                }

                return bilinformation;
            }
            catch (Exception ex)
            {
                throw new IngenBilinformationException("Der blev ikke fundet nogen bilinformation på nummerpladen.", ex);
            }
        }
开发者ID:aroesdal,项目名称:Hovedopgave,代码行数:27,代码来源:Bilinformation.cs


注:本文中的HtmlAgilityPack.HtmlWeb.Load方法示例由纯净天空整理自Github/MSDocs等开源代码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。