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 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 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 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 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 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();
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)
{
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);
}
public override CategoryCollect FindComicByCategory(string cateGoryStr)
{
CategoryCollect retCollect = new CategoryCollect();
var mainNode = GetMainNode(cateGoryStr);
if (mainNode == null)
{
return(retCollect);
}
BasicComicInfo info;
Queue <BasicComicInfo> queue = new Queue <BasicComicInfo>();
HtmlNodeCollection collect = mainNode.SelectNodes("//div[@class='cComicList']/li");
foreach (HtmlNode nodeTemp in collect)
{
info = new BasicComicInfo();
info.ComicHref = hostName + nodeTemp.SelectSingleNode("./a").Attributes["href"].Value;
info.ComicName = nodeTemp.SelectSingleNode("./a").Attributes["title"].Value;
info.ComicImgUrl = nodeTemp.SelectSingleNode("./a/img").Attributes["src"].Value;
queue.Enqueue(info);
}
collect = mainNode.SelectNodes("//span[@class='cPageChangeLink']/a");
if (collect != null)
{
string key;
Dictionary <string, string> dict;
dict = new Dictionary <string, string>();
foreach (var i in collect)
{
key = i.InnerText;
if (dict.ContainsKey(key) == false && i.Attributes["href"] != null)
{
dict.Add(key, hostName + i.Attributes["href"].Value);
}
}
if (dict.ContainsKey("上一页"))
{
retCollect.LastPageUrl = dict["上一页"];
}
if (dict.ContainsKey("下一页"))
{
retCollect.NextPageUrl = dict["下一页"];
}
}
HtmlNode node = mainNode.SelectSingleNode("//div[@class='cComicPageChange']");
if (node != null)
{
string temp = node.SelectNodes("./b")[0].InnerText;
retCollect.Count = Convert.ToInt32(temp);
}
retCollect.ComicQueue = queue;
return(retCollect);
}
public override CategoryCollect FindComicByCategory(string cateGoryStr)
{
HtmlDocument doc;
BasicComicInfo comicInfo;
Queue <BasicComicInfo> queue;
doc = new HtmlDocument();
CategoryCollect collect = new CategoryCollect();
queue = new Queue <BasicComicInfo>();
doc.LoadHtml(cateGoryStr);
Dictionary <string, string> dict;
dict = new Dictionary <string, string>();
HtmlNodeCollection nodeCollection = doc.DocumentNode.SelectNodes("//li[@class='list-comic']");
if (nodeCollection != null)
{
foreach (HtmlNode node in nodeCollection)
{
comicInfo = new BasicComicInfo();
comicInfo.ComicHref = node.SelectSingleNode("./a").Attributes["href"].Value;
comicInfo.ComicName = node.SelectSingleNode("./a/mip-img").Attributes["alt"].Value.Replace("'", "");
comicInfo.ComicImgUrl = node.SelectSingleNode("./a/mip-img").Attributes["src"].Value;
queue.Enqueue(comicInfo);
}
}
string key = "";
int current = 0;
nodeCollection = doc.DocumentNode.SelectNodes("//ul[@class='pagination']/li");
if (nodeCollection != null)
{
foreach (HtmlNode node in nodeCollection)
{
if (node.SelectSingleNode("./a") == null)
{
continue;
}
key = node.SelectSingleNode("./a").InnerText;
if (node.Attributes["class"] != null && node.Attributes["class"].Value == "active")
{
current = Convert.ToInt32(key);
}
if (dict.ContainsKey(key) == false)
{
dict.Add(key, node.SelectSingleNode("./a").Attributes["href"].Value);
}
}
}
collect.ComicQueue = queue;
collect.Count = queue.Count;
collect.PagesCollection = dict;
if (dict.ContainsKey((current + 1).ToString()))
{
collect.NextPageUrl = dict[(current + 1).ToString()];
}
if (dict.ContainsKey((current - 1).ToString()))
{
collect.LastPageUrl = dict[(current - 1).ToString()];
}
return(collect);
}
