private string HtmlText(string sourceHtml)
{
hParser.Parser parser = hParser.Parser.CreateParser(sourceHtml.Replace(System.Environment.NewLine, ""), "utf-8");
StringBuilder builderHead = new StringBuilder();
StringBuilder builderBody = new StringBuilder();
hParser.NodeFilter html = new TagNameFilter("TR");
hParser.INode nodes = parser.Parse(html)[0];
builderHead.Append(nodes.Children[0].ToHtml());
hParser.INode body = nodes.Children[1];
hParser.INode div = body.Children[0];
for (int i = 0; i < div.Children.Count; i++)
{
if (div.Children[i] is hParser.ITag)
{
builderBody.Append(div.Children[i].ToHtml());
}
}
StringBuilder builder = new StringBuilder();
builder.Append("<html>");
builder.Append(builderHead.ToString());
builder.Append("<body>");
builder.Append(string.Format("<{0}>", div.GetText()));
builder.Append(builderBody.ToString());
builder.Append("</div>");
builder.Append("</body>");
builder.Append("</html>");
return(builder.ToString());
}
static void GetBlogLink(string htmlContent)
{
Lexer lexer = new Lexer(htmlContent);
Parser parser = new Parser(lexer);
NodeList articleList = parser.Parse(articleFilter);
if (articleList.Count == 1)
{
NodeList candidateNodeList = articleList[0].Children.ExtractAllNodesThatMatch(wrapFilter, true);
for (int i = 0; i < candidateNodeList.Count; i++)
{
NodeList linkNodeList = candidateNodeList[i].Children.ExtractAllNodesThatMatch(new NodeClassFilter(typeof(ATag)), false);
if (linkNodeList.Count == 1)
{
string blogLink = ((ATag)linkNodeList[0]).ExtractLink();
blogLinkList.Add(blogLink);
}
else
{
Console.WriteLine("第" + i + "个条目中，判断链接出错！");
}
}
}
else
{
Console.WriteLine("获取包含日志列表出错！");
}
}
/// <summary>
/// 获取目标数据
/// </summary>
/// <param name="parser">目标html文件</param>
/// <param name="tag">标签名称</param>
/// <param name="attribute">标签里面的属性名称</param>
/// <param name="attValue">属性的值</param>
/// <returns>标签内的目标数据</returns>
public static string getValue(string html, string tag, string attribute, string attValue)
{
Lexer lexer = new Lexer(html);
Parser parser = new Parser(lexer);
string value = string.Empty;
NodeFilter nodeFilter = new TagNameFilter(tag);
NodeList nodeList = parser.Parse(nodeFilter);
for (int i = 0; i < nodeList.Count; i++)
{
INode node = nodeList[i];
ITag tagNode = (node as ITag);
if (tagNode.Attributes != null && tagNode.Attributes.Count > 0)
{
foreach (string key in tagNode.Attributes.Keys)
{
if (key.Contains("<TAGNAME>"))
{
continue;
}
if (key.Contains(attribute))
{
if (tagNode.Attributes[key].ToString() == attValue)
{
value = tagNode.ToPlainTextString();
return value;
}
}
}
}
}
return null;
}
/// <summary>
/// 增加一条数据
/// </summary>
public string Add(string scheduleID, string companyids, string historyids,DateTime time)
{
WebClientBLL bll = new WebClientBLL();
string[] companyidArr = companyids.Split(',');
string[] historyidArr = historyids.Split(',');
int count = 0;
if (companyidArr.Length == historyidArr.Length)
{
dal.Delete(scheduleID);
for (int i = 0; i < companyidArr.Length; i++)
{
string s = bll.GetOddsHistoryContent(historyidArr[i]);
Lexer lexer = new Lexer(s);
Parser parser = new Parser(lexer);
NodeList bodyNodes = parser.Parse(new TagNameFilter("HTML"))[0].Children.ExtractAllNodesThatMatch(new TagNameFilter("BODY"))[0].Children;
ITag table = bodyNodes.SearchFor(typeof(Winista.Text.HtmlParser.Tags.TableTag))[0] as ITag;
NodeList tableRows = table.Children.SearchFor(typeof(Winista.Text.HtmlParser.Tags.TableRow));
for (int f = 0; f < tableRows.Count; f++)
{
ITag row = tableRows[f] as ITag;
if (row.Attributes["ALIGN"].Equals("center") && row.Attributes["BGCOLOR"].Equals("#FFFFFF")){
Odds1x2History model = new Odds1x2History();
model.companyid = int.Parse(companyidArr[i]);
model.scheduleid = int.Parse(scheduleID);
model.home = float.Parse(row.Children[0].ToPlainTextString());
model.draw = float.Parse(row.Children[1].ToPlainTextString());
model.away = float.Parse(row.Children[2].ToPlainTextString());
this.FillOdds1x2History(model);
string[] t2 = row.Children[3].ToPlainTextString().Replace("showtime(", "").Replace(")", "").Split(',');
int yy = int.Parse(t2[0]);
int mm = int.Parse(t2[1].Remove(2));
int dd = int.Parse(t2[2]);
int hh = int.Parse(t2[3]);
int mi = int.Parse(t2[4]);
int ss = int.Parse(t2[5]);
model.time = new DateTime(yy, mm, dd, hh, mi, ss, DateTimeKind.Utc).AddHours(8d);
if (model.time > time)
{
continue;
}
dal.Add(model);
count++;
}
}
}
}
JSONHelper json = new JSONHelper();
json.success = true;
json.totlalCount = count;
return json.ToString();
}
static void GetStoryOfRevolution()
{
StreamReader reader = new StreamReader("catalogue.htm");
Lexer lexer = new Lexer(reader.ReadToEnd());
Parser parser = new Parser(lexer);
HasAttributeFilter linkFilterByParent = new HasAttributeFilter("class", "row zhangjieUl");
HasAttributeFilter linkFilterByClass = new HasAttributeFilter("class", "fontStyle2 colorStyleLink");
AndFilter linkFilter = new AndFilter(new HasParentFilter(linkFilterByParent, true), linkFilterByClass);
NodeList linkNodeList = parser.Parse(linkFilter);
List<string> linkUrlList = new List<string>(linkNodeList.Size());
List<string> chapterHtmlContentList = new List<string>(linkNodeList.Size());
HttpWebRequest httpWebRequest;
StreamReader chapterReader = null;
for (int i = 0; i < linkNodeList.Size(); i++)
{
ATag linkNode = (ATag)linkNodeList[i];
linkUrlList.Add(linkNode.Link);
httpWebRequest = HttpWebRequest.CreateHttp("http://www.mlxiaoshuo.com" + linkUrlList[linkUrlList.Count - 1]);
chapterReader = new StreamReader(new BufferedStream(httpWebRequest.GetResponse().GetResponseStream(), 4 * 200 * 1024));
string chapterHtmlContent = chapterReader.ReadToEnd();
chapterHtmlContentList.Add(chapterHtmlContent);
Console.WriteLine("第" + (i + 1) + "个页面获取完毕！");
}
chapterReader.Close();
HasAttributeFilter praghFilter = new HasAttributeFilter("class", "textP fontStyle2 colorStyleText");
StreamWriter writer = new StreamWriter("革命逸事.txt");
for (int i = 0; i < chapterHtmlContentList.Count; i++)
{
writer.WriteLine("第" + (i + 1) + "章");
lexer = new Lexer(chapterHtmlContentList[i]);
parser = new Parser(lexer);
NodeList praghNodeList = parser.Parse(praghFilter);
if (praghNodeList.Size() == 1)
{
for (int j = 0; j < praghNodeList[0].Children.Size(); j++)
{
if (praghNodeList[0].Children[j].GetType().Equals(typeof(ParagraphTag)))
{
ParagraphTag praghTag = (ParagraphTag)praghNodeList[0].Children[j];
writer.WriteLine(" " + praghTag.StringText);
}
}
writer.WriteLine();
}
else
{
Console.WriteLine("第" + (i + 1) + "页中，判断段落的标准出错！");
}
}
writer.Close();
}
static string GetBlogTitle(string htmlContent)
{
string result = "";
Lexer lexer = new Lexer(htmlContent);
Parser parser = new Parser(lexer);
NodeList titleList = parser.Parse(titleFilter);
if (titleList.Count == 1)
{
TitleTag titleTag = (TitleTag)titleList[0];
result = titleTag.Title;
}
else
{
Console.WriteLine("获取标题信息出错！");
}
return result;
}
/// <summary>
/// 获得列表
/// </summary>
/// <returns></returns>
public List<OddsLiveMatch> GetMatchScrollOdds(string matchid,string urlparams)
{
List<OddsLiveMatch> liveMatchList = new List<OddsLiveMatch>();
try
{
HttpHelper h = new HttpHelper();
Cookie lng = new Cookie("lng", "2");
lng.Domain = domain;
h.CookieContainer.Add(lng);
//string zoudi = h.GetHtml("https://" + domain + "/default.aspx" + urlparams);
string zoudi = h.GetHtml(urlparams);
if (!string.IsNullOrEmpty(zoudi))
{
#region 分析网页html节点
Lexer lexer = new Lexer(zoudi);
Parser parser = new Parser(lexer);
NodeList bodyNodes = parser.Parse(new TagNameFilter("HTML"))[0].Children.ExtractAllNodesThatMatch(new TagNameFilter("BODY"))[0].Children;
ITag divNode = bodyNodes.ExtractAllNodesThatMatch(new TagNameFilter("FORM"))[0].Children.ExtractAllNodesThatMatch(new TagNameFilter("DIV"))[0] as ITag;
if (divNode.Attributes["ID"].Equals("PageBody"))
{
NodeList dataDivList = divNode.Children.SearchFor(typeof(Winista.Text.HtmlParser.Tags.Div));
if (dataDivList[0].ToPlainTextString() == "走地盤")
{
if (dataDivList[2].ToPlainTextString() == "全場賽果")
{
OddsLiveHistory liveHistory = new OddsLiveHistory();
liveHistory.matchid = matchid;
liveHistory.home = float.Parse(dataDivList[3].ToPlainTextString().Split(' ')[0]);
liveHistory.draw = float.Parse(dataDivList[5].ToPlainTextString().Split(' ')[0]);
liveHistory.away = float.Parse(dataDivList[7].ToPlainTextString().Split(' ')[0]);
liveHistory.time = DateTime.Now;
dal.AddHistory(liveHistory);
}
}
}
#endregion 分析网页html节点
}
}
catch (Exception)
{
}
return liveMatchList;
}
public void StartCrawl()// private void BtnDownload_Click(object sender, RoutedEventArgs e)
{
this.parseResult = "";
Uri uri = new Uri(this.TargetUri);
#region
//<N>基于Httphelper，这样下载会要求程序自己实现验证授权
//HttpHelper httpHelper = new HttpHelper();
//HttpItem rq = new HttpItem();
//rq.URL = uri.AbsoluteUri;
//HttpResult html = httpHelper.GetHtml(rq);
//Debug.WriteLine(html.Html);
//直接基于WebBrowser，授权是由用户手动实现的
mshtml.IHTMLDocument2 doc2 = null;//(mshtml.IHTMLDocument2)webBox.Document;
string html = string.Compare(this.IsOffline, "1", StringComparison.InvariantCultureIgnoreCase) == 0 ? s_htmlFake : doc2.body.innerHTML;
Debug.WriteLine(html);
#endregion
#region 使用HtmlParser提取HTML
Lexer lexer = new Lexer(html);
hParser.Parser parser = new hParser.Parser(lexer);
hParser.NodeFilter filter = new NodeClassFilter(typeof(Winista.Text.HtmlParser.Tags.TableRow));
NodeList nodeList = parser.Parse(filter);
if (nodeList.Count == 0)
{
MessageBox.Show("没有符合要求的节点");
}
else
{
for (int i = 0; i < nodeList.Count; i++)
{
parserTR(nodeList[i]);
}
MessageBox.Show(parseResult);
}
/* parseResult = HtmlText(html);
* MessageBox.Show(parseResult);*/
#endregion
}
//分析HtmlContents中给定索引条目的内容，提取信息
private static void GetInfoFromHtml(int index)
{
//使用Winista.HtmlParser库解析HTML
//建立HTML分析工具对象
Lexer lexer = new Lexer(HtmlContents[index]);
Parser parser = new Parser(lexer);
//按属性的过滤器：两个参数分别代表要过滤的属性和属性值
HasAttributeFilter nameFilter = new HasAttributeFilter("class", "lrg");
HasAttributeFilter priceFilter = new HasAttributeFilter("class", "bld lrg red");
//获得所有满足过滤条件的HTML节点
NodeList nameList = parser.Parse(nameFilter);
for (int j = 0; j < nameList.Size(); j++)
{
//确定节点nameList[j]为Span类型的标签；HttpUtility.HtmlDecode方法把HTML编码转为文本编码，使中文正常显示
string name = HttpUtility.HtmlDecode(((Span)nameList[j]).StringText);
//Parent表示该HTML节点的父节点
//NextSobling表示该HTML节点的下一个兄弟节点
//Children表示该HTML节点的所有孩子节点组成的集合
//ExtractAllNodesThatMatch表示获取所有满足给定过滤器条件的节点，两个参数分别代表过滤器和是否进入孩子节点中迭代查找
//注意：对Winista.HtmlParser来说，“空文本节点”也是一个节点（在IE的开发者工具中显示“空文本节点”，而Chrome则不显示）；形似<del>内容</ del>在Children中会表达成三个节点
NodeList priceList = nameList[j].Parent.Parent.NextSibling.NextSibling.Children.ExtractAllNodesThatMatch(priceFilter, true);
if (priceList.Size() == 1)
{
string priceStr = ((Span)priceList[0]).StringText;
double price = Double.Parse(priceStr.Substring(2, priceStr.Length - 2));
TradeList.Add(new Commodity(name, price, "RMB"));
}
else
{
badRecordCount++;
}
}
Console.WriteLine("第" + (index + 1) + "个页面处理完成！");
//保存当前页面到本地文件
//StreamWriter writer = new StreamWriter("searchresult"+i+".html");
//writer.Write(s);
//writer.Close();
}
/// <summary>
/// 从网页版微博中获取微博信息
/// </summary>
/// <param name="fansList">保存爬得的粉丝数组</param>
public void GetInfoFromHtml(List<Fan> fansList)
{
Lexer lexer = new Lexer(currentHtmlContent);
Parser parser = new Parser(lexer);
//获取包含每条微博的div标记列表
NodeList fansNodeList = parser.Parse(fanFilter);
for (int i = 0; i < fansNodeList.Size(); i++)
{
Fan fan = new Fan();
//获取包含一个粉丝的<li>标记
Bullet fanBullet = (Bullet)fansNodeList[i];
#region 获取该粉丝头像
NodeList fanPortraitNodeList = fanBullet.Children.ExtractAllNodesThatMatch(portraitFilter, true);
if (fanPortraitNodeList.Size() == 1)
{
Div fanPortraitDiv = (Div)fanPortraitNodeList[0];
NodeList imgNodeList = fanPortraitDiv.Children.ExtractAllNodesThatMatch(new NodeClassFilter(typeof(ImageTag)), true);
if (imgNodeList.Size() == 1)
{
ImageTag imgNode = (ImageTag)imgNodeList[0];
if (imgNode.Attributes.ContainsKey("SRC") && imgNode.Attributes.ContainsKey("ALT"))
{
string imgUrl = imgNode.GetAttribute("SRC");
string imgName = imgNode.GetAttribute("ALT");
fan.Name = imgName;
WebClient wc = new WebClient();//使用WebClient是因为下载用户头像不用登录cookie
wc.DownloadFileAsync(new Uri(imgUrl), @"portrait\" + imgName + ".jpg");
wc.DownloadFileCompleted += wc_DownloadFileCompleted;
}
else
{
Console.WriteLine("第" + i + "个粉丝中，<img>标记缺少必要的属性！");
}
}
else
{
Console.WriteLine("第" + i + "个粉丝中，获取img标记出错！");
}
}
else
{
Console.WriteLine("第" + i + "个粉丝中，获取粉丝头像的标准出错！");
}
#endregion
#region 获取该粉丝的关注数/粉丝数/微博数
NodeList fanConnectNodeList = fanBullet.Children.ExtractAllNodesThatMatch(fanConnectFilter, true);
if (fanConnectNodeList.Size() == 1)
{
NodeList ATagList = fanConnectNodeList[0].Children.ExtractAllNodesThatMatch(new NodeClassFilter(typeof(ATag)), true);
if (ATagList.Size() == 3)
{
for (int j = 0; j < 3; j++)
{
ATag aTag = (ATag)ATagList[j];
switch (j)
{
case 0:
if (aTag.Attributes.ContainsKey("HREF") && aTag.GetAttribute("HREF").Contains("follow"))
{
fan.FollowCount = Int32.Parse(aTag.StringText);
}
else
{
Console.WriteLine("第" + i + "个粉丝中，获取粉丝的关注数出错！");
}
break;
case 1:
if (aTag.Attributes.ContainsKey("HREF") && aTag.GetAttribute("HREF").Contains("fans"))
{
fan.FansCount = Int32.Parse(aTag.StringText);
}
else
{
Console.WriteLine("第" + i + "个粉丝中，获取粉丝的粉丝数出错！");
}
break;
default:
fan.FeedsCount = Int32.Parse(aTag.StringText);
break;
}
}
}
else
{
Console.WriteLine("第" + i + "个粉丝中，获取粉丝关注数/粉丝数/微博数的数量出错！");
}
}
else
{
Console.WriteLine("第" + i + "个粉丝中，获取粉丝关注数/粉丝数/微博数的标准出错！");
}
#endregion
#region 获取该粉丝的简介信息
NodeList fanInfoNodeList = fanBullet.Children.ExtractAllNodesThatMatch(fanInfoFilter, true);
if (fanInfoNodeList.Size() == 1)
{
//Console.WriteLine(fanInfoNodeList[0].Parent.ToHtml());
Div fanInfoDiv = (Div)fanInfoNodeList[0];
string intro = fanInfoDiv.StringText;
if (intro.Substring(0, 2).Equals("简介"))
{
fan.Introduction = intro.Substring(3, intro.Length - 3).Replace("\n", " ").Replace("\t", " ");
}
}
else
{
if (fanInfoNodeList.Size() == 0)
{
fan.Introduction = "";
}
else
{
Console.WriteLine("第" + i + "个粉丝中，获取粉丝简介的标准出错！");
}
}
#endregion
#region 获取该粉丝的UserID、地点和性别信息；校验该粉丝的用户名信息
NodeList fanLocationNodeList = fanBullet.Children.ExtractAllNodesThatMatch(fanNameFilter, true);
if (fanLocationNodeList.Size() == 1)
{
//获取粉丝的UserID信息；校验该粉丝的用户名信息
NodeList aTagNodeList = fanLocationNodeList[0].Children.ExtractAllNodesThatMatch(new NodeClassFilter(typeof(ATag)), true);
if (aTagNodeList.Size() >= 1)
{
ATag nameNode = (ATag)aTagNodeList[0];
if (nameNode.Attributes.ContainsKey("USERCARD") && nameNode.Attributes.ContainsKey("HREF"))
{
//获取粉丝的UserID信息
string uidStr = nameNode.GetAttribute("USERCARD");
if (uidStr.Substring(0, 3).Equals("id="))
{
fan.UserID = uidStr.Substring(3, uidStr.Length - 3);
}
//获取粉丝的微博链接
string linkUrl = nameNode.GetAttribute("HREF");
fan.LinkURL = "http://www.weibo.com" + linkUrl;
}
else
{
Console.WriteLine("第" + i + "个粉丝中，包含用户id和链接的<a>标记中缺少必要的属性！");
}
//校验该粉丝的用户名信息
if (!nameNode.StringText.Equals(fan.Name))
{
Console.WriteLine("第" + i + "个粉丝中，用户名与用户头像文字描述不一致！");
}
}
//获取粉丝的性别和地点信息
NodeList locationNodeList = fanLocationNodeList[0].Children.ExtractAllNodesThatMatch(new HasAttributeFilter("class", "addr"), true);
if (locationNodeList.Size() == 1)
{
string locationStr = "";
for (int j = 0; j < locationNodeList[0].Children.Size(); j++)
{
INode node = locationNodeList[0].Children[j];
if (node.GetType().Equals(typeof(TextNode)))
{
TextNode tNode = (TextNode)node;
locationStr += tNode.ToPlainTextString();
}
if (node.GetType().Equals(typeof(TagNode)))
{
TagNode tNode = (TagNode)node;
if (tNode.Attributes.ContainsKey("CLASS"))
{
if (tNode.GetAttribute("CLASS").Contains("female"))//必须先female，因为female中也含有male，如果male在前，则所有用户均符合该条件了= =
{
fan.Gender = "female";
}
else
{
if (tNode.GetAttribute("CLASS").Contains("male"))
{
fan.Gender = "male";
}
else
{
fan.Gender = "unknown";
Console.WriteLine("第" + i + "个粉丝性别不明！");
}
}
}
}
}
fan.Location = locationStr.Trim();
}
else
{
Console.WriteLine("第" + i + "个粉丝中，获取粉丝地点的标准出错！");
}
}
else
{
Console.WriteLine("第" + i + "个粉丝中，获取该粉丝的UserID、地点和性别信息的标准出错！");
}
#endregion
#region 获取该粉丝关注用户的方式
NodeList followMethodNodeList = fanBullet.Children.ExtractAllNodesThatMatch(followMethodFilter, true);
if (followMethodNodeList.Size() == 1)
{
NodeList methodNodeList = followMethodNodeList[0].Children.ExtractAllNodesThatMatch(new NodeClassFilter(typeof(ATag)));
if (methodNodeList.Size() == 1)
{
ATag methodNode = (ATag)methodNodeList[0];
fan.FollowMethod = methodNode.StringText.Trim();
}
else
{
Console.WriteLine("第" + i + "个粉丝中，获取该粉丝关注用户的方式的数量出错！");
}
}
else
{
Console.WriteLine("第" + i + "个粉丝中，获取该粉丝关注用户的方式的标准出错！");
}
#endregion
fansList.Add(fan);
}
}
public void GetInfoFromHtml(int currentPage)
{
Lexer lexer = new Lexer(currentHtml);
Parser parser = new Parser(lexer);
NodeList poiHeadList = parser.Parse(poiListFilter);
if (poiHeadList.Count == 1)
{
NodeList poiNodeList = poiHeadList[0].Children.ExtractAllNodesThatMatch(poiFilter, false);
int numCount = 0;
for (int i = 0; i < poiNodeList.Count; i++)
{
POI poi = new POI();
DefinitionListBullet poiNode = (DefinitionListBullet)poiNodeList[i];
if (poiNode.TagName.Equals("DD"))
{
numCount++;
poi.Page = currentPage;
poi.Number = numCount;
#region 获取口味、环境和服务评分，以及获取星级
NodeList tasteNodeList = poiNode.Children.ExtractAllNodesThatMatch(tasteFilter, true);
NodeList environmentNodeList = poiNode.Children.ExtractAllNodesThatMatch(environmentFilter, true);
NodeList serviceNodeList = poiNode.Children.ExtractAllNodesThatMatch(serviceFilter, true);
if (tasteNodeList.Count == 1 && environmentNodeList.Count == 1 && serviceNodeList.Count == 1)
{
Span spanNode = (Span)tasteNodeList[0];
if (!spanNode.ToPlainTextString().Equals("-"))
{
poi.TasteRemark = Int32.Parse(spanNode.ToPlainTextString());
}
spanNode = (Span)environmentNodeList[0];
if (!spanNode.ToPlainTextString().Equals("-"))
{
poi.EnvironmentRemark = Int32.Parse(spanNode.ToPlainTextString());
}
spanNode = (Span)serviceNodeList[0];
if (!spanNode.ToPlainTextString().Equals("-"))
{
poi.ServiceRemark = Int32.Parse(spanNode.ToPlainTextString());
}
#region 获取星级
INode rankNodeOfParent = spanNode.Parent.NextSibling.NextSibling;
if (rankNodeOfParent.Children != null && rankNodeOfParent.Children.Count >= 1)
{
INode rankNodeCandidate = rankNodeOfParent.Children[0];
if (rankNodeCandidate.GetType().Equals(typeof(Span)))
{
Span rankNode = (Span)rankNodeCandidate;
string rank = rankNode.GetAttribute("TITLE");
if (rank.Contains("五"))
{
poi.Rank = 5;
}
else
{
if (rank.Contains("四"))
{
poi.Rank = 4;
}
else
{
if (rank.Contains("三"))
{
poi.Rank = 3;
}
else
{
if (rank.Contains("二"))
{
poi.Rank = 2;
}
else
{
if (rank.Contains("一"))
{
poi.Rank = 1;
}
}
}
}
}
}
}
#endregion
}
else
{
Console.WriteLine("第" + i + "条POI中，判断口味、环境和服务的标准出错！");
}
#endregion
#region 获取平均消费
NodeList averageNodeList = poiNode.Children.ExtractAllNodesThatMatch(averageFilter, true);
if (averageNodeList.Count == 1)
{
INode averageNode = averageNodeList[0];
if (averageNode.NextSibling.NextSibling.GetType().Equals(typeof(TextNode)))
{
string cost = ((TextNode)averageNode.NextSibling.NextSibling).ToPlainTextString();
poi.AverageCost = Int32.Parse(cost);
}
}
else
{
Console.WriteLine("第" + i + "条POI中，判断平均消费的标准出错！");
}
#endregion
#region 获取点评数
NodeList commentNodeList = poiNode.Children.ExtractAllNodesThatMatch(commentFilter, true);
if (commentNodeList.Count == 1)
{
INode commentNode = commentNodeList[0];
if (commentNode.GetType().Equals(typeof(ATag)))
{
string commentNum = ((ATag)commentNode).StringText;
if (commentNum.Substring(commentNum.Length - 3, 3).Equals("封点评"))
{
commentNum = commentNum.Substring(0, commentNum.Length - 3);
}
poi.CommentCount = Int32.Parse(commentNum);
}
}
else
{
Console.WriteLine("第" + i + "条POI中，判断点评数的标准出错！");
}
#endregion
#region 获取店名
NodeList nameNodeList = poiNode.Children.ExtractAllNodesThatMatch(nameFilter, true);
if (nameNodeList.Count == 1)
{
INode nameNode = nameNodeList[0];
if (nameNode.GetType().Equals(typeof(ATag)))
{
poi.Name = ((ATag)nameNode).StringText;
}
}
else
{
Console.WriteLine("第" + i + "条POI中，判断店名的标准出错！");
}
#endregion
#region 获取地址和电话
NodeList addressNodeList = poiNode.Children.ExtractAllNodesThatMatch(addressFilter, true);
if (addressNodeList.Count == 1)
{
NodeList districtNodeList = addressNodeList[0].Children.ExtractAllNodesThatMatch(new NodeClassFilter(typeof(ATag)));
if (districtNodeList.Count == 1)
{
ATag districtTag = (ATag)districtNodeList[0];
string address = districtTag.ToPlainTextString();
if (districtTag.NextSibling.GetType().Equals(typeof(TextNode)))
{
TextNode detailAddressNode = (TextNode)districtTag.NextSibling;
string detailAddress = detailAddressNode.ToPlainTextString();
detailAddress = detailAddress.Trim();
string phoneStr = detailAddress.Substring(detailAddress.Length - 8, 8);
poi.Phone = phoneStr;
address += detailAddress.Substring(0, detailAddress.Length - 8);
}
char[] removeChrVector = { ' ', '\n', '\t' };
address = address.Trim(removeChrVector);
foreach (char c in removeChrVector)
{
address = address.Replace(c.ToString(), "");
}
poi.Address = address;
}
else
{
Console.WriteLine("第" + i + "条POI中，判断含地址的<a>标记的标准出错！");
}
}
else
{
Console.WriteLine("第" + i + "条POI中，判断地址的标准出错！");
}
#endregion
#region 获取标签
NodeList tagsNodeList = poiNode.Children.ExtractAllNodesThatMatch(tagsFilter, true);
if (tagsNodeList.Count == 1)
{
INode tagsNode = tagsNodeList[0];
if (tagsNode.Children != null)
{
for (int j = 0; j < tagsNode.Children.Count; j++)
{
INode node = tagsNode.Children[j];
if (node.GetType().Equals(typeof(ATag)))
{
poi.Tags.Add(node.ToPlainTextString());
}
}
}
}
else
{
Console.WriteLine("第" + i + "条POI中，判断标签的标准出错！");
}
#endregion
poiList.Add(poi);
}
}
}
else
{
Console.WriteLine("获取POI列表出错");
}
}
public void GetLinkForPage(string url)
{
Lexer lexer = new Lexer(GetHtml(url));
Parser parse = new Parser(lexer);
parse.Encoding = "gb2312";
NodeFilter linkFilter = new LinkRegexFilter(@"^http\://item\.taobao\.com/item\.htm\?id\=\d+$");
NodeFilter classFilter = new HasAttributeFilter("class", "EventCanSelect");
AndFilter andFilter = new AndFilter(linkFilter, classFilter);
NodeList result = parse.Parse(andFilter);
int length = result.Count;
for (int i = 0; i < length; i++)
{
ItemLink.Add(result[i]);
}
}
public List<ATag> ParseCatelog(string html)
{
List<ATag> atags = new List<ATag>();
Lexer lexer = new Lexer(html);
Parser parser = new Parser(lexer);
NodeFilter nav = new HasAttributeFilter("class", "fenlei_list");
NodeList navNodes = parser.Parse(nav);
NodeFilter catelog = new LinkRegexFilter(@"^\.\./product/index\.php\?cplm\=\-\d\d\d\-$");
catelog = new HasChildFilter(catelog);
NodeList catelogNodes = navNodes[0].Children.ExtractAllNodesThatMatch(catelog);
if(catelogNodes==null){
return atags;
}
int length = catelogNodes.Count;
for (int i=0;i<length;i++)
{
INode node = catelogNodes[i];
ATag a = node.Children[0] as ATag;
atags.Add(a);
}
return atags;
}
/// <summary>
/// 辅助函数：从HTML中获得max_id
/// </summary>
/// <param name="htmlContent">HTML文本</param>
/// <returns></returns>
private bool GetMaxIdFromHtml(string htmlContent)
{
Lexer lexer = new Lexer(htmlContent);
Parser parser = new Parser(lexer);
NodeList feedNodeList = parser.Parse(idFilter[(int)Type]);
if (feedNodeList.Size() >= 1)
{
max_id = ((TagNode)feedNodeList[feedNodeList.Size() - 1]).GetAttribute("MID");
return true;
}
else
{
return false;
}
}
/// <summary>
/// 辅助函数：从HTML中获得end_id
/// </summary>
/// <param name="htmlContent">HTML文本</param>
/// <returns></returns>
private bool GetEndIdFromHtml(string htmlContent)
{
Lexer lexer = new Lexer(htmlContent);
Parser parser = new Parser(lexer);
NodeList feedNodeList = parser.Parse(idFilter[(int)Type]);
if (feedNodeList.Size() >= 1 && feedNodeList[0].GetType().Equals(typeof(Div)) && ((TagNode)feedNodeList[0]).Attributes.ContainsKey("MID"))
{
end_id = ((TagNode)feedNodeList[0]).GetAttribute("MID");
return true;
}
else
{
return false;
}
}
/// <summary>
/// 从网页版微博中获取微博信息
/// </summary>
/// <param name="currentPage">爬得的微博所在页面序号</param>
/// <param name="feedList">保存爬得的微博的数组</param>
public void GetInfoFromHtml(int currentPage, List<Feed> feedList)
{
foreach (string htmlContent in htmlContentList)
{
Lexer lexer = new Lexer(htmlContent);
Parser parser = new Parser(lexer);
//获取包含每条微博的div标记列表
NodeList feedNodeList = parser.Parse(feedFilter);
for (int i = 0; i < feedNodeList.Size(); i++)
{
serialNumber++;
Feed feed = new Feed();
feed.Page = currentPage;
feed.Number = serialNumber;
//类似微博转发的数量
int similarFeedCount = 0;
//取得第i条微博的div
TagNode feedDiv = (TagNode)feedNodeList[i];
//判断是否含有“还有X条对原微博的转发”
NodeList similarfeedCountNodeList = feedDiv.Children.ExtractAllNodesThatMatch(similarFeedCountFilter, true);
switch (similarfeedCountNodeList.Size())
{
case 1:
//说明存在“还有X条对原微博的转发”的div；此处看起来此HTML解析器不认<b>标记，而把其中包含的内容作为其下一个兄弟节点= =
similarFeedCount = Int32.Parse(((TextNode)(similarfeedCountNodeList[0].NextSibling)).ToPlainTextString());
break;
case 0:
//说明不存在“还有X条对原微博的转发”
similarFeedCount = 0;
break;
default:
Console.WriteLine("第" + i + "条微博中，判断是否含有类似微博转发的标准出错！");
break;
}
#region 获取微博作者
NodeList feedAuthorNodeList = feedDiv.Children.ExtractAllNodesThatMatch(feedAuthorFilter, true);
//在整个一条微博的范围（即一个feedDiv）内，满足feedAuthorFilter过滤器的div节点数量应该是本条微博作者加上转发类似微博的作者（如果有的话），所以是(1 + similarFeedCount)
if (feedAuthorNodeList.Size() == (1 + similarFeedCount))
{
ATag feedAuthorTag = (ATag)feedAuthorNodeList[0].Children[0];
string author = feedAuthorTag.GetAttribute("TITLE");
feed.Author = author;
//如果存在，则获取该作者的备注名
INode remarkNameNode = feedAuthorTag.NextSibling;
if (remarkNameNode.GetType().Equals(typeof(Span)))
{
string remarkName = ((Span)remarkNameNode).StringText;
//去掉前后括号
remarkName = remarkName.Substring(1, remarkName.Length - 2);
feed.RemarkName = remarkName;
}
}
else
{
//从首页爬取微博时，微博来自不同的被关注者，所以是有微博作者的；而从个人主页爬取微博时，由于所有微博作者都是该用户，所以是没有微博作者相关节点的
if (!user.NickName.Equals(""))
{
feed.Author = user.NickName;
feed.RemarkName = user.RemarkName;
}
else
{
Console.WriteLine("第" + i + "条微博中，判断微博作者的标准出错！");
}
}
#endregion
#region 获取转发微博
NodeList reFeedNodeList = feedDiv.Children.ExtractAllNodesThatMatch(reFeedFilter, true);
//转发微博；(1 + similarFeedCount)的理由和获取微博作者时相同
if (reFeedNodeList.Size() == (1 + similarFeedCount))
{
//获取转发微博的div
TagNode reFeedDiv = (TagNode)reFeedNodeList[0];
//先获取本次转发微博的相关信息
GetReFeedInfo(i, feed, reFeedDiv, feedDiv);
#region 考虑“还有X条对原微博的转发”的情况
if (similarFeedCount > 0)
{
NodeList similarFeedNodeList = feedDiv.Children.ExtractAllNodesThatMatch(similarFeedFilter, true);
if (similarFeedNodeList.Size() == similarFeedCount)
{
for (int j = 0; j < similarFeedCount; j++)
{
feedList.Add(GetSimilarFeed(currentPage, i, (TagNode)similarFeedNodeList[j], feed.OriginalAuthor, feed.Content));
}
}
else
{
Console.WriteLine("第" + i + "条微博中，获取转发微博的数量出错！");
}
}
#endregion
}
else
{
if (reFeedNodeList.Size() == 0)
{
//获取本条微博内容作为微博内容
NodeList feedContentNodeList = feedDiv.Children.ExtractAllNodesThatMatch(feedContentFilter, true);
if (feedContentNodeList.Size() == 1)
{
feed.Content = GetContentFromChildren(feed, feedContentNodeList[0], false);
#region 由于存在某些情况，转发微博被删除后更不过滤不到reFeedDiv，所以需要再次检查是否存在已删除的转发微博
NodeList deletedFeedList = feedDiv.Children.ExtractAllNodesThatMatch(refeedDeletedFilter2, true);
if (deletedFeedList.Size() > 0)
{
feed.OriginalAuthor = "Unknown";
feed.ReFeedOrNot = true;
feed.ReFeedReason = feed.Content;
feed.Content = "微博已删除";
}
#endregion
}
else
{
Console.WriteLine("第" + i + "条微博中，判断微博内容的标准出错！");
}
}
else
{
Console.WriteLine("第" + i + "条微博中，判断转发微博的标准出错！");
}
}
#endregion
//获取包含微博发送地点的div
feed.Location = GetLocationInfo(i, feedDiv);
//获取包含微博“赞”数的标记
feed.LikeCount = GetFeedLikeInfo(i, feedDiv);
//获取包含微博转发数的链接标记
feed.ReFeedCount = GetFeedForwardCount(i, feedDiv);
//获取包含微博评论数的链接标记
feed.CommentCount = GetFeedCommentCount(i, feedDiv);
//获取包含微博发送时间的链接标记
feed.Time = GetFeedTimeInfo(i, feedDiv);
//获取包含微博发送设备的链接标记
feed.Device = GetFeedSendTypeInfo(i, feedDiv);
feedList.Add(feed);
}
}
}
public void InitPage()
{
Lexer lexer = new Lexer(GetHtml(urlBase));
Parser parse = new Parser(lexer);
parse.Encoding = "gb2312";
NodeFilter linkFilter = new LinkRegexFilter(@"s\=\d+\#J_FilterTabBar");
_linkResult = parse.Parse(linkFilter);
}
public void StartCrawl()// private void BtnDownload_Click(object sender, RoutedEventArgs e)
{
List <ImportInvoiceDTO> list = new List <ImportInvoiceDTO>();
List <hParser.Tags.TableRow> validRowList = new List <hParser.Tags.TableRow>();
this.parseResult = "";
Uri uri = new Uri(this.TargetUri);
#region <N>基于Httphelper，这样下载会要求程序自己实现验证授权
//<N>基于Httphelper，这样下载会要求程序自己实现验证授权
//HttpHelper httpHelper = new HttpHelper();
//HttpItem rq = new HttpItem();
//rq.URL = uri.AbsoluteUri;
//HttpResult html = httpHelper.GetHtml(rq);
//Debug.WriteLine(html.Html);
//直接基于WebBrowser，授权是由用户手动实现的
mshtml.IHTMLDocument2 doc2 = null;//(mshtml.IHTMLDocument2)webBox.Document;
string html = string.Compare(this.IsOffline, "1", StringComparison.InvariantCultureIgnoreCase) == 0 ? s_htmlFake : doc2.body.innerHTML;
Debug.WriteLine(html);
#endregion
#region 使用HtmlParser提取HTML
Lexer lexer = new Lexer(html);
hParser.Parser parser = new hParser.Parser(lexer);
hParser.NodeFilter filter = new NodeClassFilter(typeof(Winista.Text.HtmlParser.Tags.TableRow));
NodeList nodeList = parser.Parse(filter);
if (nodeList.Count == 0)
{
MessageBox.Show("没有符合要求的节点");
}
else
{
for (int i = 0; i < nodeList.Count; i++)
{
//抓取一行
var tagTR = parserTR(nodeList[i]);
#region 充填有效行
if (tagTR != null)
{
validRowList.Add(tagTR);
}
#endregion
}
parserValidTR(validRowList, ref list);
#if DEBUG
// MessageBox.Show(parseResult);
#endif
}
/* parseResult = HtmlText(html);
* MessageBox.Show(parseResult);*/
#endregion
#region 步
if (list == null || list.Count == 0)
{
MessageBox.Show("该页面上没有检测到预期数据");
return;
}
ImportInvoiceListDTO soap = new ImportInvoiceListDTO
{
List = list,
Result = new ImportInvoiceResultDTO
{
Message = "CALLBACK",
Status = 9
}
};
//using (var factory = new ChannelFactory<ISyncImportInvoiceService>("*"))
//{
// var chl = factory.CreateChannel();
// soap = chl.PullImportInvoices(soap);
// if (soap.Result.Status == 0)
// {
// //重试
// soap = chl.PullImportInvoices(soap);
// }
//}
//if (soap.Result.Status == -1)
//{
// // 修改UI线程
// MessageBox.Show(soap.Result.Message);
//}
CallWS(soap);
MessageBox.Show("本页已同步完成，请点击下一页继续同步");
//FakeBusy();
#endregion
}
public void ParseProducts(ATag a)
{
string html = GetHtml(a.Link.Replace("../", "http://rrxf.cn/"));
Lexer lexer = new Lexer(html);
Parser parser = new Parser(lexer);
NodeFilter nav = new HasAttributeFilter("class", "photoyi");
NodeList navNodes = parser.Parse(nav);
if (navNodes == null)
return;
int length = navNodes.Count;
for (int i = 0; i < length; i++)
{
ATag link = ParseProductUrl(navNodes[i].ToHtml());
Console.WriteLine(link.Link);
ParseProduct(link);
}
}
public override IEnumerable <string> Process(string fileName)
{
System.Net.WebClient aWebClient = new System.Net.WebClient();
aWebClient.Encoding = System.Text.Encoding.Default;
string html = aWebClient.DownloadString(this.url);
//string html = File.ReadAllText(fileName);
Lexer lexer = new Lexer(html);
Winista.Text.HtmlParser.Parser parser = new Winista.Text.HtmlParser.Parser(lexer);
NodeList htmlNodes = parser.Parse(null);
List <IsotopicAtom> atoms = new List <IsotopicAtom>();
var node = FindFirstNode(htmlNodes, "tbody");
INode nextNode;
IsotopicAtom atom = null;
while ((nextNode = FindFirstNode(node, "tr")) != null)
{
if (nextNode.Children != null)
{
var tds = nextNode.Children.ExtractAllNodesThatMatch(new NameFilter("td"));
if (tds.Count == 1)
{
atom = null;
}
if (tds.Count >= 3 && tds[0].FirstChild != null)
{
var t1 = tds[0].FirstChild.GetText().Trim();
var t2 = tds[1].FirstChild.GetText().Trim();
if (Char.IsDigit(t1[0]) && Char.IsLetter(t2[0]))
{
atom = new IsotopicAtom();
atoms.Add(atom);
atom.Name = tds[1].FirstChild.GetText().Trim();
Peak p = new Peak();
p.Mz = GetDouble(tds[3]);
p.Intensity = GetDouble(tds[4]);
atom.Isotopics.Add(p);
}
else if (atom != null)
{
var txt = tds[0].FirstChild.GetText().Trim();
if (txt.Length > 0 && Char.IsLetter(txt[0]))
{
tds.Remove(0);
}
Peak p = new Peak();
p.Mz = GetDouble(tds[1]);
p.Intensity = GetDouble(tds[2]);
atom.Isotopics.Add(p);
}
}
}
node = nextNode.NextSibling;
if (node == null)
{
break;
}
}
atoms.ForEach(m => m.Isotopics.RemoveAll(n => n.Intensity == 0.0));
atoms.RemoveAll(m => m.Isotopics.Count == 0);
var dic = atoms.ToDictionary(m => m.Name);
var x = new IsotopicAtom();
x.Name = "X";
x.Isotopics.Add(new Peak(1, 0.9));
x.Isotopics.Add(new Peak(2, 0.1));
atoms.Insert(0, x);
atoms.Add(AddHevayAtom("(H2)", "H", 1, dic));
atoms.Add(AddHevayAtom("(C13)", "C", 1, dic));
atoms.Add(AddHevayAtom("(N15)", "N", 1, dic));
atoms.Add(AddHevayAtom("(O18)", "O", 2, dic));
using (StreamWriter sw = new StreamWriter(fileName))
{
atoms.ForEach(m =>
{
sw.WriteLine("{0}\t{1}", m.Name, m.Isotopics.Count);
m.Isotopics.ForEach(n => sw.WriteLine("{0:0.000000}\t{1:0.000000}", n.Mz, n.Intensity));
sw.WriteLine();
});
}
return(new string[] { fileName });
}
/// <summary>
/// 获取目标数据
/// </summary>
/// <param name="parser">目标html文件</param>
/// <param name="tag">标签名称</param>
/// <param name="attribute">标签里面的属性名称</param>
/// <param name="attValue">属性的值</param>
/// <returns>标签内的目标数据</returns>
public static string getValue(string html, string tag, string attribute, string attValue)
{
Lexer lexer = new Lexer(html);
Parser parser = new Parser(lexer);
string value = string.Empty;
NodeFilter nodeFilter = new HasAttributeFilter(attribute, attValue);
NodeList nodeList = parser.Parse(nodeFilter);
if (nodeList.Count >= 1)
{
ITag tagNode = (nodeList[0] as ITag);
return tagNode.ToPlainTextString();
}
//for (int i = 0; i < nodeList.Count; i++)
//{
// INode node = nodeList[i];
// ITag tagNode = (node as ITag);
// if (tagNode.Attributes != null && tagNode.Attributes.Count > 0)
// {
// foreach (string key in tagNode.Attributes.Keys)
// {
// if (key.Contains("<TAGNAME>"))
// {
// continue;
// }
// if (key.Contains(attribute))
// {
// if (tagNode.Attributes[key].ToString() == attValue)
// {
// value = tagNode.ToPlainTextString();
// return value;
// }
// }
// }
// }
//}
return null;
}
public ATag ParseProductUrl(string html)
{
Lexer lexer = new Lexer(html);
Parser parser = new Parser(lexer);
NodeFilter filter = new LinkRegexFilter(@"lookcp\.php\?cpid\=\d{0,}");
NodeList alist = parser.Parse(filter);
ATag a = alist[0] as ATag;
a.Link = "http://rrxf.cn/product/" + a.Link;
return a;
}
/// <summary>
/// 获得列表
/// </summary>
/// <returns></returns>
public List<OddsLiveMatch> GetScrollMatchList()
{
List<OddsLiveMatch> liveMatchList = new List<OddsLiveMatch>();
try
{
HttpHelper h = new HttpHelper();
Cookie lng = new Cookie("lng", "2");
lng.Domain = domain;
h.CookieContainer.Add(lng);
string zoudi = h.GetHtml("https://" +domain+ "/default.aspx"+ zoudiUrl);
if (!string.IsNullOrEmpty(zoudi))
{
#region 分析网页html节点
Lexer lexer = new Lexer(zoudi);
Parser parser = new Parser(lexer);
NodeList bodyNodes = parser.Parse(new TagNameFilter("HTML"))[0].Children.ExtractAllNodesThatMatch(new TagNameFilter("BODY"))[0].Children;
ITag divNode = bodyNodes.ExtractAllNodesThatMatch(new TagNameFilter("FORM"))[0].Children.ExtractAllNodesThatMatch(new TagNameFilter("DIV"))[0] as ITag;
if (divNode.Attributes["ID"].Equals("PageBody"))
{
NodeList dataDivList = divNode.Children.SearchFor(typeof(Winista.Text.HtmlParser.Tags.Div));
if (dataDivList[0].ToPlainTextString() == "走地盤")
{
if (dataDivList[2].ToPlainTextString() == "全場賽果")
{
return liveMatchList;
}
for (int i = 0; i < dataDivList.Count; i++)
{
ITag div = dataDivList[i] as ITag;
if (div.Attributes["CLASS"] != null && div.Attributes["CLASS"].Equals("menuRow"))
{
OddsLiveMatch oddsLive = new OddsLiveMatch();
oddsLive.urlparams = (div.FirstChild as ITag).Attributes["HREF"].ToString();
oddsLive.id = oddsLive.urlparams.Split('&')[0].Substring(4);
oddsLive.time = DateTime.Now;
oddsLive.name = div.ToPlainTextString();
liveMatchList.Add(oddsLive);
}
}
}
}
#endregion 分析网页html节点
}
}
catch (Exception)
{
}
return liveMatchList;
}
private void CrawlCurrentPage(WebBrowser wb, bool isOffline, bool IsUnConfirmChecked, ref bool hasValidData)
{
mshtml.IHTMLDocument2 doc2 = isOffline ? null : (mshtml.IHTMLDocument2)wb.Document;
string html = isOffline ? s_htmlFake : doc2.body.innerHTML;
Debug.WriteLine(html);
List <ImportInvoiceDTO> list = new List <ImportInvoiceDTO>();
List <hParser.Tags.TableRow> validRowList = new List <hParser.Tags.TableRow>();
//this.parseResult = "";
#region 使用IHTMLDocument2提取HTML
mshtml.HTMLTableClass table = IsUnConfirmChecked ? (mshtml.HTMLTableClass)doc2.all.item("example1", 0) : (mshtml.HTMLTableClass)doc2.all.item("example", 0);
if (table == null)
{
hasValidData = false;
//throw new InvalidOperationException("无效table");
return;
}
mshtml.HTMLTableSectionClass tbody = (mshtml.HTMLTableSectionClass)table.lastChild;
if (tbody == null)
{
hasValidData = false;
//throw new InvalidOperationException("无效tbody");
return;
}
var tbodyHtml = tbody.innerHTML;
if (0 == string.Compare(tbody.innerText, "没找到记录", StringComparison.InvariantCultureIgnoreCase))
{
hasValidData = false;
//throw new InvalidOperationException("无效tbody");
return;
}
#region WPF WebBroswer交互源代码DOM元素总结
#if RESEARCH
//HTMLDocument doc01 = wb.Document as HTMLDocument;
////IHTMLDocument2 doc02 = wb.Document as IHTMLDocument2;
//Debug.WriteLine(doc01.body.innerHTML);
///读/写元素
///
mshtml.IHTMLElement login_pass = (mshtml.IHTMLElement)doc2.all.item("login_pass", 0);
mshtml.IHTMLElement password = (mshtml.IHTMLElement)doc2.all.item("password", 0);
password.setAttribute("value", "12345678");
login_pass.setAttribute("style", "");
mshtml.IHTMLElement login_pass1 = (mshtml.IHTMLElement)doc2.all.item("login_pass1", 0);
mshtml.IHTMLElement password1 = (mshtml.IHTMLElement)doc2.all.item("password1", 0);
login_pass1.setAttribute("style", "display:none;");
//password1.setAttribute("style", "width:1px");
//IHTMLElement item = doc01.getElementById("ptmm");
//item.innerHTML = "<INPUT id=\"pwd\" class=\"login_input password\" type=\"text\" value=\"\" />";
//// doc01.body.insertAdjacentHTML(,);
//MessageBox.Show(item.innerText);
//wb.NavigateToString(doc01.body.innerHTML);
/// Trigger event
//点击确定按钮
loginBT.click();
/// script injection
///
//Basic ds = new Basic();
//wb.ObjectForScripting = ds;//该对象可由显示在WebBrowser控件中的网页所包含的脚本代码访问
///Levarage JS
///
mshtml.IHTMLWindow2 win = (mshtml.IHTMLWindow2)doc2.parentWindow;
win.execScript("Login('12345678', '', 1)", "javascript");
return;
#endif
#endregion
#endregion
#region 使用HtmlParser提取tbodyHtml
Lexer lexer = new Lexer(tbodyHtml);
hParser.Parser parser = new hParser.Parser(lexer);
hParser.NodeFilter filter = new NodeClassFilter(typeof(Winista.Text.HtmlParser.Tags.TableRow));
NodeList nodeList = parser.Parse(filter);
if (nodeList.Count == 0)
{
hasValidData = false;
MessageBox.Show("没有符合要求的节点");
}
else
{
for (int i = 0; i < nodeList.Count; i++)
{
//抓取一行
var tagTR = parserTR(nodeList[i]);
#region 充填有效行
if (tagTR != null)
{
validRowList.Add(tagTR);
}
#endregion
}
parserValidTR(validRowList, IsUnConfirmChecked, ref list);
}
#endregion
#region 使用HtmlParser提取HTML
/* Lexer lexer = new Lexer(html);
* hParser.Parser parser = new hParser.Parser(lexer);
* hParser.NodeFilter filter = new NodeClassFilter(typeof(Winista.Text.HtmlParser.Tags.TableRow));
* NodeList nodeList = parser.Parse(filter);
* if (nodeList.Count == 0)
* MessageBox.Show("没有符合要求的节点");
* else
* {
* for (int i = 0; i < nodeList.Count; i++)
* {
* //抓取一行
* var tagTR = parserTR(nodeList[i]);
*
#region 充填有效行
* if (tagTR != null)
* validRowList.Add(tagTR);
#endregion
*
* }
*
* parserValidTR(validRowList, ref list);
*
* }
*/
#endregion
#region 日志 & 导出 & 持久化
if (list == null || list.Count == 0)
{
MessageBox.Show("该页面上没有检测到预期数据");
hasValidData = false;
}
ImportInvoiceListDTO soap = new ImportInvoiceListDTO
{
List = list,
Result = new ImportInvoiceResultDTO
{
Message = "CALLBACK",
Status = 9
}
};
Debug.Write(soap);
#region Log
if (this.IfLog == "1")
{
soap.List.ForEach(impinfo =>
{
if (IsUnConfirmChecked)
{
LogHelper.WriteLog(typeof(WebBoxView), string.Format("发票代码{0} 发票号码{1} 开票日期{2} 销方税号{3} 金额{4} 税额{5} 来源{6} 发票状态{7} 勾选标志{8} 操作时间{9}", impinfo.InvoiceCode, impinfo.InvoiceNumber, impinfo.CreateDate, impinfo.SalesTaxNumber, impinfo.Amount, impinfo.Tax, impinfo.From, impinfo.Status, impinfo.SelectTag, impinfo.ChosenTime));
}
else
{
LogHelper.WriteLog(typeof(WebBoxView), string.Format("发票代码{0} 发票号码{1} 开票日期{2} 销方税号{3} 金额{4} 税额{5} 来源{6} 发票状态{7} 确认月份{8}", impinfo.InvoiceCode, impinfo.InvoiceNumber, impinfo.CreateDate, impinfo.SalesTaxNumber, impinfo.Amount, impinfo.Tax, impinfo.From, impinfo.Status, impinfo.SelectTag));
}
});
}
#endregion
if (this.IfCallWS == "1")
{
CallWS(soap);
}
Debug.Write("本页已同步完成，请点击下一页继续同步");
//FakeBusy();
#endregion
}