Ejemplo n.º 1
0
 public static void Run()
 {
     OoSpider.Create(new Site(), typeof(News163)).AddUrl("http://news.163.com/13/0802/05/958I1E330001124J_2.html")
     .AddPipeline(new MultiPagePipeline())
     .AddPipeline(new ConsolePipeline())
     .SetScheduler(new RedisScheduler("localhost", "")).Run();
 }
Ejemplo n.º 2
0
        public static void Run()
        {
            var site = new Site();

            site.AddStartUrl("http://flashsword20.iteye.com/blog");
            OoSpider.Create(site, typeof(IteyeBlog)).Run();
        }
Ejemplo n.º 3
0
        public static void Run()
        {
            Site site = new Site {
                Encoding = Encoding.UTF8
            };

            site.AddStartUrl("http://www.oschina.net/question/1995445_2136783");
            OoSpider.Create(site, typeof(OschinaAnswer)).Run();
        }
Ejemplo n.º 4
0
        public static void Run()
        {
            Site site = new Site();

            site.AddStartUrl("http://www.36kr.com/");
            Core.Spider thread = OoSpider.Create(site, new CollectorPageModelToDbPipeline(), typeof(Kr36NewsModel)).SetThreadNum(20);
            thread.Start();
            SpiderMonitor spiderMonitor = SpiderMonitor.Instance;

            spiderMonitor.Register(thread);
        }
Ejemplo n.º 5
0
        public static void RunTask()
        {
            OoSpider ooSpider = OoSpider.Create("ganji_posts_" + DateTime.Now.Date.ToString("yyyy-MM-dd"), new Site {
                SleepTime = 1000, Encoding = Encoding.UTF8
            }, new CollectorPageModelToDbPipeline(), typeof(Ganji));

            ooSpider.SetEmptySleepTime(15000);
            ooSpider.SetThreadNum(10);
            ooSpider.SetScheduler(new RedisScheduler("localhost", ""));
            ooSpider.AddUrl("http://sh.ganji.com/zpdianhuaxiaoshou/o1/");
            ooSpider.Run();
        }
Ejemplo n.º 6
0
        public static void RunTask()
        {
            OoSpider ooSpider = OoSpider.Create("aiqiyi_movies_" + DateTime.Now.ToLocalTime().ToString(),
                                                new Site {
                SleepTime = 1000, Encoding = Encoding.UTF8
            }, new CollectorPageModelToDbPipeline(), typeof(walter));

            ooSpider.SetEmptySleepTime(15000);
            ooSpider.SetThreadNum(1);
            ooSpider.SetScheduler(new RedisScheduler("localhost", null));
            ooSpider.AddUrl("http://top.iqiyi.com/dianshiju.html#");
            ooSpider.Run();
        }
Ejemplo n.º 7
0
        //[ExtractBy(Value = "//div[@class='BlogStat']/regex('\\d+-\\d+-\\d+\\s+\\d+:\\d+')")]
        //public DateTime Date { get; set; }

        public static void Run()
        {
            Site site = new Site
            {
                UserAgent = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/30.0.1599.101 Safari/537.36"
            };

            site.AddStartUrl("http://my.oschina.net/flashsword/blog");
            site.SleepTime  = 0;
            site.RetryTimes = 3;

            OoSpider.Create(site, new CollectorPageModelToDbPipeline(), typeof(OschinaBlog)).SetThreadNum(1).Run();
        }
Ejemplo n.º 8
0
        public static void RunTask()
        {
            OoSpider ooSpider = OoSpider.Create(new Site
            {
                SleepTime = 10000
            }, new CollectorPageModelToDbPipeline(), typeof(Ganji));

            ooSpider.SetThreadNum(1);
            Request request = new Request("http://mobds.ganji.com/datashare/", null);

            request.Method = "POST";
            ooSpider.AddRequest(request);
            ooSpider.Run();
        }
Ejemplo n.º 9
0
 public static void Run()
 {
     OoSpider.Create(new Site(), new ConsolePageModelPipeline(), typeof(QqMeishi)).AddUrl("http://meishi.qq.com/beijing/c/all").SetThreadNum(4).Run();
 }
Ejemplo n.º 10
0
 public void TestOschinaBlog()
 {
     //results will be saved to "/data/webmagic/" in json format
     OoSpider.Create(new Site(), new JsonFilePageModelPipeline("/data/webmagic/"), typeof(OschinaBlog)).AddUrl("http://my.oschina.net/flashsword/blog").Run();
 }