예제 #1
0
        public static JArray CrawlerSingleQuestion(int questionId, List <string> proxys)
        {
            var proxy = proxys[new Random().Next(0, proxys.Count - 1)];

            try
            {
                var a = HttpClientHolder.Proxy_GetRequest($"https://www.zujuan.com/question/detail-{questionId}.shtml",
                                                          proxy);
                if (a.IndexOf("试题已经被删除") >= 0)
                {
                    // AddDeleteQuestion(questionId);
                }
                if (a.IndexOf("限制访问试题") >= 0)
                {
                    throw new Exception("test");
                }
                Console.WriteLine($"start crawler https://www.zujuan.com/question/detail-{questionId}.shtml  {proxy}");
                //例如我想提取记录中的NAME值
                string value = GrabAnswer.GetValue(a, "var MockDataTestPaper =", "OT2.renderQList").TrimEnd(new char[] { ';' });
                value = value.Trim().TrimEnd(new char[] { ';' }).Trim();
                //; UpdateProxGrabyime(proxy.Id);

                //更新代理时间

                return(JArray.Parse(value));
            }
            catch (IOException io)
            {
                if (!UnusefulProxy.Any(t => t.Equals(proxy)))
                {
                    UnusefulProxy.Add(proxy);
                }
            }
            catch (JsonReaderException je)
            {
                //AddDeleteQuestion(questionId);
            }
            catch (WebException we)
            {
                //if (we.Status == WebExceptionStatus.ConnectFailure || we.Status == WebExceptionStatus.ProtocolError)
                //{
                if (!UnusefulProxy.Any(t => t.Equals(proxy)))
                {
                    UnusefulProxy.Add(proxy);
                }
                //SetProxyDisable(proxy.Id);

                //}
            }
            return(null);
        }
예제 #2
0
        public static JArray CrawlerSingleQuestion(string questionId, List <string> proxys)
        {
            var proxy = proxys[new Random().Next(0, proxys.Count - 1)];

            try
            {
                var a = HttpClientHolder.Proxy_GetRequest($"https://www.zujuan.com/question/detail-{questionId}.shtml",
                                                          proxy);
                if (a.IndexOf("试题已经被删除") >= 0)
                {
                    Console.WriteLine($"{questionId} has delete!!!");
                    UpdateQuestionRemoteStatus(questionId.ToInt());
                    return(null);
                }
                if (a.IndexOf("限制访问试题") >= 0)
                {
                    using (var db = new CrawlerEntities())
                    {
                        var id     = questionId.NullToInt();
                        var entity = db.QuestionAll.FirstOrDefault(t => t.QuestionId == id);
                        if (entity != null)
                        {
                            entity.IsGrabAns = false;
                            db.SaveChanges();
                        }
                    }
                    return(null);
                }
                Console.WriteLine($"start crawler https://www.zujuan.com/question/detail-{questionId}.shtml  {proxy}");
                //例如我想提取记录中的NAME值
                string value = GetValue(a, "var MockDataTestPaper =", "OT2.renderQList").TrimEnd(new char[] { ';' });
                value = value.Trim().TrimEnd(new char[] { ';' }).Trim();
                //; UpdateProxGrabyime(proxy.Id);
                Console.WriteLine($"aleady get {questionId} return value");
                //更新代理时间

                return(JArray.Parse(value));
            }
            catch (IOException io)
            {
                if (!UnusefulProxy.Any(t => t.Equals(proxy)))
                {
                    UnusefulProxy.Add(proxy);
                }
            }
            catch (JsonReaderException je)
            {
                UpdateQuestionRemoteStatus(questionId.ToInt());
            }
            catch (WebException we)
            {
                using (var db = new CrawlerEntities())
                {
                    var id     = questionId.NullToInt();
                    var entity = db.QuestionAll.FirstOrDefault(t => t.QuestionId == id);
                    if (entity != null)
                    {
                        entity.IsGrabAns = false;
                        db.SaveChanges();
                    }
                }
                //if (we.Status == WebExceptionStatus.ConnectFailure || we.Status == WebExceptionStatus.ProtocolError)
                //{
                if (!UnusefulProxy.Any(t => t.Equals(proxy)))
                {
                    UnusefulProxy.Add(proxy);
                }
                //SetProxyDisable(proxy.Id);

                //}
            }
            catch (Exception e)
            {
                using (var db = new CrawlerEntities())
                {
                    var id     = questionId.NullToInt();
                    var entity = db.QuestionAll.FirstOrDefault(t => t.QuestionId == id);
                    if (entity != null)
                    {
                        entity.IsGrabAns = false;
                        db.SaveChanges();
                    }
                }
            }
            //UpdateQuestionGrabStatus(questionId.NullToInt());
            return(null);
        }