Exemplo n.º 1
0
        public static void Run()
        {
            int      captrueHouseCount = 0;
            DateTime startTime         = DateTime.Now;

            var peopleRentingConf = CrawlerDataDapper.GetConfigurationList(ConstConfigurationName.HuZhuZuFang)
                                    .FirstOrDefault();

            var pageCount = peopleRentingConf != null
                ? JsonConvert.DeserializeObject <dynamic>(peopleRentingConf.ConfigurationValue).pagecount.Value
                : 10;

            var hsHouseOnlineUrl        = new HashSet <string>();
            List <BaseHouseInfo> houses = new List <BaseHouseInfo>();

            for (var pageNum = 1; pageNum < pageCount; pageNum++)
            {
                string result = getResultFromAPI(pageNum);
                houses.AddRange(GetHouseData(result));
            }
            CrawlerDataDapper.BulkInsertHouses(houses);
            captrueHouseCount = captrueHouseCount + houses.Count;

            BizCrawlerLog.SaveLog($"爬取上海互助租房数据",
                                  $"本次共爬取到{captrueHouseCount}条数据,耗时{ (DateTime.Now - startTime).TotalSeconds}秒。", 1);
        }
Exemplo n.º 2
0
 public static void Run()
 {
     foreach (var doubanConf in CrawlerDataDapper.GetConfigurationList(ConstConfigurationName.MoguHouse))
     {
         LogHelper.RunActionNotThrowEx(() =>
         {
             List <BaseHouseInfo> houses = new List <BaseHouseInfo>();
             var confInfo = Newtonsoft.Json.JsonConvert.DeserializeObject <dynamic>(doubanConf.ConfigurationValue);
             var cityName = confInfo.cityname.Value;
             var cityId   = (int)confInfo.cityid.Value;
             // 2:合租 3:整租 5:业主房源
             var rentTypes = new List <int>()
             {
                 2, 3, 5
             };
             foreach (var rentType in rentTypes)
             {
                 for (var pageIndex = 1; pageIndex <= confInfo.pagecount.Value; pageIndex++)
                 {
                     var list = GetHouseData(cityName, cityId, pageIndex, rentType);
                     houses.AddRange(list);
                 }
             }
             CrawlerDataDapper.BulkInsertHouses(houses);
         }, "MoGuHouseCrawler Run ", doubanConf);
     }
 }
Exemplo n.º 3
0
 public static void Run()
 {
     try
     {
         int      captrueHouseCount = 0;
         DateTime startTime         = DateTime.Now;
         foreach (var doubanConf in CrawlerDataDapper.GetConfigurationList(ConstConfigurationName.Douban))
         {
             LogHelper.RunActionNotThrowEx(() =>
             {
                 List <BaseHouseInfo> houses = new List <BaseHouseInfo>();
                 var confInfo = Newtonsoft.Json.JsonConvert.DeserializeObject <dynamic>(doubanConf.ConfigurationValue);
                 for (var pageIndex = 0; pageIndex < confInfo.pagecount.Value; pageIndex++)
                 {
                     var lstHouseInfo = GetHouseData(confInfo.groupid.Value,
                                                     confInfo.cityname.Value, pageIndex);
                     houses.AddRange(lstHouseInfo);
                 }
                 captrueHouseCount = captrueHouseCount + houses.Count;
                 CrawlerDataDapper.BulkInsertHouses(houses);
             }, "DoubanHouseCrawler CaptureHouseInfo ", doubanConf);
         }
         BizCrawlerLog.SaveLog($"爬取豆瓣租房小组数据",
                               $"本次共爬取到{captrueHouseCount}条数据,耗时{ (DateTime.Now - startTime).TotalSeconds}秒。", 1);
     }
     catch (Exception ex)
     {
         LogHelper.Error("DoubanHouseCrawler CrawlerHouseInfo Exception", ex);
     }
 }
Exemplo n.º 4
0
        private static int CaptureHouse()
        {
            int captrueHouseCount       = 0;
            List <BaseHouseInfo> houses = new List <BaseHouseInfo>();

            for (var pageNum = 1; pageNum < 20; pageNum++)
            {
                var result = GetHTML(pageNum);
                houses.AddRange(GetHouseDataFromHTML(result));
            }
            captrueHouseCount = captrueHouseCount + houses.Count;
            CrawlerDataDapper.BulkInsertHouses(houses);
            return(captrueHouseCount);
        }
Exemplo n.º 5
0
 public static void Run()
 {
     foreach (var doubanConf in CrawlerDataDapper.GetConfigurationList(ConstConfigurationName.Zuber))
     {
         LogHelper.RunActionNotThrowEx(() =>
         {
             List <BaseHouseInfo> houses = new List <BaseHouseInfo>();
             var confInfo = Newtonsoft.Json.JsonConvert.DeserializeObject <dynamic>(doubanConf.ConfigurationValue);
             var cityName = confInfo.cityname.Value;
             var sequence = "";
             for (var i = 0; i <= confInfo.pagecount.Value; i++)
             {
                 var tupleResult = GetHouseData(cityName, sequence);
                 sequence        = tupleResult.Item2;
                 houses.AddRange(tupleResult.Item1);
             }
             CrawlerDataDapper.BulkInsertHouses(houses);
         }, "DoubanHouseCrawler CaptureHouseInfo ", doubanConf);
     }
 }
Exemplo n.º 6
0
        private static int CaptureHouse(BizCrawlerConfiguration crawlerConfiguration)
        {
            var confInfo = JsonConvert.DeserializeObject <dynamic>(crawlerConfiguration.ConfigurationValue);

            if (confInfo.shortcutname == null || string.IsNullOrEmpty(confInfo.shortcutname.Value))
            {
                return(0);
            }
            int    captrueHouseCount    = 0;
            string cityShortCutName     = confInfo.shortcutname.Value;
            List <BaseHouseInfo> houses = new List <BaseHouseInfo>();

            for (var pageNum = 1; pageNum < confInfo.pagecount.Value; pageNum++)
            {
                var result = GetResultByAPI(cityShortCutName, pageNum);
                houses.AddRange(GetHouseData(cityShortCutName, result));
            }
            captrueHouseCount = captrueHouseCount + houses.Count;
            CrawlerDataDapper.BulkInsertHouses(houses);
            return(captrueHouseCount);
        }