public override Queue <BasicComicInfo> GetTopComic(string response)
{
Queue <BasicComicInfo> queue;
queue = new Queue <BasicComicInfo>();
HtmlNode mainNode = GetMainNode(response);
if (mainNode == null || response == "")
{
return(queue);
}
BasicComicInfo comicInfo;
HtmlNodeCollection collect = mainNode.SelectNodes("//div[@class='cTabHotHtmHide']/li");
foreach (HtmlNode nodeTemp in collect)
{
comicInfo = new BasicComicInfo();
comicInfo.ComicHref = hostName + nodeTemp.SelectSingleNode("./a").Attributes["href"].Value;
comicInfo.ComicName = nodeTemp.SelectSingleNode("./a").Attributes["title"].Value;
comicInfo.ComicImgUrl = nodeTemp.SelectSingleNode("./a/img").Attributes["src"].Value;
queue.Enqueue(comicInfo);
}
return(queue);
}
public override SearchResult GetSearchComic(string response)
{
SearchResult searchResult;
BasicComicInfo basicComicInfo;
searchResult = new SearchResult();
HtmlNode mainNode = GetMainNode(response);
Queue <BasicComicInfo> queue = new Queue <BasicComicInfo>();
searchResult.SearchQueue = queue;
if (response == "")
{
return(searchResult);
}
HtmlNodeCollection nodeCollect = mainNode.SelectNodes("//ul[@class='list_con_li update_con autoHeight']/li");
if (nodeCollect != null)
{
foreach (HtmlNode node in nodeCollect)
{
basicComicInfo = new BasicComicInfo();
basicComicInfo.ComicHref = node.SelectSingleNode("./a").Attributes["href"].Value;
basicComicInfo.ComicName = node.SelectSingleNode("./a").Attributes["title"].Value;
basicComicInfo.ComicImgUrl = node.SelectSingleNode("./a/img").Attributes["src"].Value;
queue.Enqueue(basicComicInfo);
}
}
string key = "";
nodeCollect = mainNode.SelectNodes("//ul[@class='pagination']/li/a");
if (nodeCollect != null)
{
Dictionary <string, string> dict = new Dictionary <string, string>();
foreach (HtmlNode temp in nodeCollect)
{
key = temp.InnerText;
if (dict.ContainsKey(key) == false)
{
dict.Add(key, hostName + temp.Attributes["href"].Value);
}
}
if (dict.ContainsKey("下一页"))
{
searchResult.NextPageUrl = dict["下一页"];
}
}
int num = Convert.ToInt32(mainNode.SelectSingleNode("//em[@class='c_6']").InnerText);
searchResult.Count = num;
return(searchResult);
}
public override SearchResult GetSearchComic(string response)//给出搜索漫画结果
{
BasicComicInfo comicInfo;
SearchResult result = new SearchResult();
Queue <BasicComicInfo> queue = new Queue <BasicComicInfo>();
Regex[] regex = new Regex[3];
regex[0] = new Regex(@"(?<count>\d+)</\w+>\s*本相关漫画");
regex[1] = new Regex(@"img\salt='(?<title>[\w\s，。！]*)?(<font\s*color=red>)?\s*(?<title1>[\w\s，。！]*)?(</font>)?(?<title2>\w+)?'\s*src='(?<url>[\w./:-]*)'></div>\s*<div\s*class='cListTitle'>\s*<a\s*target='_blank'\s*href='(?<href>[\w-/]*)'");
regex[2] = new Regex(@"");//下一页
foreach (Match macth in regex[1].Matches(response))
{
comicInfo = new BasicComicInfo();
comicInfo.ComicHref = hostName + macth.Groups["href"].Value;
comicInfo.ComicName = macth.Groups["title"].Value + macth.Groups["title1"].Value + macth.Groups["title2"].Value;
comicInfo.ComicImgUrl = macth.Groups["url"].Value;
queue.Enqueue(comicInfo);
}
var count = regex[0].Match(response).Groups["count"].Value;
if (count != "")
{
result.Count = Convert.ToInt32(count);
}
else
{
result.Count = 0;
}
result.SearchQueue = queue;
return(result);
}
public override Queue <BasicComicInfo> GetTopComic(string response)
{
string title = "";
string href = "";
string url = "";
BasicComicInfo basicCominfo;
Queue <BasicComicInfo> queue = new Queue <BasicComicInfo>();
HtmlDocument document = new HtmlDocument();
document.LoadHtml(response);
HtmlNodeCollection collect = document.DocumentNode.SelectNodes("//div[@class='cHpComic']");
foreach (var i in collect)
{
basicCominfo = new BasicComicInfo();
title = i.SelectSingleNode("./a[@target='_blank']").Attributes["title"].Value;
href = i.SelectSingleNode("./a[@target='_blank']").Attributes["href"].Value;
url = i.SelectSingleNode("./a/img").Attributes["src"].Value;
basicCominfo.ComicName = title;
basicCominfo.ComicImgUrl = url;
basicCominfo.ComicHref = hostName + href;
queue.Enqueue(basicCominfo);
}
return(queue);
}
public override Queue <BasicComicInfo> GetTopComic(string response)
{
Queue <BasicComicInfo> queue = new Queue <BasicComicInfo>();
HtmlNode mainNode = GetMainNode(response);
HtmlNode node = mainNode.SelectSingleNode("//ul[@class='list_con_li clearfix']");
HtmlNodeCollection collect = node.SelectNodes("./li");
if (collect == null)
{
return(queue);
}
BasicComicInfo comicInfo;
foreach (HtmlNode nodeTemp in collect)
{
comicInfo = new BasicComicInfo();
comicInfo.ComicHref = nodeTemp.SelectSingleNode("./a").Attributes["href"].Value;
comicInfo.ComicName = nodeTemp.SelectSingleNode("./a/img").Attributes["alt"].Value;
comicInfo.ComicImgUrl = nodeTemp.SelectSingleNode("./a/img").Attributes["src"].Value;
queue.Enqueue(comicInfo);
}
return(queue);
}
public override Queue <BasicComicInfo> GetTopComic(string response)
{
HtmlDocument doc;
BasicComicInfo comicInfo;
Queue <BasicComicInfo> queue;
doc = new HtmlDocument();
queue = new Queue <BasicComicInfo>();
doc.LoadHtml(response);
HtmlNodeCollection collection = doc.DocumentNode.SelectNodes("//div[@class='itemBox']/div[@class='itemImg']");
if (collection == null)
{
return(queue);
}
foreach (HtmlNode node in collection)
{
comicInfo = new BasicComicInfo();
comicInfo.ComicHref = node.SelectSingleNode("./a").Attributes["href"].Value;
comicInfo.ComicName = node.SelectSingleNode("./a/mip-img").Attributes["alt"].Value;
comicInfo.ComicImgUrl = node.SelectSingleNode("./a/mip-img").Attributes["src"].Value;
queue.Enqueue(comicInfo);
}
return(queue);
}
public override CategoryCollect FindComicByCategory(string cateGoryStr)//实现漫画目录图片枚举
{
Regex regex;
BasicComicInfo basic;
CategoryCollect category = new CategoryCollect();
var comicQueue = new Queue <BasicComicInfo>();
HtmlDocument document = new HtmlDocument();
document.LoadHtml(cateGoryStr);
HtmlNode node = document.DocumentNode.SelectSingleNode("//div[@class='cComicList']");
HtmlNodeCollection collect = node.SelectNodes("./li/a");
foreach (var i in collect)
{
basic = new BasicComicInfo();
basic.ComicHref = hostAttach + i.Attributes["href"].Value;
basic.ComicName = i.Attributes["title"].Value;
basic.ComicImgUrl = i.SelectSingleNode("./img").Attributes["src"].Value;
comicQueue.Enqueue(basic);
}
regex = new Regex(@"href='(?<href>[\w:/.]*)'>\s*下一页");//还可以修改，暂时不动
category.NextPageUrl = hostAttach + regex.Match(cateGoryStr).Groups["href"].Value;
category.ComicQueue = comicQueue;
category.PagesCollection = new Dictionary <string, string>();
return(category);
}
public override SearchResult GetSearchComic(string response)
{
BasicComicInfo comicInfo;
SearchResult result = new SearchResult();
Queue <BasicComicInfo> queue = new Queue <BasicComicInfo>();
HtmlDocument document = new HtmlDocument();
document.LoadHtml(response);
HtmlNode node = document.DocumentNode.SelectSingleNode("//div[@class='cComicList']");
HtmlNodeCollection collect = node.SelectNodes("./li/a");
foreach (var i in collect)
{
comicInfo = new BasicComicInfo();
comicInfo.ComicHref = hostAttach + i.Attributes["href"].Value;
comicInfo.ComicName = i.Attributes["title"].Value;
comicInfo.ComicImgUrl = i.SelectSingleNode("./img").Attributes["src"].Value;
queue.Enqueue(comicInfo);
}
result.Count = queue.Count;
result.SearchQueue = queue;
result.NextPageUrl = "";
return(result);
}
public override Queue <BasicComicInfo> GetTopComic(string response)
{
string temp;
HtmlNode node;
HtmlDocument doc;
doc = new HtmlDocument();
doc.LoadHtml(response);
Queue <BasicComicInfo> queue;
BasicComicInfo basicInfo;
queue = new Queue <BasicComicInfo>();
HtmlNodeCollection nodeCollect = doc.DocumentNode.SelectNodes("//div[@class='mh-item']");
foreach (HtmlNode n in nodeCollect)
{
node = n.SelectSingleNode("./p[@class='mh-cover ']");
if (node == null)
{
continue;
}
temp = node.Attributes["style"].Value;
basicInfo = new BasicComicInfo();
basicInfo.ComicImgUrl = temp.Substring(temp.IndexOf("(") + 1, temp.Length - temp.IndexOf("(") - 2);
node = n.SelectSingleNode("./div[@class='mh-item-detali']");
basicInfo.ComicName = node.SelectSingleNode("./h2/a").Attributes["title"].Value;
basicInfo.ComicHref = hostAttach + node.SelectSingleNode("./h2/a").Attributes["href"].Value;
queue.Enqueue(basicInfo);
}
return(queue);
}
public override CategoryCollect FindComicByCategory(string cateGoryStr)//通过漫画分类获取漫画
{
var basicInfo = new BasicComicInfo();
var comicCollect = new CategoryCollect();
var bookList = AnalyseTool.GetTag(cateGoryStr, @"<div class=""book-list"">", "</div>");
comicCollect.Count = 0;
Regex regex = new Regex(@"href=""(?<href>[/\w]*)""\stitle=""(?<title>[\w\&！!，s]*)""><img\s*(data-src|src)=""(?<url>[:\w./]*)""");
var comicQueue = new Queue <BasicComicInfo>();
foreach (Match i in regex.Matches(bookList))
{
basicInfo = new BasicComicInfo();
basicInfo.ComicHref = host + i.Groups["href"].Value;
basicInfo.ComicName = i.Groups["title"].Value;
basicInfo.ComicImgUrl = i.Groups["url"].Value;
comicQueue.Enqueue(basicInfo);
}
var pageInfo = AnalyseTool.GetTag(cateGoryStr, @"<div class=""pager-cont"">", "</div>");
regex = new Regex(@"href=""(?<href>[/\w._]*)""\s*\w+=""[\w-:;]*"">下一页");
comicCollect.NextPageUrl = homePage + regex.Match(cateGoryStr).Groups["href"].Value;
comicCollect.Count = comicQueue.Count;
comicCollect.ComicQueue = comicQueue;
return(comicCollect);
}
//需要修改路径和标签
public override CategoryCollect FindComicByCategory(string cateGoryStr)
{
HtmlDocument doc;
HtmlNode node;
BasicComicInfo basicInfo;
HtmlNodeCollection collect;
CategoryCollect cateCollect;
Queue <BasicComicInfo> comicQueue;
basicInfo = null;
doc = new HtmlDocument();
cateCollect = new CategoryCollect();
comicQueue = new Queue <BasicComicInfo>();
doc.LoadHtml(cateGoryStr);
collect = doc.DocumentNode.SelectNodes("//ul[@class='liemh htmls indliemh']/li");
foreach (HtmlNode temp in collect)
{
basicInfo = new BasicComicInfo();
node = temp.SelectSingleNode("./a");
basicInfo.ComicName = node.Attributes["title"].Value;
basicInfo.ComicHref = node.Attributes["href"].Value;
basicInfo.ComicImgUrl = temp.SelectSingleNode("./a/img").Attributes["src"].Value;
comicQueue.Enqueue(basicInfo);
}
node = doc.DocumentNode.SelectSingleNode("//div[@class='pagination-wrapper']");
cateCollect.NextPageUrl = hostName + node.SelectNodes("./a[@class='next']")[0].Attributes["href"].Value;
cateCollect.Count = comicQueue.Count;
cateCollect.ComicQueue = comicQueue;
return(cateCollect);
}
public override Queue <BasicComicInfo> GetTopComic(string response)
{
HtmlDocument doc;
HtmlNodeCollection tempCollect;
BasicComicInfo basic = null;
Queue <BasicComicInfo> queue = null;
Dictionary <string, string> dict;
doc = new HtmlDocument();
dict = new Dictionary <string, string>();
queue = new Queue <BasicComicInfo>();
doc.LoadHtml(response);
HtmlNodeCollection collect = doc.DocumentNode.SelectNodes("//ul[@class='liemh indliemh']");
foreach (HtmlNode node in collect)
{
tempCollect = node.SelectNodes("./li/a");
foreach (HtmlNode node1 in tempCollect)
{
if (dict.ContainsKey(node1.Attributes["title"].Value) == false)
{
basic = new BasicComicInfo();
basic.ComicHref = node1.Attributes["href"].Value;
basic.ComicName = node1.Attributes["title"].Value;
basic.ComicImgUrl = node1.SelectSingleNode("./img").Attributes["src"].Value;
queue.Enqueue(basic);
}
}
}
return(queue);
}
public override Queue <BasicComicInfo> GetTopComic(string response)
{
Queue <BasicComicInfo> comicQueue;
BasicComicInfo basic;
comicQueue = new Queue <BasicComicInfo>();
response = AnalyseTool.GetTag(response, @"<div class=""cmt-cont cf""", "</div>");
var pattern = @"href=""(?<href>[/\w]*)""\s*title=""(?<title>[\w\s;！♀♂&【】&]*)""><img\s*(src|data-src)=""(?<url>[:\w/.]*)""";
Regex regex = new Regex(pattern);
MatchCollection matchCollect = regex.Matches(response);
var count = 0;
foreach (Match i in matchCollect)
{
basic = new BasicComicInfo();
basic.ComicName = i.Groups["title"].Value;
basic.ComicImgUrl = i.Groups["url"].Value;
basic.ComicHref = host + i.Groups["href"].Value;
comicQueue.Enqueue(basic);
count++;
}
return(comicQueue);
}
public override SearchResult GetSearchComic(string response)
{
BasicComicInfo comicInfo;
SearchResult result = new SearchResult();
Queue <BasicComicInfo> queue = new Queue <BasicComicInfo>();
Regex[] regex = new Regex[2];
regex[0] = new Regex(@"找到\s*(<\w+>)?(?<count>\d+)");
regex[1] = new Regex(@"<a\sclass=""bcover""\s*href=""(?<href>[\w/_-]*)""\s*title=""(?<title>[\：\w\s\[\]\！\。\、\-\—\~\（\）\！]*)"">\s*<img\s*src=""(?<url>[\w\s/:.]*)""");
var count = regex[0].Match(response).Groups["count"].Value;
result.Count = Convert.ToInt32(count);
foreach (Match match in regex[1].Matches(response))
{
comicInfo = new BasicComicInfo();
comicInfo.ComicHref = homePage + match.Groups["href"].Value;
comicInfo.ComicImgUrl = match.Groups["url"].Value;
comicInfo.ComicName = match.Groups["title"].Value;
queue.Enqueue(comicInfo);
}
result.SearchQueue = queue;
return(result);
}
public override SearchResult GetSearchComic(string response)
{
BasicComicInfo comicInfo;
SearchResult result = new SearchResult();
HtmlNode mainNode = GetMainNode(response);
HtmlNodeCollection nodeCollect = mainNode.SelectNodes("//div[@class='mh-item-detali']/h2/a");
result.SearchQueue = new Queue <BasicComicInfo>();
result.Count = 0;
if (nodeCollect == null)
{
return(result);
}
foreach (HtmlNode node in nodeCollect)
{
comicInfo = new BasicComicInfo();
comicInfo.ComicHref = host + node.Attributes["href"].Value;
comicInfo.ComicImgUrl = mainNode.SelectSingleNode("//img[@class='mh-cover']").Attributes["src"].Value;
comicInfo.ComicName = node.Attributes["title"].Value;
result.SearchQueue.Enqueue(comicInfo);
}
result.Count = result.SearchQueue.Count;
return(result);
}
public override CategoryCollect FindComicByCategory(string cateGoryStr)
{
string tempStr = "";
HtmlDocument doc;
HtmlNode node;
BasicComicInfo basic;
Dictionary <string, string> dict;
Queue <BasicComicInfo> queue;
CategoryCollect collectInfo;
queue = new Queue <BasicComicInfo>();
collectInfo = new CategoryCollect();
doc = new HtmlDocument();
doc.LoadHtml(cateGoryStr);
HtmlNodeCollection collect = doc.DocumentNode.SelectNodes("//div[@class='box-body']/ul[@class='mh-list col7']/li/div[@class='mh-item']");
foreach (HtmlNode temp in collect)
{
basic = new BasicComicInfo();
node = temp.SelectSingleNode("./div[@class='mh-item-detali']/h2[@class='title']/a");
basic.ComicName = node.Attributes["title"].Value;
basic.ComicHref = hostAttach + node.Attributes["href"].Value;
node = temp.SelectSingleNode("./p[@class='mh-cover']");
tempStr = node.Attributes["style"].Value;
basic.ComicImgUrl = tempStr.Substring(tempStr.IndexOf("(") + 1, tempStr.IndexOf(")") - tempStr.IndexOf("(") - 1);
queue.Enqueue(basic);
}
node = doc.DocumentNode.SelectSingleNode("//div[@class='page-pagination pull-right mt20']");
collect = node.SelectNodes("./ul/li/a");
dict = new Dictionary <string, string>();
var count = 0;
var index = 0;
foreach (HtmlNode temp in collect)
{
count++;
tempStr = temp.Attributes["data-index"].Value;
if (dict.ContainsKey(tempStr) == false)
{
dict.Add(tempStr, hostAttach + temp.Attributes["href"].Value);
}
if (temp.Attributes["class"] != null && temp.Attributes["class"].Value == "active")
{
index = count;
}
}
collectInfo.NextPageUrl = dict[(index + 1).ToString()];
collectInfo.ComicQueue = queue;
collectInfo.Count = queue.Count;
collectInfo.PagesCollection = dict;
return(collectInfo);
}
public virtual Queue <BasicComicInfo> GetTopComic(string response)//获取热门漫画
{
BasicComicInfo comicInfo;
comicInfo = new BasicComicInfo();
Queue <BasicComicInfo> queue = new Queue <BasicComicInfo>();
return(queue);
}
public override SearchResult GetSearchComic(string response)
{
BasicComicInfo basic;
SearchResult result = new SearchResult();
HtmlNodeCollection nodeCollect;
HtmlDocument doc;
doc = new HtmlDocument();
doc.LoadHtml(response);
nodeCollect = doc.DocumentNode.SelectNodes("//div[@class='mh-item']");
result.Count = 0;
string strTemp;
HtmlNode subNode;
Queue <BasicComicInfo> queue;
queue = new Queue <BasicComicInfo>();
if (nodeCollect == null)
{
return(result);
}
subNode = doc.DocumentNode.SelectSingleNode("//header[@class='box-header']");
strTemp = subNode.SelectSingleNode("./h1/span").InnerText;
strTemp = Regex.Match(strTemp, @"\d+").Value;
result.Count = Convert.ToInt32(strTemp);
foreach (HtmlNode temp in nodeCollect)
{
basic = new BasicComicInfo();
strTemp = temp.SelectSingleNode("./p").Attributes["style"].Value;
basic.ComicImgUrl = strTemp.Substring(strTemp.IndexOf("(") + 1, strTemp.Length - strTemp.IndexOf("(") - 2);
subNode = temp.SelectSingleNode("./div/h2/a");
basic.ComicName = subNode.Attributes["title"].Value;
basic.ComicHref = hostAttach + subNode.Attributes["href"].Value;
queue.Enqueue(basic);
}
nodeCollect = doc.DocumentNode.SelectNodes("//div[@class='page-pagination pull-right mt20']/ul/li/a");
int index = 0;
foreach (HtmlNode temp in nodeCollect)
{
if (temp.Attributes["class"] != null && temp.Attributes["class"].Value == "active")
{
result.NextPageUrl = hostAttach + nodeCollect[++index].Attributes["href"].Value;
break;
}
index++;
}
result.SearchQueue = queue;
return(result);
}
public override CategoryCollect FindComicByCategory(string cateGoryStr)
{
HtmlDocument doc;
HtmlNode node;
BasicComicInfo basicInfo;
HtmlNodeCollection collect;
CategoryCollect cateCollect;
Queue <BasicComicInfo> comicQueue;
basicInfo = null;
doc = new HtmlDocument();
cateCollect = new CategoryCollect();
comicQueue = new Queue <BasicComicInfo>();
doc.LoadHtml(cateGoryStr);
collect = doc.DocumentNode.SelectNodes("//div[@class='recommendedpic allfloatleft']");
if (collect == null)
{
collect = doc.DocumentNode.SelectNodes("//div[@class='recommendedpicl center']");
}
foreach (HtmlNode temp in collect)
{
basicInfo = new BasicComicInfo();
node = temp.SelectSingleNode("./a");
basicInfo.ComicName = node.Attributes["title"].Value;
basicInfo.ComicHref = node.Attributes["href"].Value;
basicInfo.ComicImgUrl = hostName + temp.SelectSingleNode("./a/img").Attributes["src"].Value;
comicQueue.Enqueue(basicInfo);
}
string href = "";
HtmlNode hrefNode = doc.DocumentNode.SelectSingleNode("//div[@class='gray reminderguild']");
Regex regex = new Regex(@"href=""(?<href>[\w_\.]*)""\s*title=""下一页""");
Regex regexhref = new Regex(@"href=""(?<href>[\w\-\./]*)""\s*target=""_self"">全部");
if (hrefNode != null)
{
href = regexhref.Match(hrefNode.OuterHtml).Groups["href"].Value;
href = href.Substring(0, href.LastIndexOf("/")) + "/";
cateCollect.NextPageUrl = hostName + href + regex.Match(cateGoryStr).Groups["href"].Value;
}
else
{
cateCollect.NextPageUrl = "http://www.dmzx.com/zuixin/";
}
cateCollect.Count = comicQueue.Count;
cateCollect.ComicQueue = comicQueue;
return(cateCollect);
}
public Queue <BasicComicInfo> AnalyseURL(string response, string express)
{
Regex regex = new Regex(express);
BasicComicInfo basic = new BasicComicInfo();
Queue <BasicComicInfo> queue = new Queue <BasicComicInfo>();
MatchCollection match = regex.Matches(response);
foreach (Match i in match)
{
basic = new BasicComicInfo();
basic.ComicImgUrl = i.Groups["url"].Value;
basic.ComicName = i.Groups["data1"].Value + i.Groups["data2"].Value + i.Groups["data3"].Value;
basic.ComicHref = hostName + i.Groups["href"].Value;
queue.Enqueue(basic);
}
return(queue);
}
public override SearchResult GetSearchComic(string response)
{
SearchResult result = new SearchResult();
HtmlDocument doc = new HtmlDocument();
Queue <BasicComicInfo> queue;
queue = new Queue <BasicComicInfo>();
doc.LoadHtml(response);
BasicComicInfo info;
HtmlNodeCollection collect = doc.DocumentNode.SelectNodes("//ul[@class='liemh htmls indliemh']/li");
if (collect == null)
{
return(result);
}
foreach (HtmlNode node in collect)
{
info = new BasicComicInfo();
info.ComicHref = node.SelectSingleNode("./a").Attributes["href"].Value;
info.ComicName = node.SelectSingleNode("./a").Attributes["title"].Value;
info.ComicImgUrl = node.SelectSingleNode("./a/img").Attributes["src"].Value;
queue.Enqueue(info);
}
HtmlNode nodeTemp = doc.DocumentNode.SelectSingleNode("//div[@class='position']");
Regex regex = new Regex(@"(?<data>\d+)");
result.Count = Convert.ToInt32(regex.Match(nodeTemp.InnerText).Groups["data"].Value);
collect = doc.DocumentNode.SelectNodes("//a[@class='next']");
if (collect != null)
{
result.NextPageUrl = hostName + collect[0].Attributes["href"].Value;
}
else
{
result.NextPageUrl = "";
}
result.SearchQueue = queue;
return(result);
}
public override CategoryCollect FindComicByCategory(string response)
{
HtmlDocument doc;
CategoryCollect cateInfo;
Queue <BasicComicInfo> queue;
Dictionary <string, string> pageDict;
doc = new HtmlDocument();
cateInfo = new CategoryCollect();
queue = new Queue <BasicComicInfo>();
doc.LoadHtml(response);
BasicComicInfo basicInfo = null;
HtmlNodeCollection collection = doc.DocumentNode.SelectNodes("//ul[@class='grid-row clearfix']/li | //ul[@class='grid-row clearfix first']/li");
foreach (HtmlNode node in collection)
{
basicInfo = new BasicComicInfo();
basicInfo.ComicName = node.SelectSingleNode("./p/a").InnerText;
basicInfo.ComicHref = node.SelectSingleNode("./p/a").Attributes["href"].Value;
basicInfo.ComicImgUrl = node.SelectSingleNode("./a/img").Attributes["src"].Value;
queue.Enqueue(basicInfo);
}
pageDict = new Dictionary <string, string>();
collection = doc.DocumentNode.SelectNodes("//ul[@class='pagination']/li/a");
foreach (HtmlNode node in collection)
{
if (pageDict.ContainsKey(node.InnerText) == false)
{
pageDict.Add(node.InnerText, hostName + node.Attributes["href"].Value);
}
}
var temp = doc.DocumentNode.SelectSingleNode("//div[@class='head']/span").InnerText;
var currentPage = Convert.ToInt32(temp.Substring(0, temp.IndexOf("/")));
cateInfo.ComicQueue = queue;
cateInfo.Count = queue.Count;
cateInfo.NextPageUrl = pageDict[(currentPage + 1).ToString()];
cateInfo.PagesCollection = pageDict;
return(cateInfo);
}
public override Queue<BasicComicInfo> GetTopComic(string response)//实现热门
{
BasicComicInfo basic = null;
Queue<BasicComicInfo> queue = new Queue<BasicComicInfo>();
HtmlDocument document = new HtmlDocument();
document.LoadHtml(response);
HtmlNode node = document.DocumentNode.SelectSingleNode("//div[@class='cComicHot']");
HtmlNodeCollection collect = node.SelectNodes("./div/li/a");
foreach (var i in collect)
{
basic = new BasicComicInfo();
basic.ComicHref = hostAttach + i.Attributes["href"].Value;
basic.ComicName = i.Attributes["title"].Value;
basic.ComicImgUrl = i.SelectSingleNode("./img").Attributes["src"].Value;
queue.Enqueue(basic);
}
return queue;
}
public override Queue <BasicComicInfo> GetTopComic(string response)//实现热门
{
BasicComicInfo basicComicInfo;
HtmlNode mainNode = GetMainNode(response);
Queue <BasicComicInfo> queue = new Queue <BasicComicInfo>();
HtmlNodeCollection nodes = mainNode.SelectNodes("//div[@class='index-manga-item']");
if (nodes != null)
{
foreach (HtmlNode temp in nodes)
{
basicComicInfo = new BasicComicInfo();
basicComicInfo.ComicHref = host + temp.SelectSingleNode("./a").Attributes["href"].Value;
basicComicInfo.ComicName = temp.SelectSingleNode("./p/a").InnerText;
basicComicInfo.ComicImgUrl = temp.SelectSingleNode("./a/img").Attributes["src"].Value;
queue.Enqueue(basicComicInfo);
}
}
return(queue);
}
public override Queue <BasicComicInfo> GetTopComic(string response)
{
HtmlDocument doc;
Queue <BasicComicInfo> queue;
BasicComicInfo basicInfo;
doc = new HtmlDocument();
queue = new Queue <BasicComicInfo>();
doc.LoadHtml(response);
HtmlNodeCollection collect = doc.DocumentNode.SelectNodes("//a[@class='cover']");
foreach (HtmlNode tempNode in collect)
{
basicInfo = new BasicComicInfo();
basicInfo.ComicHref = tempNode.Attributes["href"].Value;
basicInfo.ComicName = tempNode.Attributes["title"].Value;
basicInfo.ComicImgUrl = tempNode.SelectSingleNode("./img").Attributes["src"].Value;
queue.Enqueue(basicInfo);
}
return(queue);
}
public override Queue <BasicComicInfo> GetTopComic(string response)
{
HtmlNode node;
HtmlDocument doc = new HtmlDocument();
doc.LoadHtml(response);
BasicComicInfo basic = null;
Queue <BasicComicInfo> queue;
queue = new Queue <BasicComicInfo>();
HtmlNodeCollection collect = doc.DocumentNode.SelectNodes("//div[@class='picbox']");
if (collect == null)
{
return(queue);
}
foreach (HtmlNode temp in collect)
{
basic = new BasicComicInfo();
node = temp.SelectSingleNode("./a");
basic.ComicName = node.Attributes["title"].Value;
basic.ComicHref = node.Attributes["href"].Value;
node = node.SelectSingleNode("./img");
if (node.Attributes["data-original"] == null)
{
continue;
}
basic.ComicImgUrl = hostName + node.Attributes["data-original"].Value;
queue.Enqueue(basic);
}
return(queue);
}
public override CategoryCollect FindComicByCategory(string cateGoryStr)
{
CategoryCollect cateCollect = new CategoryCollect();
var dat = AnalyseTool.GetTag(cateGoryStr, @"<div class=""cComicList""", @"<div class=""cComicPageChange2");
Regex regex = new Regex(@"href=['""](?<href>[/\w-]*)['""]\s*class=['""][\w_]*['""]\stitle=['""](?<title>[\w-！!\s，。]*)['""]><img\salt=['""][\w-!,。\s,]*['""]\s*src=['""](?<url>[\w:/.-]*)");
var basicInfo = new BasicComicInfo();
var comicQueue = new Queue <BasicComicInfo>();
foreach (Match i in regex.Matches(dat))
{
basicInfo = new BasicComicInfo();
basicInfo.ComicHref = hostName + i.Groups["href"].Value;
basicInfo.ComicName = i.Groups["title"].Value;
basicInfo.ComicImgUrl = i.Groups["url"].Value;
comicQueue.Enqueue(basicInfo);
}
dat = AnalyseTool.GetTag(cateGoryStr, "<span class='cPageChangeLink'>", "</span>");
regex = new Regex(@"<a\s*href='(?<url>[\w-/]*)'>下一页");
cateCollect.NextPageUrl = hostName + regex.Match(dat).Groups["url"].Value;
cateCollect.ComicQueue = comicQueue;
cateCollect.PagesCollection = new Dictionary <string, string>();
return(cateCollect);
}
public override CategoryCollect FindComicByCategory(string cateGoryStr)
{
HtmlDocument doc;
HtmlNode node;
HtmlNodeCollection nodeCollect;
CategoryCollect collect;
BasicComicInfo basicInfo = null;
Queue <BasicComicInfo> queue;
queue = new Queue <BasicComicInfo>();
collect = new CategoryCollect();
doc = new HtmlDocument();
doc.LoadHtml(cateGoryStr);
nodeCollect = doc.DocumentNode.SelectNodes("//div[@class='nag cf']/div/div/a");
foreach (HtmlNode temp in nodeCollect)
{
node = temp.SelectSingleNode("./span/img");
basicInfo = new BasicComicInfo();
basicInfo.ComicHref = temp.Attributes["href"].Value;
basicInfo.ComicName = temp.Attributes["title"].Value;
basicInfo.ComicImgUrl = node.Attributes["src"].Value;
queue.Enqueue(basicInfo);
}
collect.ComicQueue = queue;
collect.Count = queue.Count;
node = doc.DocumentNode.SelectSingleNode("//a[@class='nextpostslink']");
if (node != null)
{
collect.NextPageUrl = node.Attributes["href"].Value;
}
return(collect);
}
public override CategoryCollect FindComicByCategory(string cateGoryStr)
{
CategoryCollect cateCollect = new CategoryCollect();
Queue <BasicComicInfo> queue = new Queue <BasicComicInfo>();
HtmlNode mainNode = GetMainNode(cateGoryStr);
cateCollect.ComicQueue = queue;
HtmlNode node = mainNode.SelectSingleNode("//ul[@class='list_con_li clearfix']");
if (node == null)
{
return(cateCollect);
}
HtmlNodeCollection collect = node.SelectNodes("./li");
if (collect == null)
{
return(cateCollect);
}
BasicComicInfo comicInfo;
foreach (HtmlNode nodeTemp in collect)
{
comicInfo = new BasicComicInfo();
comicInfo.ComicHref = nodeTemp.SelectSingleNode("./a").Attributes["href"].Value;
comicInfo.ComicName = nodeTemp.SelectSingleNode("./a/img").Attributes["alt"].Value;
comicInfo.ComicImgUrl = nodeTemp.SelectSingleNode("./a/img").Attributes["src"].Value;
queue.Enqueue(comicInfo);
}
int count = 0;
string key = "";
node = mainNode.SelectSingleNode("//span[@class='comi_num']/em");
count = Convert.ToInt32(node.InnerText);
collect = mainNode.SelectNodes("//ul[@class='pagination']/li/a");
cateCollect.PagesCollection = new Dictionary <string, string>();
if (collect != null)
{
foreach (HtmlNode temp in collect)
{
key = temp.InnerText;
if (cateCollect.PagesCollection.ContainsKey(key) == false)
{
cateCollect.PagesCollection.Add(key, hostName + temp.Attributes["href"].Value);
}
}
if (cateCollect.PagesCollection.ContainsKey("下一页"))
{
cateCollect.NextPageUrl = cateCollect.PagesCollection["下一页"];
}
}
return(cateCollect);
}
public override CategoryCollect FindComicByCategory(string cateGoryStr)
{
CategoryCollect collect;
BasicComicInfo basicComicInfo;
collect = new CategoryCollect();
HtmlNode mainNode = GetMainNode(cateGoryStr);
Queue <BasicComicInfo> queue = new Queue <BasicComicInfo>();
HtmlNodeCollection nodes = mainNode.SelectNodes("//div[@class='mh-item']");
if (nodes != null)
{
foreach (HtmlNode temp in nodes)
{
basicComicInfo = new BasicComicInfo();
basicComicInfo.ComicHref = host + temp.SelectSingleNode("./a").Attributes["href"].Value;
basicComicInfo.ComicName = temp.SelectSingleNode("./div/h2/a").InnerText;
basicComicInfo.ComicImgUrl = temp.SelectSingleNode("./a/img").Attributes["src"].Value;
queue.Enqueue(basicComicInfo);
}
}
int curIndex = 0;
int count = 1;
nodes = mainNode.SelectNodes("//div[@class='page-pagination']/ul/li");
collect.PagesCollection = new Dictionary <string, string>();
if (nodes != null)
{
foreach (HtmlNode temp in nodes)//这部分有问题，找不到page-pagination段
{
if (!collect.PagesCollection.ContainsKey(temp.InnerText))
{
HtmlNode node = temp.SelectSingleNode("./a");
if (node.Attributes["class"] != null)
{
curIndex = count;
}
collect.PagesCollection.Add(node.InnerText, host + node.Attributes["href"].Value);
count++;
}
}
}
collect.ComicTotalCount = queue.Count;
collect.ComicQueue = queue;
if (curIndex - 1 > 0 && collect.Count > 0)
{
collect.LastPageUrl = collect.PagesCollection[(curIndex - 1).ToString()];
}
else
{
collect.LastPageUrl = collect.PagesCollection[(curIndex).ToString()];
}
if (curIndex + 1 < collect.PagesCollection.Count && collect.Count > 0)
{
collect.NextPageUrl = collect.PagesCollection[(curIndex + 1).ToString()];
}
else
{
collect.NextPageUrl = collect.PagesCollection[(collect.PagesCollection.Count - 1).ToString()];
}
return(collect);
}
