/// <summary>
/// 解析明细页内容
/// </summary>
/// <param name="documentNode"></param>
/// <returns></returns>
private Hashtable parseDetailPage2(HtmlNode documentNode)
{
List <string> multipage = null;
Hashtable returndata = new Hashtable();
HtmlNode tempNode = null;
string tempString = null;
string tempInnerText = null;
Regex tempReg = null;
Match tempMatch = null;
tempNode = documentNode.SelectSingleNode("//div[@id='content']");
if (tempNode != null)
{
tempString = tempNode.InnerHtml;
tempString = HTMLUtil.RemoveHtmlContent(tempString, "div", "style", "script");
tempString = HTMLUtil.RemoveHtmlTag(tempString, "p", "img", "br");
tempString = tempString.Replace("\r\n", "").Replace("\t", "");
tempString = tempString.Replace("\r\n", "").Replace("\t", "").Replace("手机请访问：:feisuz", "").Replace("feisuz", "")
.Replace("feisuz", "").Replace("作者的话:", "").Replace("新书，求收藏求推荐", "").Replace("本书红薯网首发,请勿转载!", "");
returndata.Add(CollectionFieldName.ExContent, tempString);
}
HtmlNode nextLink = documentNode.SelectNodes("//*[@id='content']/div[@class='text']/a")?.FirstOrDefault(x => x.InnerText == "下一节");
if (nextLink != null)
{
string url = nextLink.GetAttributeValue("href", "");
if (!string.IsNullOrEmpty(url) && url != "#")
{
returndata.Add(CollectionFieldName.NextUrl, url);
}
}
return(returndata);
}
/// <summary>
/// 解析明细页内容
/// </summary>
/// <param name="documentNode"></param>
/// <returns></returns>
private Hashtable parseDetailPage1(HtmlNode documentNode)
{
List <string> multipage = null;
Hashtable returndata = new Hashtable();
HtmlNode tempNode = null;
string tempString = null;
string tempInnerText = null;
Regex tempReg = null;
Match tempMatch = null;
tempNode = documentNode.SelectSingleNode("//div[@id=\"ccontent\"]");
if (tempNode != null)
{
tempString = tempNode.InnerHtml;
tempString = HTMLUtil.RemoveHtmlContent(tempString, "div", "style", "script", "a");
//tempString = HTMLUtil.RemoveHtmlTag(tempString, "p", "img", "br");
tempString = tempString.Replace("\r\n", "")
.Replace("\t", "")
.Replace("領域文學首發地址httP://ｗｗｗ.ｌｉｎｇｙｕ.ｏｒｇ<br><br>", "")
.Replace("領域文學首發地址ｗｗｗ.ｌｉｎｇｙｕ.ｏｒｇ<br><br> <br><br>", "")
.Replace("请记住本书首发域名：http://www.lingyu.org 领域文学手机版阅读网址： m.lingyu.org", "");
string pattern = @"http://www.lingyu.org/\w+/\d+/\d+/\d+.html";
tempString = Regex.Replace(tempString, pattern, "");
returndata.Add(CollectionFieldName.Chap_Content, tempString);
//移除无效字符,用来计算长度
tempInnerText = HTMLUtil.RemoveHtmlTag(tempString)
.Replace(" ", "")
.Replace("領域文學首發地址httP://ｗｗｗ.ｌｉｎｇｙｕ.ｏｒｇ<br><br>", "")
.Replace("領域文學首發地址ｗｗｗ.ｌｉｎｇｙｕ.ｏｒｇ<br><br> <br><br>", "")
.Replace("请记住本书首发域名：http://www.lingyu.org 领域文学手机版阅读网址： m.lingyu.org", "");
if (!string.IsNullOrEmpty(tempInnerText))
{
returndata.Add(CollectionFieldName.Chap_ContentLen, tempInnerText.Length);
string into = "";
if (tempInnerText.Length > 40)
{
into = tempInnerText.Substring(0, 40) + "...";
}
else
{
into = tempInnerText;
}
returndata.Add(CollectionFieldName.Chap_Intro, into);
int price = (tempInnerText.Length / 500) * 3;
if (price > 15)
{
price = 15;
}
returndata.Add(CollectionFieldName.Chap_Pirce, price);
}
returndata.Add(CollectionFieldName.Chap_Status, ChapterStatus.ChapterStatus_OnLine);
returndata.Add(CollectionFieldName.Chap_ChapterType, ChapterType.ChapterType_Free);
tempInnerText = tempNode.InnerText;
}
return(returndata);
}
/// <summary>
/// 解析明细页内容
/// </summary>
/// <param name="documentNode"></param>
/// <returns></returns>
private Hashtable parseDetailPage1(HtmlNode documentNode)
{
List <string> multipage = null;
Hashtable returndata = new Hashtable();
HtmlNode tempNode = null;
string tempString = null;
string tempInnerText = null;
Regex tempReg = null;
Match tempMatch = null;
tempNode = documentNode.SelectSingleNode("//div[@id='content']");
if (tempNode != null)
{
tempString = tempNode.InnerHtml;
tempString = HTMLUtil.RemoveHtmlContent(tempString, "div", "style", "script", "center", "span");
tempString = tempString.Replace("\r\n", "").Replace("\t", "")
.Replace("全本小说网欢迎您！WWW.YZNN.COM T1706231537", "")
.Replace("F606121", "")
.Replace("全本小说网欢迎您！WWW.YZNN.COM", "");
returndata.Add(CollectionFieldName.Chap_Content, tempString);
//移除无效字符,用来计算长度
tempInnerText = HTMLUtil.RemoveHtmlTag(tempString).Replace(" ", "");
if (!string.IsNullOrEmpty(tempInnerText))
{
returndata.Add(CollectionFieldName.Chap_ContentLen, tempInnerText.Length);
string into = "";
if (tempInnerText.Length > 40)
{
into = tempInnerText.Substring(0, 40) + "...";
}
else
{
into = tempInnerText;
}
returndata.Add(CollectionFieldName.Chap_Intro, into);
int price = (tempString.Length / 1000) * 5;
if (price == 0)
{
price = 5;
}
if (price > 15)
{
price = 15;
}
returndata.Add(CollectionFieldName.Chap_Pirce, price);
}
returndata.Add(CollectionFieldName.Chap_Status, ChapterStatus.ChapterStatus_OnLine);
returndata.Add(CollectionFieldName.Chap_ChapterType, ChapterType.ChapterType_Free);
tempInnerText = tempNode.InnerText;
}
else
{
int i = 1;
int j = 1 + 1;
}
return(returndata);
}
/// <summary>
/// 解析明细页内容
/// </summary>
/// <param name="documentNode"></param>
/// <returns></returns>
private Hashtable parseDetailPage1(HtmlNode documentNode)
{
List <string> multipage = null;
Hashtable returndata = new Hashtable();
HtmlNode tempNode = null;
string tempString = null;
string tempInnerText = null;
Regex tempReg = null;
Match tempMatch = null;
tempNode = documentNode.SelectSingleNode("//div[@id='content']");
if (tempNode != null)
{
tempString = tempNode.InnerHtml;
tempString = HTMLUtil.RemoveHtmlContent(tempString, "div", "style", "script");
tempString = HTMLUtil.RemoveHtmlTag(tempString, "p", "img", "br");
tempString = tempString.Replace("\r\n", "").Replace("\t", "");
returndata.Add(CollectionFieldName.Chap_Content, tempString);
tempInnerText = HTMLUtil.RemoveHtmlTag(tempString).Replace(" ", "");
if (!string.IsNullOrEmpty(tempInnerText))
{
returndata.Add(CollectionFieldName.Chap_ContentLen, tempInnerText.Length);
string into = "";
if (tempInnerText.Length > 40)
{
into = tempInnerText.Substring(0, 40) + "...";
}
else
{
into = tempInnerText;
}
returndata.Add(CollectionFieldName.Chap_Intro, into);
int price = (tempString.Length / 1000) * 5;
if (price == 0)
{
price = 5;
}
if (price > 15)
{
price = 15;
}
returndata.Add(CollectionFieldName.Chap_Pirce, price);
}
returndata.Add(CollectionFieldName.Chap_Status, ChapterStatus.ChapterStatus_OnLine);
returndata.Add(CollectionFieldName.Chap_ChapterType, ChapterType.ChapterType_Free);
tempInnerText = tempNode.InnerText;
}
HtmlNode nextLink = documentNode.SelectNodes("//*[@id='content']/div[@class='text']/a")?.FirstOrDefault(x => x.InnerText == "下一节");
if (nextLink != null)
{
string url = nextLink.GetAttributeValue("href", "");
if (!string.IsNullOrEmpty(url) && url != "#")
{
returndata.Add(CollectionFieldName.NextUrl, url);
}
}
return(returndata);
}
private void dealHtmlstring(ref string Htmlstring)
{
HtmlDocument document = new HtmlDocument();
document.LoadHtml(Htmlstring);
HtmlNode htmlNode = document.DocumentNode;
//清洗多余标签
htmlNode.InnerHtml = HTMLUtil.RemoveHtmlTag(htmlNode.InnerHtml, "p", "vedio", "img", "br");
}
public string DeepClear(string htmlString = "")
{
if (!string.IsNullOrEmpty(htmlString))
{
htmlString = HTMLUtil.RemoveHtmlTag(htmlString, "p", "img", "br");
htmlString = HTMLUtil.ClearImgTag(htmlString);
Regex contentRegex = new Regex(@"(style="".*?"")");
htmlString = contentRegex.Replace(htmlString, "");
}
return(htmlString);
}
/// <summary>
/// 解析明细页内容
/// </summary>
/// <param name="documentNode"></param>
/// <returns></returns>
private Hashtable parseDetailPage1(HtmlNode documentNode)
{
List <string> multipage = null;
Hashtable returndata = new Hashtable();
HtmlNode tempNode = null;
string tempString = null;
string tempInnerText = null;
Regex tempReg = null;
Match tempMatch = null;
tempNode = documentNode.SelectSingleNode("//div[@class=\"panel-body content-body content-ext\"]");
if (tempNode != null)
{
tempString = tempNode.InnerHtml;
tempString = HTMLUtil.RemoveHtmlContent(tempString, "div", "style", "script");
//tempString = HTMLUtil.RemoveHtmlTag(tempString, "p", "img", "br");
tempString = tempString.Replace("\r\n", "").Replace("\t", "").Replace("手机请访问：:feisuz", "")
.Replace("feisuz", "").Replace("作者的话:", "").Replace("新书，求收藏求推荐", "").Replace("本书红薯网首发,请勿转载!", "");
returndata.Add(CollectionFieldName.Chap_Content, tempString);
//移除无效字符,用来计算长度
tempInnerText = HTMLUtil.RemoveHtmlTag(tempString).Replace(" ", "").Replace("feisuz", "")
.Replace("作者的话:", "").Replace("新书，求收藏求推荐", "").Replace("本书红薯网首发,请勿转载!", "");
if (!string.IsNullOrEmpty(tempInnerText))
{
returndata.Add(CollectionFieldName.Chap_ContentLen, tempInnerText.Length);
string into = "";
if (tempInnerText.Length > 40)
{
into = tempInnerText.Substring(0, 40) + "...";
}
else
{
into = tempInnerText;
}
returndata.Add(CollectionFieldName.Chap_Intro, into);
int price = (tempString.Length / 1000) * 5;
if (price == 0)
{
price = 5;
}
if (price > 15)
{
price = 15;
}
returndata.Add(CollectionFieldName.Chap_Pirce, price);
}
returndata.Add(CollectionFieldName.Chap_Status, ChapterStatus.ChapterStatus_OnLine);
returndata.Add(CollectionFieldName.Chap_ChapterType, ChapterType.ChapterType_Free);
tempInnerText = tempNode.InnerText;
}
return(returndata);
}
/// <summary>
/// 解析明细页内容
/// </summary>
/// <param name="documentNode"></param>
/// <returns></returns>
private Hashtable parseDetailPage1(HtmlNode documentNode)
{
List <string> multipage = null;
Hashtable returndata = new Hashtable();
HtmlNode tempNode = null;
string tempString = null;
string tempInnerText = null;
Regex tempReg = null;
Match tempMatch = null;
tempNode = documentNode.SelectSingleNode("//div[@class='readout']/div[@class='shuneirong']");
if (tempNode != null)
{
tempString = tempNode.InnerHtml;
tempString = HTMLUtil.RemoveHtmlContent(tempString, "div", "style", "script", "center", "span");
tempString = tempString.Replace("\r\n", "").Replace("\t", "")
.Replace("免费小说", "")
.Replace("biquge5200.com", "")
.Replace("biquge5200", "")
.Replace("笔趣阁", "")
.Replace("http://", "")
.Replace("本书红薯网首发,请勿转载!", "");
returndata.Add(CollectionFieldName.Chap_Content, tempString);
//移除无效字符,用来计算长度
tempInnerText = HTMLUtil.RemoveHtmlTag(tempString).Replace(" ", "");
if (!string.IsNullOrEmpty(tempInnerText))
{
returndata.Add(CollectionFieldName.Chap_ContentLen, tempInnerText.Length);
string into = "";
if (tempInnerText.Length > 150)
{
into = tempInnerText.Substring(0, 150) + "...";
}
else
{
into = tempInnerText;
}
returndata.Add(CollectionFieldName.Chap_Intro, into);
}
returndata.Add(CollectionFieldName.Chap_Status, ChapterStatus.ChapterStatus_OnLine);
returndata.Add(CollectionFieldName.Chap_ChapterType, ChapterType.ChapterType_Free);
tempInnerText = tempNode.InnerText;
}
else
{
int i = 1;
int j = 1 + 1;
}
return(returndata);
}
/// <summary>
/// 图片相对路径改为全路径
/// </summary>
/// <param name="documentNode"></param>
/// <param name="InternalRealUrl"></param>
protected static void ReplaceIncorrectImageSrc(HtmlNode documentNode, string InternalRealUrl)
{
HtmlNodeCollection imgNode = documentNode.SelectNodes("//img");
if (imgNode == null)
{
return;
}
foreach (var item in imgNode)
{
var url = item.GetAttributeValue("src", "");
var realUrl = HTMLUtil.GetFullURL(InternalRealUrl, url);
item.SetAttributeValue("src", realUrl);
//documentNode.InnerHtml=documentNode.InnerHtml.Replace(url, realUrl);
}
}
/// <summary>
/// 章节目录列表数据
/// </summary>
/// <param name="hashtable"></param>
private void parseListPage(Hashtable hashtable)
{
List <Hashtable> detaiList = hashtable.ContainsKey(CollectionFieldName.Items) ? (List <Hashtable>)hashtable[CollectionFieldName.Items] : null;
List <string> nextPages = hashtable.ContainsKey(CollectionFieldName.Pages) ? (List <string>)hashtable[CollectionFieldName.Pages] : null;
List <string> multiPages = hashtable.ContainsKey(CollectionFieldName.MultiPages) ? (List <string>)hashtable[CollectionFieldName.MultiPages] : null;
Hashtable htKeys = new Hashtable(); //判断是否重复
//detaiList = null;
if (detaiList != null)
{
foreach (Hashtable cm in detaiList)
{
//continue;
string url = (string)cm[CollectionFieldName.Url];
if (!HTMLUtil.IsCorrect(url))
{
continue;
}
url = GetFullURL(url);
cm[CollectionFieldName.Url] = url;
wxchapter rm = new wxchapter();
fillWxChapterModel(rm, cm, _CollectionModel.CollectionId);
//防止出现重复章节一直循环
if (htKeys.ContainsKey(rm.Id))
{
continue;
}
htKeys.Add(rm.Id, rm.Id);
//章节数据保存
this._CollectionModel.chapterList.Add(rm);
}
}
this.currentUrl_ChapterList = null;
if (nextPages != null)
{
foreach (string url in nextPages)
{
this.currentUrl_ChapterList = GetFullURL(url);
}
}
}
/// <summary>
/// 解析开始页
/// </summary>
/// <param name="documentNode"></param>
/// <returns></returns>
private Hashtable parseStartupPage(HtmlNode documentNode)
{
Hashtable ht = new Hashtable();
Regex tempReg = null;
Match tempMatch = null;
HtmlNode linkNodes = documentNode.SelectSingleNode("//meta[@property='og:title']");
if (linkNodes != null)
{
var title = linkNodes.GetAttributeValue("content", "");
ht.Add(CollectionFieldName.Novel_Name, title);
}
linkNodes = documentNode.SelectSingleNode("//div[@class='pic text-center']/img");
if (linkNodes != null)
{
var imgUrl = linkNodes?.GetAttributeValue("src", "");
imgUrl = HTMLUtil.GetFullURL(InternalRealUrl, imgUrl);
ht.Add(CollectionFieldName.Novel_CoverImgs, imgUrl);
}
linkNodes = documentNode.SelectSingleNode("//meta[@property='og:novel:category']");
if (linkNodes != null)
{
var tag = linkNodes?.GetAttributeValue("content", "");
ht.Add(CollectionFieldName.Novel_Tag, tag);
}
var url = InternalRealUrl;
ht.Add(CollectionFieldName.Url, url);
tempReg = new Regex(@"/(\d+).html");
tempMatch = tempReg.Match(InternalRealUrl);
if (tempMatch.Success)
{
ht.Add(CollectionFieldName.Novel_UniqueFlag, tempReg.Replace(tempMatch.Value, "$1"));
}
Hashtable returndata = new Hashtable();
if (ht != null)
{
returndata.Add(CollectionFieldName.BookInfo, ht);
}
return(returndata);
}
/// <summary>
/// 修改占位图片路径
/// </summary>
/// <param name="documentNode"></param>
/// <param name="InternalRealUrl"></param>
protected static void ReplacePlaceholderImageSrc(HtmlNode documentNode, string InternalRealUrl, string PlaceholderAttribute)
{
HtmlNodeCollection imgNode = documentNode.SelectNodes("//img");
if (imgNode == null)
{
return;
}
foreach (var item in imgNode)
{
var url = item.GetAttributeValue(PlaceholderAttribute, "");
if (!string.IsNullOrEmpty(url))
{
var realUrl = HTMLUtil.GetFullURL(InternalRealUrl, url);
item.SetAttributeValue("src", realUrl);
item.Attributes.Remove(PlaceholderAttribute);
}
}
}
/// <summary>
/// 解析明细页内容
/// </summary>
/// <param name="documentNode"></param>
/// <returns></returns>
private Hashtable parseDetailPage2(HtmlNode documentNode)
{
Hashtable returndata = new Hashtable();
HtmlNode tempNode = null;
string tempString = null;
string tempInnerText = null;
Regex tempReg = null;
Match tempMatch = null;
tempNode = documentNode.SelectSingleNode("//div[@class='content']");
if (tempNode != null)
{
tempString = tempNode.InnerHtml;
tempString = HTMLUtil.RemoveHtmlTag(tempString, "p", "img", "br");
tempString = HTMLUtil.RemoveHtmlContent(tempString, "style", "script");
returndata.Add(CollectionFieldName.Chap_Content, tempString);
tempInnerText = tempNode.InnerText;
if (!string.IsNullOrEmpty(tempInnerText))
{
int price = (tempString.Length / 1000) * 5;
if (price == 0)
{
price = 5;
}
if (price > 15)
{
price = 15;
}
returndata.Add(CollectionFieldName.Chap_ContentLen, tempString.Length);
returndata.Add(CollectionFieldName.Chap_Pirce, price);
}
returndata.Add(CollectionFieldName.Chap_Status, ChapterStatus.ChapterStatus_OnLine);
returndata.Add(CollectionFieldName.Chap_ChapterType, ChapterType.ChapterType_Pay);
}
return(returndata);
}
/// <summary>
/// 解析明细页内容
/// </summary>
/// <param name="documentNode"></param>
/// <returns></returns>
private Hashtable parseDetailPage1(HtmlNode documentNode)
{
Hashtable returndata = new Hashtable();
HtmlNode tempNode = null;
string tempString = null;
string tempInnerText = null;
Regex tempReg = null;
Match tempMatch = null;
tempNode = documentNode.SelectSingleNode("//div[@class='cDetail']");
if (tempNode != null)
{
tempString = tempNode.InnerHtml;
tempString = HTMLUtil.RemoveHtmlTag(tempString, "p", "img", "br");
tempString = HTMLUtil.RemoveHtmlContent(tempString, "style", "script");
returndata.Add(CollectionFieldName.Chap_Content, tempString);
tempInnerText = tempNode.InnerText;
if (!string.IsNullOrEmpty(tempInnerText))
{
returndata.Add(CollectionFieldName.Chap_ContentLen, tempInnerText.Length);
string into = "";
if (tempInnerText.Length > 40)
{
into = tempInnerText.Substring(0, 40) + "...";
}
else
{
into = tempInnerText;
}
returndata.Add(CollectionFieldName.Chap_Intro, into);
}
returndata.Add(CollectionFieldName.Chap_Status, ChapterStatus.ChapterStatus_OnLine);
returndata.Add(CollectionFieldName.Chap_ChapterType, ChapterType.ChapterType_Free);
}
return(returndata);
}
/// <summary>
/// 解析明细页内容
/// </summary>
/// <param name="documentNode"></param>
/// <returns></returns>
private Hashtable parseDetailPage1(HtmlNode documentNode)
{
List <string> multipage = null;
Hashtable returndata = new Hashtable();
HtmlNode tempNode = null;
string tempString = null;
string tempInnerText = null;
Regex tempReg = null;
Match tempMatch = null;
tempNode = documentNode.SelectSingleNode("//div[@class='articleCon']");
if (tempNode != null)
{
tempString = tempNode.InnerHtml;
tempString = HTMLUtil.RemoveHtmlContent(tempString, "div", "style", "script", "dt", "a");
tempString = tempString.ToLower();
//tempString = HTMLUtil.RemoveHtmlTag(tempString, "p", "img", "br");
tempString = tempString.Replace("\r\n", "").Replace("\t", "")
.Replace("本站访问地址http://www.ziyouge.com 任意搜索引擎内输入:紫幽阁 即可访问!", "")
.Replace("http://www.ziyouge.com", "")
.Replace("紫幽阁", "")
.Replace("wanben.me", "")
.Replace("ziyouge.com", "")
.Replace("ziyouge", "")
.Replace("http://", "")
.Replace("http", "")
.Replace("紫Ｙou阁 ＷwＷ.ZiyouＧＥ.com", "")
.Replace("WWw.ZiyoUgE.com", "")
.Replace("品书网", "")
.Replace("www.vodtw.com", "")
.Replace("本书来自", "")
.Replace("/html/book/19/19092/", "")
;
//正则替换域名
string pattern = @"(?=.{3,255}$)[a-zA-Z0-9][-a-zA-Z0-9]{0,62}(\.[a-zA-Z0-9][-a-zA-Z0-9]{0,62})+";
tempString = Regex.Replace(tempString, pattern, "");
returndata.Add(CollectionFieldName.Chap_Content, tempString);
//移除无效字符,用来计算长度
tempInnerText = HTMLUtil.RemoveHtmlTag(tempString).Replace(" ", "").Replace("feisuz", "")
.Replace("作者的话:", "").Replace("新书，求收藏求推荐", "").Replace("本书红薯网首发,请勿转载!", "");
if (!string.IsNullOrEmpty(tempInnerText))
{
returndata.Add(CollectionFieldName.Chap_ContentLen, tempInnerText.Length);
string into = "";
if (tempInnerText.Length > 40)
{
into = tempInnerText.Substring(0, 40) + "...";
}
else
{
into = tempInnerText;
}
returndata.Add(CollectionFieldName.Chap_Intro, into);
int price = (tempString.Length / 1000) * 5;
if (price == 0)
{
price = 5;
}
if (price > 15)
{
price = 15;
}
returndata.Add(CollectionFieldName.Chap_Pirce, price);
}
returndata.Add(CollectionFieldName.Chap_Status, ChapterStatus.ChapterStatus_OnLine);
returndata.Add(CollectionFieldName.Chap_ChapterType, ChapterType.ChapterType_Free);
tempInnerText = tempNode.InnerText;
}
return(returndata);
}
/// <summary>
/// 解析开始页
/// </summary>
/// <param name="documentNode"></param>
/// <returns></returns>
private Hashtable parseStartupPage(HtmlNode documentNode)
{
Hashtable ht = new Hashtable();
Regex tempReg = null;
Match tempMatch = null;
HtmlNode linkNodes = documentNode.SelectSingleNode("//span[@class='book_name']");
if (linkNodes != null)
{
var title = linkNodes.InnerText;
ht.Add(CollectionFieldName.Novel_Name, title);
}
linkNodes = documentNode.SelectSingleNode("//div[@class='books_bar clear']");
if (linkNodes != null)
{
var imgUrl = linkNodes.SelectSingleNode("div[@class='lr_list']/img")?.GetAttributeValue("src", "");
ht.Add(CollectionFieldName.Novel_CoverImgs, imgUrl);
var tag = linkNodes.SelectSingleNode("//ul[@class='book_list']/li[4]")?.InnerText;
ht.Add(CollectionFieldName.Novel_Tag, tag.Replace("类别：", ""));
var statusName = linkNodes.SelectSingleNode("//ul[@class='book_list']/li[3]")?.InnerText;
if (!string.IsNullOrEmpty(statusName) && statusName.Contains("完结"))
{
ht.Add(CollectionFieldName.Novel_Status, BookStatus.BookStatus_Finish);
}
else
{
ht.Add(CollectionFieldName.Novel_Status, BookStatus.BookStatus_Update);
}
var ContentLenStr = linkNodes.SelectSingleNode("//ul[@class='book_list']/li[2]")?.InnerText;
int ContentLen = 0;
if (!string.IsNullOrEmpty(ContentLenStr))
{
tempReg = new Regex(@"(\d+.\d+)|(\d+)");
tempMatch = tempReg.Match(ContentLenStr);
if (tempMatch.Success)
{
if (ContentLenStr.Contains("万"))
{
ContentLen = (int)(Convert.ToDouble(tempMatch.Value) * 10000);
}
else if (ContentLenStr.Contains("千"))
{
ContentLen = (int)(Convert.ToDouble(tempMatch.Value) * 1000);
}
else
{
ContentLen = Convert.ToInt32(tempMatch.Value);
}
}
ht.Add(CollectionFieldName.Novel_ContentLen, ContentLen);
}
}
linkNodes = documentNode.SelectSingleNode("//a[@class='more_link']");
if (linkNodes != null)
{
var url = linkNodes.GetAttributeValue("href", "");
url = HTMLUtil.GetFullURL(InternalRealUrl, url);
ht.Add(CollectionFieldName.Url, url);
}
linkNodes = documentNode.SelectSingleNode("//div[@id='divDescription']");
if (linkNodes != null)
{
var intr = linkNodes.InnerHtml;
ht.Add(CollectionFieldName.Novel_Intr, intr);
}
tempReg = new Regex(@"/book/(\d+).html");
tempMatch = tempReg.Match(InternalRealUrl);
if (tempMatch.Success)
{
ht.Add(CollectionFieldName.Novel_UniqueFlag, tempReg.Replace(tempMatch.Value, "$1"));
}
Hashtable returndata = new Hashtable();
if (ht != null)
{
returndata.Add(CollectionFieldName.BookInfo, ht);
}
return(returndata);
}
/// <summary>
/// 解析明细页内容
/// </summary>
/// <param name="documentNode"></param>
/// <returns></returns>
private Hashtable parseDetailPage1(HtmlNode documentNode)
{
List <string> multipage = null;
Hashtable returndata = new Hashtable();
HtmlNode tempNode = null;
string tempString = null;
string tempInnerText = null;
Regex tempReg = null;
Match tempMatch = null;
tempNode = documentNode.SelectSingleNode("//div[@id=\"content\"]");
if (tempNode != null)
{
tempString = tempNode.InnerHtml;
tempString = HTMLUtil.RemoveHtmlContent(tempString, "div", "style", "script", "a");
//tempString = HTMLUtil.RemoveHtmlTag(tempString, "p", "img", "br");
tempString = tempString.Replace("\r\n", "")
.Replace("\t", "")
.Replace("手机请访问：:feisuz", "")
.Replace("feisuz", "")
.Replace("作者的话:", "")
.Replace("新书，求收藏求推荐", "")
.Replace("本书红薯网首发,请勿转载!", "")
.Replace("老铁!还在找\"美艳冥妻\"免费小说?", "")
.Replace(" (www.yikanxiaoshuo.com = ", "").Trim().TrimEnd(')')
.Replace("<br> <br> 百度直接搜索: \"易看小说\" 看免费小说,没毛病!<br>", "")
.Replace("老铁!还在找\"绝望游戏\"免费小说?", "")
.Replace("百度直接搜索: \"易看小说\" 看免费小说,没毛病!", "")
.Replace("\"易看小说\"", "")
.Replace("易看小说", "")
.Replace("免费小说", "")
.Replace("(更快免费阅读加微信：jxxs9966)", "")
.Replace("jxxs9966", "")
;
returndata.Add(CollectionFieldName.Chap_Content, tempString);
//移除无效字符,用来计算长度
tempInnerText = HTMLUtil.RemoveHtmlTag(tempString).Replace(" ", "");
if (!string.IsNullOrEmpty(tempInnerText))
{
returndata.Add(CollectionFieldName.Chap_ContentLen, tempInnerText.Length);
string into = "";
if (tempInnerText.Length > 40)
{
into = tempInnerText.Substring(0, 40) + "...";
}
else
{
into = tempInnerText;
}
returndata.Add(CollectionFieldName.Chap_Intro, into);
int price = (tempString.Length / 1000) * 5;
if (price == 0)
{
price = 5;
}
if (price > 15)
{
price = 15;
}
returndata.Add(CollectionFieldName.Chap_Pirce, price);
}
returndata.Add(CollectionFieldName.Chap_Status, ChapterStatus.ChapterStatus_OnLine);
returndata.Add(CollectionFieldName.Chap_ChapterType, ChapterType.ChapterType_Free);
tempInnerText = tempNode.InnerText;
}
return(returndata);
}
/// <summary>
/// 解析明细页内容
/// </summary>
/// <param name="documentNode"></param>
/// <returns></returns>
private Hashtable parseDetailPage1(HtmlNode documentNode)
{
List <string> multipage = null;
Hashtable returndata = new Hashtable();
HtmlNode tempNode = null;
string tempString = null;
string tempInnerText = null;
Regex tempReg = null;
Match tempMatch = null;
tempNode = documentNode.SelectSingleNode("//div[@id='booktext']");
if (tempNode != null)
{
tempString = tempNode.InnerHtml;
tempString = HTMLUtil.RemoveHtmlContent(tempString, "div", "style", "script", "dt", "a");
tempString = tempString.ToLower();
//tempString = HTMLUtil.RemoveHtmlTag(tempString, "p", "img", "br");
tempString = tempString.Replace("\r\n", "").Replace("\t", "");
tempString = tempString.Replace("【快速查找本站请百度搜索: 书包520】", "")
.Replace("【本站域名更改为“ www.shubao520.net ” ,或者在百度搜索: 书包520】", "");
tempString = tempString.Replace("【本站域名更改为“www.shubao520.net”,或者在百度搜索:书包520】", "")
.Replace("【快速查找本站请百度搜索:书包520】", "")
.Replace("书包520", "")
.Replace("www.shubao520.net", "")
.Replace("百度", "")
.Replace("搜索", "")
.Replace("域名", "");
//正则替换域名
string pattern = @"(?=.{3,255}$)[a-zA-Z0-9][-a-zA-Z0-9]{0,62}(\.[a-zA-Z0-9][-a-zA-Z0-9]{0,62})+";
tempString = Regex.Replace(tempString, pattern, "");
string pattern1 = @"<.+>";
tempString = Regex.Replace(tempString, pattern1, "");
returndata.Add(CollectionFieldName.Chap_Content, tempString);
//移除无效字符,用来计算长度
tempInnerText = HTMLUtil.RemoveHtmlTag(tempString).Replace(" ", "").Replace("feisuz", "")
.Replace("作者的话:", "").Replace("新书，求收藏求推荐", "").Replace("本书红薯网首发,请勿转载!", "");
if (!string.IsNullOrEmpty(tempInnerText))
{
returndata.Add(CollectionFieldName.Chap_ContentLen, tempInnerText.Length);
string into = "";
if (tempInnerText.Length > 40)
{
into = tempInnerText.Substring(0, 40) + "...";
}
else
{
into = tempInnerText;
}
returndata.Add(CollectionFieldName.Chap_Intro, into);
int price = (tempInnerText.Length / 1000) * 5;
if (price == 0)
{
price = 5;
}
if (price > 15)
{
price = 15;
}
returndata.Add(CollectionFieldName.Chap_Pirce, price);
}
returndata.Add(CollectionFieldName.Chap_Status, ChapterStatus.ChapterStatus_OnLine);
returndata.Add(CollectionFieldName.Chap_ChapterType, ChapterType.ChapterType_Free);
tempInnerText = tempNode.InnerText;
}
return(returndata);
}
/// <summary>
/// Search on Allmusic for the requested string
/// </summary>
/// <param name="searchBy"></param>
/// <param name="searchStr"></param>
/// <returns></returns>
public bool FindInfo(SearchBy searchBy, string searchStr)
{
_searchby = searchBy;
HTMLUtil util = new HTMLUtil();
string strPostData = "";
if (SearchBy.Albums == searchBy)
{
strPostData = string.Format(ALBUMSEARCH, HttpUtility.UrlEncode(searchStr));
}
else
{
searchStr = SwitchArtist(searchStr);
strPostData = string.Format(ARTISTSEARCH, HttpUtility.UrlEncode(searchStr));
}
string strHTML = PostHTTP(MAINURL + URLPROGRAM, strPostData);
if (strHTML.Length == 0)
{
return(false);
}
_htmlCode = strHTML; // save the html content...
Regex multiples = new Regex(
@"\sSearch\sResults\sfor:",
RegexOptions.IgnoreCase
| RegexOptions.Multiline
| RegexOptions.IgnorePatternWhitespace
| RegexOptions.Compiled
);
if (multiples.IsMatch(strHTML))
{
string pattern = "";
if (searchBy.ToString().Equals("Artists"))
{
pattern = @"<tr.*?>\s*?.*?<td\s*?class=""relevance\stext-center"">\s*?.*\s*?.*</td>" +
@"\s*?.*<td.*\s*?.*</td>\s*?.*<td>.*<a.*href=""(?<code>.*?)"">(?<name>.*)</a>.*</td>" +
@"\s*?.*<td>(?<detail>.*)</td>\s*?.*<td>(?<detail2>.*)</td>";
}
else if (searchBy.ToString().Equals("Albums"))
{
pattern = @"<tr.*?>\s*?.*?<td\s*?class=""relevance\stext-center"">\s*?.*\s*?.*</td>" +
@"\s*?.*<td.*\s*?.*</td>\s*?.*<td>.*<a.*href=""(?<code>.*?)"">(?<name>.*)</a>.*</td>" +
@"\s*?.*<td>(?<detail>.*)</td>\s*?.*<td>.*</td>\s*?.*<td>(?<detail2>.*)</td>";
}
Match m;
Regex itemsFoundFromSite = new Regex(
pattern,
RegexOptions.IgnoreCase
| RegexOptions.Multiline
| RegexOptions.IgnorePatternWhitespace
| RegexOptions.Compiled
);
for (m = itemsFoundFromSite.Match(strHTML); m.Success; m = m.NextMatch())
{
string code = m.Groups["code"].ToString();
string name = m.Groups["name"].ToString();
string detail = m.Groups["detail"].ToString();
string detail2 = m.Groups["detail2"].ToString();
util.RemoveTags(ref name);
util.ConvertHTMLToAnsi(name, out name);
util.RemoveTags(ref detail);
util.ConvertHTMLToAnsi(detail, out detail);
util.RemoveTags(ref detail2);
util.ConvertHTMLToAnsi(detail2, out detail2);
if (SearchBy.Artists == searchBy)
{
detail += " - " + detail2;
if (detail.Length > 0)
{
_codes.Add(code);
_values.Add(name + " - " + detail);
}
else
{
_codes.Add(code);
_values.Add(name);
}
}
else
{
MusicAlbumInfo albumInfo = new MusicAlbumInfo();
albumInfo.AlbumURL = code;
albumInfo.Artist = detail;
albumInfo.Title = name;
albumInfo.DateOfRelease = detail2;
_albumList.Add(albumInfo);
}
}
_multiple = true;
}
else // found the right one
{
}
return(true);
}
/// <summary>
/// Quitar los saltos de linea y poner el TAG html para el salto y limpiar un texto y suprimir los tags html por su equivalente en ascii
/// </summary>
/// <param name="texto">Texto HTML</param>
/// <returns></returns>
public static string sanitize(string texto)
{
return(HTMLUtil.sanitize(texto));
}
/// <summary>
/// 解析开始页
/// </summary>
/// <param name="documentNode"></param>
/// <returns></returns>
private Hashtable parseStartupPage(HtmlNode documentNode)
{
Hashtable ht = new Hashtable();
Regex tempReg = null;
Match tempMatch = null;
HtmlNode linkNodes = documentNode.SelectSingleNode("//meta[@property='og:title']");
if (linkNodes != null)
{
var title = linkNodes.GetAttributeValue("content", "");
ht.Add(CollectionFieldName.Novel_Name, title);
}
linkNodes = documentNode.SelectSingleNode("//div[@class='pic text-center']/img");
if (linkNodes != null)
{
var imgUrl = linkNodes?.GetAttributeValue("src", "");
imgUrl = HTMLUtil.GetFullURL(InternalRealUrl, imgUrl);
ht.Add(CollectionFieldName.Novel_CoverImgs, imgUrl);
}
linkNodes = documentNode.SelectSingleNode("//meta[@property='og:novel:category']");
if (linkNodes != null)
{
var tag = linkNodes?.GetAttributeValue("content", "");
ht.Add(CollectionFieldName.Novel_Tag, tag);
}
//linkNodes = documentNode.SelectSingleNode("//meta[@property='og:novel:category']");
//if (linkNodes != null)
//{
// var statusName = linkNodes?.GetAttributeValue("content","");
// if (!string.IsNullOrEmpty(statusName) && statusName.Contains("完结"))
// ht.Add(CollectionFieldName.Novel_Status, BookStatus.BookStatus_Finish);
// else
// ht.Add(CollectionFieldName.Novel_Status, BookStatus.BookStatus_Update);
//}
//linkNodes = documentNode.SelectSingleNode("//meta[@property='og:novel:category']");
//if (linkNodes != null)
//{
// var ContentLenStr = linkNodes.SelectSingleNode("div[@class='fn-clear']/ul/li[4]")?.InnerText;
// int ContentLen = 0;
// if (!string.IsNullOrEmpty(ContentLenStr))
// {
// tempReg = new Regex(@"(\d+.\d+)|(\d+)");
// tempMatch = tempReg.Match(ContentLenStr);
// if (tempMatch.Success)
// {
// if (ContentLenStr.Contains("万"))
// ContentLen = (int)(Convert.ToDouble(tempMatch.Value) * 10000);
// if (ContentLenStr.Contains("千"))
// ContentLen = (int)(Convert.ToDouble(tempMatch.Value) * 1000);
// }
// ht.Add(CollectionFieldName.Novel_ContentLen, ContentLen);
// }
//}
//linkNodes = documentNode.SelectSingleNode("//div[@class='panel']/a[@class='btn block white']");
//if (linkNodes != null)
//{
// var url = linkNodes.GetAttributeValue("href", "");
// ht.Add(CollectionFieldName.Url, url);
//}
var url = InternalRealUrl;
ht.Add(CollectionFieldName.Url, url);
//linkNodes = documentNode.SelectSingleNode("//div[@class='book_intro']/p[@id='summary']");
//if (linkNodes != null)
//{
// var intr = linkNodes.InnerHtml;
// ht.Add(CollectionFieldName.Novel_Intr, intr);
//}
tempReg = new Regex(@"/(\d+).html");
tempMatch = tempReg.Match(InternalRealUrl);
if (tempMatch.Success)
{
ht.Add(CollectionFieldName.Novel_UniqueFlag, tempReg.Replace(tempMatch.Value, "$1"));
}
Hashtable returndata = new Hashtable();
if (ht != null)
{
returndata.Add(CollectionFieldName.BookInfo, ht);
}
return(returndata);
}
/// <summary>
/// 获取完整url地址
/// </summary>
/// <param name="relativeURL"></param>
/// <returns></returns>
protected string GetFullURL(string relativeURL)
{
return(HTMLUtil.GetFullURL(baseUrl, relativeURL));
}
/// <summary>
/// Parse the Detail Page returned from the Allmusic Scraper
/// </summary>
/// <param name="strHTML"></param>
/// <returns></returns>
public bool Parse(string strHTML)
{
HTMLUtil util = new HTMLUtil();
int begIndex = 0;
int endIndex = 0;
string strHTMLLow = strHTML.ToLower();
// Get the Artist Name
string pattern = @"<h1.*class=""title"">(.*)</h1>";
if (!FindPattern(pattern, strHTML))
{
return(false);
}
_strArtistName = _match.Groups[1].Value;
// Born
pattern = @"<h3>.*Born.*</h3>\s*?<p>(.*)</p>";
if (FindPattern(pattern, strHTML))
{
string strValue = _match.Groups[1].Value;
util.RemoveTags(ref strValue);
util.ConvertHTMLToAnsi(strValue, out _strBorn);
_strBorn = _strBorn.Trim();
}
// Years Active
pattern = @"(<span.*?class=""active"">(.*?)</span>)";
if (FindPattern(pattern, strHTML))
{
while (_match.Success)
{
_strYearsActive += string.Format("{0}s, ", _match.Groups[2].Value);
_match = _match.NextMatch();
}
_strYearsActive = _strYearsActive.Trim(new[] { ' ', ',' });
}
// Genre
pattern = @"<div.*?id=""genre-style"">\s*?.*?\s*?<h3>.*?Genres.*?</h3>\s*?.*?(<p>(.*?)</p>)";
if (FindPattern(pattern, strHTML))
{
string data = "";
while (_match.Success)
{
data += string.Format("{0}, ", _match.Groups[2].Value);
_match = _match.NextMatch();
}
util.RemoveTags(ref data);
util.ConvertHTMLToAnsi(data, out _strGenres);
_strGenres = _strGenres.Trim(new[] { ' ', ',' });
}
// Style
begIndex = strHTMLLow.IndexOf("<h3>styles</h3>");
endIndex = strHTMLLow.IndexOf("<!--end genre/styles-->", begIndex + 2);
if (begIndex != -1 && endIndex != -1)
{
string contentInfo = strHTML.Substring(begIndex, endIndex - begIndex);
pattern = @"(<li>(.*?)</li>)";
if (FindPattern(pattern, contentInfo))
{
string data = "";
while (_match.Success)
{
data += string.Format("{0}, ", _match.Groups[2].Value);
_match = _match.NextMatch();
}
util.RemoveTags(ref data);
util.ConvertHTMLToAnsi(data, out _strStyles);
_strStyles = _strStyles.Trim(new[] { ' ', ',' });
}
}
// Mood
begIndex = strHTMLLow.IndexOf("<h3>moods</h3>");
endIndex = strHTMLLow.IndexOf("</div>", begIndex + 2);
if (begIndex != -1 && endIndex != -1)
{
string contentInfo = strHTML.Substring(begIndex, endIndex - begIndex);
pattern = @"(<li>(.*?)</li>)";
if (FindPattern(pattern, contentInfo))
{
string data = "";
while (_match.Success)
{
data += string.Format("{0}, ", _match.Groups[2].Value);
_match = _match.NextMatch();
}
util.RemoveTags(ref data);
util.ConvertHTMLToAnsi(data, out _strTones);
_strTones = _strTones.Trim(new[] { ' ', ',' });
}
}
// Instruments
begIndex = strHTMLLow.IndexOf("<h3>instruments</h3>");
endIndex = strHTMLLow.IndexOf("</div>", begIndex + 2);
if (begIndex != -1 && endIndex != -1)
{
string contentInfo = strHTML.Substring(begIndex, endIndex - begIndex);
if (FindPattern(pattern, contentInfo))
{
string data = "";
while (_match.Success)
{
data += string.Format("{0}, ", _match.Groups[2].Value);
_match = _match.NextMatch();
}
util.RemoveTags(ref data);
util.ConvertHTMLToAnsi(data, out _strInstruments);
_strInstruments = _strInstruments.Trim(new[] { ' ', ',' });
}
}
// picture URL
pattern = @"<div.*?class=""image"">\s*?.*<img.*id=""artist_image"".*?src=\""(.*?)\""";
if (FindPattern(pattern, strHTML))
{
_strArtistPictureURL = _match.Groups[1].Value;
}
// parse AMG BIOGRAPHY
pattern = @"<td.*?class=""tab_off""><a.*?href=""(.*?)"">.*?Biography.*?</a>";
if (FindPattern(pattern, strHTML))
{
try
{
string contentinfo = AllmusicSiteScraper.GetHTTP(_match.Groups[1].Value);
begIndex = contentinfo.IndexOf("<!--Begin Biography -->");
endIndex = contentinfo.IndexOf("</div>", begIndex + 2);
if (begIndex != -1 && endIndex != -1)
{
pattern = @"<p.*?class=""text"">(.*?)</p>";
if (FindPattern(pattern, contentinfo))
{
string data = _match.Groups[1].Value;
util.RemoveTags(ref data);
util.ConvertHTMLToAnsi(data, out data);
_strAMGBiography = data.Trim();
}
}
}
catch (Exception) {}
}
string compilationPage = "";
string singlesPage = "";
string dvdPage = "";
string miscPage = "";
// discography (albums)
pattern = @"<td.*class=""tab_off""><a.*?href=""(.*?)"">.*Discography.*</a>";
if (FindPattern(pattern, strHTML))
{
// Get Link to other sub pages
compilationPage = _match.Groups[1].Value + "/compilations";
singlesPage = _match.Groups[1].Value + "/singles-eps";
dvdPage = _match.Groups[1].Value + "/dvds-videos";
miscPage = _match.Groups[1].Value + "/other";
try
{
string contentinfo = AllmusicSiteScraper.GetHTTP(_match.Groups[1].Value);
pattern = @"sorted.*? cell"">(?<year>.*?)</td>\s*?.*?</td>\s*.*?<a.*?"">(?<album>.*?)" +
@"</a>.*?</td>\s*.*?</td>\s*.*?"">(?<label>.*?)</td>";
if (FindPattern(pattern, contentinfo))
{
while (_match.Success)
{
string year = _match.Groups["year"].Value;
string albumTitle = _match.Groups["album"].Value;
string label = _match.Groups["label"].Value;
util.RemoveTags(ref year);
util.ConvertHTMLToAnsi(year, out year);
util.RemoveTags(ref albumTitle);
util.ConvertHTMLToAnsi(albumTitle, out albumTitle);
util.RemoveTags(ref label);
util.ConvertHTMLToAnsi(label, out label);
try
{
string[] dAlbumInfo = { year.Trim(), albumTitle.Trim(), label.Trim() };
_discographyAlbum.Add(dAlbumInfo);
}
catch {}
_match = _match.NextMatch();
}
}
}
catch (Exception) {}
}
// Compilations
if (compilationPage != "")
{
try
{
string contentinfo = AllmusicSiteScraper.GetHTTP(compilationPage);
pattern = @"sorted.*? cell"">(?<year>.*?)</td>\s*?.*?</td>\s*.*?<a.*?"">(?<album>.*?)" +
@"</a>.*?</td>\s*.*?</td>\s*.*?"">(?<label>.*?)</td>";
if (FindPattern(pattern, contentinfo))
{
while (_match.Success)
{
string year = _match.Groups["year"].Value;
string albumTitle = _match.Groups["album"].Value;
string label = _match.Groups["label"].Value;
util.RemoveTags(ref year);
util.ConvertHTMLToAnsi(year, out year);
util.RemoveTags(ref albumTitle);
util.ConvertHTMLToAnsi(albumTitle, out albumTitle);
util.RemoveTags(ref label);
util.ConvertHTMLToAnsi(label, out label);
try
{
string[] dAlbumInfo = { year.Trim(), albumTitle.Trim(), label.Trim() };
_discographyCompilations.Add(dAlbumInfo);
}
catch {}
_match = _match.NextMatch();
}
}
}
catch (Exception) {}
}
// Singles
if (singlesPage != "")
{
try
{
string contentinfo = AllmusicSiteScraper.GetHTTP(singlesPage);
pattern = @"sorted.*? cell"">(?<year>.*?)</td>\s*?.*?</td>\s*.*?<a.*?"">(?<album>.*?)" +
@"</a>.*?</td>\s*.*?</td>\s*.*?"">(?<label>.*?)</td>";
if (FindPattern(pattern, contentinfo))
{
while (_match.Success)
{
string year = _match.Groups["year"].Value;
string albumTitle = _match.Groups["album"].Value;
string label = _match.Groups["label"].Value;
util.RemoveTags(ref year);
util.ConvertHTMLToAnsi(year, out year);
util.RemoveTags(ref albumTitle);
util.ConvertHTMLToAnsi(albumTitle, out albumTitle);
util.RemoveTags(ref label);
util.ConvertHTMLToAnsi(label, out label);
try
{
string[] dAlbumInfo = { year.Trim(), albumTitle.Trim(), label.Trim() };
_discographySingles.Add(dAlbumInfo);
}
catch {}
_match = _match.NextMatch();
}
}
}
catch (Exception) {}
}
// DVD Videos
if (dvdPage != "")
{
try
{
string contentinfo = AllmusicSiteScraper.GetHTTP(dvdPage);
pattern = @"sorted.*? cell"">(?<year>.*?)</td>\s*?.*?</td>\s*.*?<a.*?"">(?<album>.*?)" +
@"</a>.*?</td>\s*.*?</td>\s*.*?"">(?<label>.*?)</td>";
if (FindPattern(pattern, contentinfo))
{
while (_match.Success)
{
string year = _match.Groups["year"].Value;
string albumTitle = _match.Groups["album"].Value;
string label = _match.Groups["label"].Value;
util.RemoveTags(ref year);
util.ConvertHTMLToAnsi(year, out year);
util.RemoveTags(ref albumTitle);
util.ConvertHTMLToAnsi(albumTitle, out albumTitle);
util.RemoveTags(ref label);
util.ConvertHTMLToAnsi(label, out label);
try
{
string[] dAlbumInfo = { year.Trim(), albumTitle.Trim(), label.Trim() };
_discographyMisc.Add(dAlbumInfo);
}
catch {}
_match = _match.NextMatch();
}
}
}
catch (Exception) {}
}
// Other
if (miscPage != "")
{
try
{
string contentinfo = AllmusicSiteScraper.GetHTTP(miscPage);
pattern = @"sorted.*? cell"">(?<year>.*?)</td>\s*?.*?</td>\s*.*?<a.*?"">(?<album>.*?)" +
@"</a>.*?</td>\s*.*?</td>\s*.*?"">(?<label>.*?)</td>";
if (FindPattern(pattern, contentinfo))
{
while (_match.Success)
{
string year = _match.Groups["year"].Value;
string albumTitle = _match.Groups["album"].Value;
string label = _match.Groups["label"].Value;
util.RemoveTags(ref year);
util.ConvertHTMLToAnsi(year, out year);
util.RemoveTags(ref albumTitle);
util.ConvertHTMLToAnsi(albumTitle, out albumTitle);
util.RemoveTags(ref label);
util.ConvertHTMLToAnsi(label, out label);
try
{
string[] dAlbumInfo = { year.Trim(), albumTitle.Trim(), label.Trim() };
_discographyMisc.Add(dAlbumInfo);
}
catch {}
_match = _match.NextMatch();
}
}
}
catch (Exception) {}
}
_bLoaded = true;
return(_bLoaded);
}
public bool FindAlbuminfo(string strAlbum, string artistName, int releaseYear)
{
_albumList.Clear();
// strAlbum="1999";//escapolygy";
// make request
// type is
// http://www.allmusic.com/cg/amg.dll?P=amg&SQL=escapolygy&OPT1=2
HTMLUtil util = new HTMLUtil();
string postData = String.Format("P=amg&SQL={0}&OPT1=2", HttpUtility.UrlEncode(strAlbum));
string html = PostHTTP("http://www.allmusic.com/cg/amg.dll", postData);
if (html.Length == 0)
{
return(false);
}
// check if this is an album
MusicAlbumInfo newAlbum = new MusicAlbumInfo();
newAlbum.AlbumURL = "http://www.allmusic.com/cg/amg.dll?" + postData;
if (newAlbum.Parse(html))
{
_albumList.Add(newAlbum);
return(true);
}
string htmlLow = html;
htmlLow = htmlLow.ToLower();
int startOfTable = htmlLow.IndexOf("id=\"expansiontable1\"");
if (startOfTable < 0)
{
return(false);
}
startOfTable = htmlLow.LastIndexOf("<table", startOfTable);
if (startOfTable < 0)
{
return(false);
}
HTMLTable table = new HTMLTable();
string strTable = html.Substring(startOfTable);
table.Parse(strTable);
for (int i = 1; i < table.Rows; ++i)
{
HTMLTable.HTMLRow row = table.GetRow(i);
string albumName = "";
string albumUrl = "";
string nameOfAlbum = "";
string nameOfArtist = "";
for (int iCol = 0; iCol < row.Columns; ++iCol)
{
string column = row.GetColumValue(iCol);
if (iCol == 1 && (column.Length != 0))
{
albumName = "(" + column + ")";
}
if (iCol == 2)
{
nameOfArtist = column;
util.RemoveTags(ref nameOfArtist);
if (!column.Equals(" "))
{
albumName = String.Format("- {0} {1}", nameOfArtist, albumName);
}
}
if (iCol == 4)
{
string tempAlbum = column;
util.RemoveTags(ref tempAlbum);
albumName = String.Format("{0} {1}", tempAlbum, albumName);
nameOfAlbum = tempAlbum;
}
if (iCol == 4 && column.IndexOf("<a href=\"") >= 0)
{
int pos1 = column.IndexOf("<a href=\"");
pos1 += +"<a href=\"".Length;
int iPos2 = column.IndexOf("\">", pos1);
if (iPos2 >= 0)
{
if (nameOfAlbum.Length == 0)
{
nameOfAlbum = albumName;
}
// full album url:
// http://www.allmusic.com/cg/amg.dll?p=amg&token=&sql=10:66jieal64xs7
string url = column.Substring(pos1, iPos2 - pos1);
string albumNameStripped;
albumUrl = String.Format("http://www.allmusic.com{0}", url);
MusicAlbumInfo newAlbumInfo = new MusicAlbumInfo();
util.ConvertHTMLToAnsi(albumName, out albumNameStripped);
newAlbumInfo.Title2 = albumNameStripped;
newAlbumInfo.AlbumURL = util.ConvertHTMLToAnsi(albumUrl);
newAlbumInfo.Artist = util.ConvertHTMLToAnsi(nameOfArtist);
newAlbumInfo.Title = util.ConvertHTMLToAnsi(nameOfAlbum);
_albumList.Add(newAlbumInfo);
}
}
}
}
// now sort
_albumList.Sort(new AlbumSort(strAlbum, artistName, releaseYear));
return(true);
}
public bool Parse(string html)
{
_songs.Clear();
HTMLUtil util = new HTMLUtil();
string strHtmlLow = html.ToLower();
int begIndex = 0;
int endIndex = 0;
// Extract Cover URL
string pattern = @"<!--Begin.*?Album.*?Photo-->\s*?.*?<img.*?src=\""(.*?)\""";
if (FindPattern(pattern, html))
{
_strImageURL = _match.Groups[1].Value;
}
// Extract Review
pattern = @"<td.*?class=""tab_off""><a.*?href=""(.*?)"">.*?Review.*?</a>";
if (FindPattern(pattern, html))
{
try
{
string contentinfo = AllmusicSiteScraper.GetHTTP(_match.Groups[1].Value);
pattern = @"<p.*?class=""author"">.*\s*?.*?<p.*?class=""text"">(.*?)</p>";
if (FindPattern(pattern, contentinfo))
{
string data = _match.Groups[1].Value;
util.RemoveTags(ref data);
util.ConvertHTMLToAnsi(data, out data);
_strReview = data.Trim();
}
}
catch (Exception) {}
}
// Extract Artist
pattern = @"<h3.*?artist</h3>\s*?.*?<a.*"">(.*)</a>";
if (FindPattern(pattern, html))
{
_artist = _match.Groups[1].Value;
util.RemoveTags(ref _artist);
}
// Extract Album
pattern = @"<h3.*?album</h3>\s*?.*?<p>(.*)</P>";
if (FindPattern(pattern, html))
{
_strTitle = _match.Groups[1].Value;
util.RemoveTags(ref _strTitle);
}
// Extract Rating
pattern = @"<h3.*?rating</h3>\s*?.*?src=""(.*?)""";
if (FindPattern(pattern, html))
{
string strRating = _match.Groups[1].Value;
util.RemoveTags(ref strRating);
strRating = strRating.Substring(26, 1);
try
{
_iRating = Int32.Parse(strRating);
}
catch (Exception) {}
}
// Release Date
pattern = @"<h3.*?release.*?date</h3>\s*?.*?<p>(.*)</P>";
if (FindPattern(pattern, html))
{
_strDateOfRelease = _match.Groups[1].Value;
util.RemoveTags(ref _strDateOfRelease);
// extract the year out of something like "1998 (release)" or "12 feb 2003"
int nPos = _strDateOfRelease.IndexOf("19");
if (nPos > -1)
{
if ((int)_strDateOfRelease.Length >= nPos + 3 && Char.IsDigit(_strDateOfRelease[nPos + 2]) &&
Char.IsDigit(_strDateOfRelease[nPos + 3]))
{
string strYear = _strDateOfRelease.Substring(nPos, 4);
_strDateOfRelease = strYear;
}
else
{
nPos = _strDateOfRelease.IndexOf("19", nPos + 2);
if (nPos > -1)
{
if ((int)_strDateOfRelease.Length >= nPos + 3 && Char.IsDigit(_strDateOfRelease[nPos + 2]) &&
Char.IsDigit(_strDateOfRelease[nPos + 3]))
{
string strYear = _strDateOfRelease.Substring(nPos, 4);
_strDateOfRelease = strYear;
}
}
}
}
nPos = _strDateOfRelease.IndexOf("20");
if (nPos > -1)
{
if ((int)_strDateOfRelease.Length > nPos + 3 && Char.IsDigit(_strDateOfRelease[nPos + 2]) &&
Char.IsDigit(_strDateOfRelease[nPos + 3]))
{
string strYear = _strDateOfRelease.Substring(nPos, 4);
_strDateOfRelease = strYear;
}
else
{
nPos = _strDateOfRelease.IndexOf("20", nPos + 1);
if (nPos > -1)
{
if ((int)_strDateOfRelease.Length > nPos + 3 && Char.IsDigit(_strDateOfRelease[nPos + 2]) &&
Char.IsDigit(_strDateOfRelease[nPos + 3]))
{
string strYear = _strDateOfRelease.Substring(nPos, 4);
_strDateOfRelease = strYear;
}
}
}
}
}
// Extract Genre
begIndex = strHtmlLow.IndexOf("<h3>genre</h3>");
endIndex = strHtmlLow.IndexOf("</div>", begIndex + 2);
if (begIndex != -1 && endIndex != -1)
{
string contentInfo = html.Substring(begIndex, endIndex - begIndex);
pattern = @"(<li>(.*?)</li>)";
if (FindPattern(pattern, contentInfo))
{
string data = "";
while (_match.Success)
{
data += string.Format("{0}, ", _match.Groups[2].Value);
_match = _match.NextMatch();
}
util.RemoveTags(ref data);
util.ConvertHTMLToAnsi(data, out _strGenre);
_strGenre = _strGenre.Trim(new[] { ' ', ',' });
}
}
// Extract Styles
begIndex = strHtmlLow.IndexOf("<h3>style</h3>");
endIndex = strHtmlLow.IndexOf("</div>", begIndex + 2);
if (begIndex != -1 && endIndex != -1)
{
string contentInfo = html.Substring(begIndex, endIndex - begIndex);
pattern = @"(<li>(.*?)</li>)";
if (FindPattern(pattern, contentInfo))
{
string data = "";
while (_match.Success)
{
data += string.Format("{0}, ", _match.Groups[2].Value);
_match = _match.NextMatch();
}
util.RemoveTags(ref data);
util.ConvertHTMLToAnsi(data, out _strStyles);
_strStyles = _strStyles.Trim(new[] { ' ', ',' });
}
}
// Extract Moods
begIndex = strHtmlLow.IndexOf("<h3>moods</h3>");
endIndex = strHtmlLow.IndexOf("</div>", begIndex + 2);
if (begIndex != -1 && endIndex != -1)
{
string contentInfo = html.Substring(begIndex, endIndex - begIndex);
pattern = @"(<li>(.*?)</li>)";
if (FindPattern(pattern, contentInfo))
{
string data = "";
while (_match.Success)
{
data += string.Format("{0}, ", _match.Groups[2].Value);
_match = _match.NextMatch();
}
util.RemoveTags(ref data);
util.ConvertHTMLToAnsi(data, out _strTones);
_strTones = _strTones.Trim(new[] { ' ', ',' });
}
}
// Extract Songs
begIndex = strHtmlLow.IndexOf("<!-- tracks table -->");
endIndex = strHtmlLow.IndexOf("<!-- end tracks table -->", begIndex + 2);
if (begIndex != -1 && endIndex != -1)
{
string contentInfo = html.Substring(begIndex, endIndex - begIndex);
pattern = @"<tr.*class=""visible"".*?\s*?<td.*</td>\s*?.*<td.*</td>\s*?.*<td.*?>(?<track>.*)</td>" +
@"\s*?.*<td.*</td>\s*?.*<td.*?>(?<title>.*)</td>\s*?.*?<td.*?>\s*?.*</td>\s*?.*?<td.*?>(?<duration>.*)</td>";
if (FindPattern(pattern, contentInfo))
{
while (_match.Success)
{
// Tracknumber
int iTrack = 0;
try
{
iTrack = Int32.Parse(_match.Groups["track"].Value);
}
catch (Exception) {}
// Song Title
string strTitle = _match.Groups["title"].Value;
util.RemoveTags(ref strTitle);
util.ConvertHTMLToAnsi(strTitle, out strTitle);
// Duration
int iDuration = 0;
string strDuration = _match.Groups["duration"].Value;
int iPos = strDuration.IndexOf(":");
if (iPos >= 0)
{
string strMin, strSec;
strMin = strDuration.Substring(0, iPos);
iPos++;
strSec = strDuration.Substring(iPos);
int iMin = 0, iSec = 0;
try
{
iMin = Int32.Parse(strMin);
iSec = Int32.Parse(strSec);
}
catch (Exception) {}
iDuration = iMin * 60 + iSec;
}
// Create new song object
MusicSong newSong = new MusicSong();
newSong.Track = iTrack;
newSong.SongName = strTitle;
newSong.Duration = iDuration;
_songs.Add(newSong);
_match = _match.NextMatch();
}
}
}
// Set to "Not available" if no value from web
if (_artist.Length == 0)
{
_artist = GUILocalizeStrings.Get(416);
}
if (_strDateOfRelease.Length == 0)
{
_strDateOfRelease = GUILocalizeStrings.Get(416);
}
if (_strGenre.Length == 0)
{
_strGenre = GUILocalizeStrings.Get(416);
}
if (_strTones.Length == 0)
{
_strTones = GUILocalizeStrings.Get(416);
}
if (_strStyles.Length == 0)
{
_strStyles = GUILocalizeStrings.Get(416);
}
if (_strTitle.Length == 0)
{
_strTitle = GUILocalizeStrings.Get(416);
}
if (_strTitle2.Length == 0)
{
_strTitle2 = _strTitle;
}
Loaded = true;
return(true);
}
// Filmograpy and bio
public bool GetActorDetails(IMDBUrl url, out IMDBActor actor)
{
actor = new IMDBActor();
string[] vdbParserStr = VdbParserStringActorDetails();
if (vdbParserStr == null || vdbParserStr.Length != 46)
{
return(false);
}
try
{
string absoluteUri;
string strBody = GetPage(url.URL, "utf-8", out absoluteUri);
if (strBody == null)
{
return(false);
}
if (strBody.Length == 0)
{
return(false);
}
#region Actor imdb id
// IMDBActorID
try
{
int pos = url.URL.LastIndexOf("nm");
string id = url.URL.Substring(pos, 9).Replace("/", string.Empty);
actor.IMDBActorID = id;
}
catch (Exception) { }
#endregion
HTMLParser parser = new HTMLParser(strBody);
string strThumb = string.Empty;
string value = string.Empty;
string value2 = string.Empty;
#region Actor name
// Actor name
if ((parser.skipToEndOf(vdbParserStr[0])) && // <title>
(parser.extractTo(vdbParserStr[1], ref value))) // - IMDb</title>
{
value = new HTMLUtil().ConvertHTMLToAnsi(value);
value = Util.Utils.RemoveParenthesis(value).Trim();
actor.Name = HttpUtility.HtmlDecode(value.Trim());
}
if (actor.Name == string.Empty)
{
actor.Name = url.Title;
}
#endregion
// Photo
string parserTxt = parser.Content;
string photoBlock = string.Empty;
#region Actor photo
if (parser.skipToStartOf(vdbParserStr[2]) && // <td id="img_primary"
(parser.extractTo(vdbParserStr[3], ref photoBlock))) // </td>
{
parser.Content = photoBlock;
if ((parser.skipToEndOf(vdbParserStr[4])) && // <img src="
(parser.extractTo(vdbParserStr[5], ref strThumb))) // "
{
actor.ThumbnailUrl = strThumb;
}
parser.Content = parserTxt;
}
#endregion
#region Actor birth date
// Birth date
if ((parser.skipToEndOf(vdbParserStr[6])) && // >Born:</h4>
(parser.skipToEndOf(vdbParserStr[7])) && // birth_monthday=
(parser.skipToEndOf(vdbParserStr[8])) && // >
(parser.extractTo(vdbParserStr[9], ref value)) && // <
(parser.skipToEndOf(vdbParserStr[10])) && // year=
(parser.extractTo(vdbParserStr[11], ref value2))) // "
{
actor.DateOfBirth = value + " " + value2;
}
#endregion
#region Actor death date
// Death date
if ((parser.skipToEndOf(vdbParserStr[12])) && // >Died:</h4>
(parser.skipToEndOf(vdbParserStr[13])) && // death_monthday="
(parser.skipToEndOf(vdbParserStr[14])) && // >
(parser.extractTo(vdbParserStr[15], ref value)) && // <
(parser.skipToEndOf(vdbParserStr[16])) && // death_date="
(parser.extractTo(vdbParserStr[17], ref value2))) // "
{
actor.DateOfDeath = value + " " + value2;
}
#endregion
parser.resetPosition();
#region Actor birth place
// Birth place
if ((parser.skipToEndOf(vdbParserStr[18])) && // birth_place=
(parser.skipToEndOf(vdbParserStr[19])) && // >
(parser.extractTo(vdbParserStr[20], ref value))) // <
{
actor.PlaceOfBirth = HttpUtility.HtmlDecode(value);
}
#endregion
#region Actor death place
// Death place
if ((parser.skipToEndOf(vdbParserStr[21])) && // death_place=
(parser.skipToEndOf(vdbParserStr[22])) && // >
(parser.extractTo(vdbParserStr[23], ref value))) // <
{
actor.PlaceOfDeath = HttpUtility.HtmlDecode(value);
}
#endregion
//Mini Biography
parser.resetPosition();
#region Actor biography
if ((parser.skipToEndOf(vdbParserStr[24])) && // <td id="overview-top">
(parser.skipToEndOf(vdbParserStr[25])) && // <p>
(parser.extractTo(vdbParserStr[26], ref value))) // See full bio</a>
{
value = new HTMLUtil().ConvertHTMLToAnsi(value);
actor.MiniBiography = Util.Utils.stripHTMLtags(value);
actor.MiniBiography = actor.MiniBiography.Replace(vdbParserStr[45], string.Empty).Trim(); // See full bio »
actor.MiniBiography = HttpUtility.HtmlDecode(actor.MiniBiography); // Remove HTML entities like ½
if (actor.MiniBiography != string.Empty)
{
// get complete biography
string bioURL = absoluteUri;
if (!bioURL.EndsWith(vdbParserStr[27])) // /
{
bioURL += vdbParserStr[28]; // /bio
}
else
{
bioURL += vdbParserStr[29]; // bio
}
string strBioBody = GetPage(bioURL, "utf-8", out absoluteUri);
if (!string.IsNullOrEmpty(strBioBody))
{
HTMLParser parser1 = new HTMLParser(strBioBody);
if (parser1.skipToEndOf(vdbParserStr[30]) && // <h5>Mini Biography</h5>
parser1.skipToEndOf(vdbParserStr[31]) && // <div class="wikipedia_bio">
parser1.extractTo(vdbParserStr[32], ref value)) // </div>
{
value = new HTMLUtil().ConvertHTMLToAnsi(value);
value = Regex.Replace(value, @"</h5>\s<h5>", "\n\r");
value = Regex.Replace(value, @"<h5>", "\n\r\n\r");
value = Regex.Replace(value, @"</h5>", ":\n\r");
actor.Biography = Util.Utils.stripHTMLtags(value).Trim();
actor.Biography = HttpUtility.HtmlDecode(actor.Biography);
}
else
{
parser1.resetPosition();
if (parser1.skipToEndOf(vdbParserStr[33]) && // <h5>Mini Biography</h5>
parser1.extractTo(vdbParserStr[34], ref value)) // </p>
{
value = new HTMLUtil().ConvertHTMLToAnsi(value);
actor.Biography = Util.Utils.stripHTMLtags(value).Trim();
actor.Biography = HttpUtility.HtmlDecode(actor.Biography);
}
}
}
}
}
#endregion
// Person is movie director or an actor/actress
bool isActorPass = false;
bool isDirectorPass = false;
bool isWriterPass = false;
parser.resetPosition();
HTMLParser dirParser = new HTMLParser(); // HTML body for Director
HTMLParser wriParser = new HTMLParser(); // HTML body for Writers
#region Check person role in movie (actor, director or writer)
if ((parser.skipToEndOf(vdbParserStr[35])) && // name="Director">Director</a>
(parser.skipToEndOf(vdbParserStr[36]))) // </div>
{
isDirectorPass = true;
dirParser.Content = parser.Content;
}
parser.resetPosition();
if ((parser.skipToEndOf(vdbParserStr[37])) && // name="Writer">Writer</a>
(parser.skipToEndOf(vdbParserStr[38]))) // </div>
{
isWriterPass = true;
wriParser.Content = parser.Content;
}
parser.resetPosition();
if (parser.skipToEndOf(vdbParserStr[39]) || // name="Actress">Actress</a>
parser.skipToEndOf(vdbParserStr[40])) // name="Actor">Actor</a>
{
isActorPass = true;
}
#endregion
#region Get movies for every role
// Get filmography Actor
if (isActorPass)
{
GetActorMovies(actor, parser, false, false);
}
// Get filmography for writers
if (isWriterPass)
{
parser = wriParser;
parser.resetPosition();
if ((parser.skipToEndOf(vdbParserStr[41])) && // name="Writer">Writer</a>
(parser.skipToEndOf(vdbParserStr[42]))) // </div>
{
GetActorMovies(actor, parser, false, true);
}
}
// Get filmography Director
if (isDirectorPass)
{
parser = dirParser;
parser.resetPosition();
if (parser.skipToEndOf(vdbParserStr[43]) && // name="Director">Director</a>
parser.skipToEndOf(vdbParserStr[44])) // </div>
{
GetActorMovies(actor, parser, true, false);
}
}
#endregion
// Add filmography
if (actor.Count > 0)
{
actor.SortActorMoviesByYear();
}
return(true);
}
catch (Exception ex)
{
Log.Error("IMDB.GetActorDetails({0} exception:{1} {2} {3}", url.URL, ex.Message, ex.Source, ex.StackTrace);
}
return(false);
}
/// <summary>
/// 解析明细页内容
/// </summary>
/// <param name="documentNode"></param>
/// <returns></returns>
private Hashtable parseDetailPage1(HtmlNode documentNode)
{
List <string> multipage = null;
Hashtable returndata = new Hashtable();
HtmlNode tempNode = null;
string tempString = null;
string tempInnerText = null;
Regex tempReg = null;
Match tempMatch = null;
tempNode = documentNode.SelectSingleNode("//div[@id='content']");
if (tempNode != null)
{
tempString = tempNode.InnerHtml;
tempString = HTMLUtil.RemoveHtmlContent(tempString, "div", "style", "script", "dt", "a");
tempString = tempString.ToLower();
//tempString = HTMLUtil.RemoveHtmlTag(tempString, "p", "img", "br");
tempString = tempString.Replace("\r\n", "").Replace("\t", "")
.Replace("本站访问地址http://www.ziyouge.com 任意搜索引擎内输入:紫幽阁 即可访问!", "")
.Replace("http://www.ziyouge.com", "")
.Replace("紫幽阁", "")
.Replace("wanben.me", "")
.Replace("ziyouge.com", "")
.Replace("ziyouge", "")
.Replace("http://", "")
.Replace("http", "")
.Replace("紫Ｙou阁 ＷwＷ.ZiyouＧＥ.com", "")
.Replace("WWw.ZiyoUgE.com", "")
.Replace("品书网", "")
.Replace("www.vodtw.com", "")
.Replace("本书来自", "")
.Replace("/html/book/19/19092/", "")
.Replace("大家想继续看我的书，可以加我微信gdy3208新书出了，我会第一时间发动态通知大家！", "")
.Replace("本站重要通知:请使用本站的免费小说app,无广告、破防盗版、更新快,会员同步书架,请关注微信公众号 appxsyd (按住三秒复制) 下载免费阅读器!!", "")
.Replace("本站重要通知: 请使用本站的免费小说app,无广告、破防盗版、更新快,会员同步书架,请关注微信公众号 gegegengxin (按住三秒复制)下载免费阅读器!!", "")
.Replace("本站重要通知:", "")
.Replace("请使用本站的免费小说", "")
.Replace("app", "")
.Replace("无广告、破防盗版、更新快,会员同步书架", "")
.Replace("请关注微信公众号", "")
.Replace("appxsyd", "")
.Replace("gegegengxin", "")
.Replace("(按住三秒复制)", "")
.Replace("(按住三秒复制)", "")
.Replace("下载免费阅读器", "")
;
//正则替换域名
string pattern = @"(?=.{3,255}$)[a-zA-Z0-9][-a-zA-Z0-9]{0,62}(\.[a-zA-Z0-9][-a-zA-Z0-9]{0,62})+";
tempString = Regex.Replace(tempString, pattern, "");
string pattern1 = @"<.+>";
tempString = Regex.Replace(tempString, pattern1, "");
returndata.Add(CollectionFieldName.Chap_Content, tempString);
//移除无效字符,用来计算长度
tempInnerText = HTMLUtil.RemoveHtmlTag(tempString).Replace(" ", "").Replace("feisuz", "")
.Replace("作者的话:", "").Replace("新书，求收藏求推荐", "").Replace("本书红薯网首发,请勿转载!", "");
if (!string.IsNullOrEmpty(tempInnerText))
{
returndata.Add(CollectionFieldName.Chap_ContentLen, tempInnerText.Length);
string into = "";
if (tempInnerText.Length > 40)
{
into = tempInnerText.Substring(0, 40) + "...";
}
else
{
into = tempInnerText;
}
returndata.Add(CollectionFieldName.Chap_Intro, into);
int price = (tempString.Length / 1000) * 5;
if (price == 0)
{
price = 5;
}
if (price > 15)
{
price = 15;
}
returndata.Add(CollectionFieldName.Chap_Pirce, price);
}
returndata.Add(CollectionFieldName.Chap_Status, ChapterStatus.ChapterStatus_OnLine);
returndata.Add(CollectionFieldName.Chap_ChapterType, ChapterType.ChapterType_Free);
tempInnerText = tempNode.InnerText;
}
return(returndata);
}
/// <summary>
/// 解析明细页内容
/// </summary>
/// <param name="documentNode"></param>
/// <returns></returns>
private Hashtable parseDetailPage1(HtmlNode documentNode)
{
List <string> multipage = null;
Hashtable returndata = new Hashtable();
HtmlNode tempNode = null;
string tempString = null;
string tempInnerText = null;
Regex tempReg = null;
Match tempMatch = null;
tempNode = documentNode.SelectSingleNode("//div[@class='messagecontent']");
if (tempNode != null)
{
tempString = tempNode.InnerHtml;
tempString = HTMLUtil.RemoveHtmlContent(tempString, "div", "style", "script");
tempString = tempString.Replace("\r\n", "").Replace("\t", "");
//正则替换
string pattern = @"www\.[a-zA-Z0-9]+\.(?:com|cn|net|org)/(\w+|/)+\.html";
tempString = Regex.Replace(tempString, pattern, "");
string pattern1 = @"www\.[a-zA-Z0-9]+\.(?:com|cn|net|org)/(\w+|/)+";
tempString = Regex.Replace(tempString, pattern1, "");
string pattern2 = @"www\.[a-zA-Z0-9]+\.(?:com|cn|net|org)/?";
tempString = Regex.Replace(tempString, pattern2, "");
returndata.Add(CollectionFieldName.Chap_Content, tempString);
//移除无效字符,用来计算长度
tempInnerText = HTMLUtil.RemoveHtmlTag(tempString).Replace(" ", "");
if (!string.IsNullOrEmpty(tempInnerText))
{
returndata.Add(CollectionFieldName.Chap_ContentLen, tempInnerText.Length);
string into = "";
if (tempInnerText.Length > 40)
{
into = tempInnerText.Substring(0, 40) + "...";
}
else
{
into = tempInnerText;
}
returndata.Add(CollectionFieldName.Chap_Intro, into);
int price = (tempString.Length / 1000) * 5;
if (price == 0)
{
price = 5;
}
if (price > 15)
{
price = 15;
}
returndata.Add(CollectionFieldName.Chap_Pirce, price);
}
returndata.Add(CollectionFieldName.Chap_Status, ChapterStatus.ChapterStatus_OnLine);
returndata.Add(CollectionFieldName.Chap_ChapterType, ChapterType.ChapterType_Free);
tempInnerText = tempNode.InnerText;
}
return(returndata);
}
/// <summary>
/// Volver a poner el formato HTML en un documento descodificado como ascii
/// </summary>
/// <param name="texto">Texto HTML</param>
/// <returns></returns>
public static string decodeHTML(string texto)
{
return(HTMLUtil.decodeHTML(texto));
}
private void FindIMDBActor(string strURL)
{
string[] vdbParserStr = VdbParserStringActor();
if (vdbParserStr == null || vdbParserStr.Length != 29)
{
return;
}
try
{
string absoluteUri;
// UTF-8 have problem with special country chars, default IMDB enc is used
string strBody = GetPage(strURL, "utf-8", out absoluteUri);
string value = string.Empty;
HTMLParser parser = new HTMLParser(strBody);
if ((parser.skipToEndOf(vdbParserStr[0])) && // <title>
(parser.extractTo(vdbParserStr[1], ref value)) && // </title>
!value.ToLowerInvariant().Equals(vdbParserStr[2])) // imdb name search
{
value = new HTMLUtil().ConvertHTMLToAnsi(value);
value = Util.Utils.RemoveParenthesis(value).Trim();
IMDBUrl oneUrl = new IMDBUrl(absoluteUri, value, "IMDB");
_elements.Add(oneUrl);
return;
}
parser.resetPosition();
string popularBody = string.Empty;
string exactBody = string.Empty;
string url = string.Empty;
string name = string.Empty;
string role = string.Empty;
if (parser.skipToStartOfNoCase(vdbParserStr[3])) // Popular names
{
parser.skipToEndOf(vdbParserStr[4]); // <table>
parser.extractTo(vdbParserStr[5], ref popularBody); // </table>
parser = new HTMLParser(popularBody);
while (parser.skipToStartOf(vdbParserStr[6])) // href="/name/
{
parser.skipToEndOf(vdbParserStr[7]); // href="
parser.extractTo(vdbParserStr[8], ref url); // "
parser.skipToEndOf(vdbParserStr[9]); // Image()).src='/rg/find-name-
parser.skipToEndOf(vdbParserStr[10]); // ';">
parser.extractTo(vdbParserStr[11], ref name); // </a>
parser.skipToEndOf(vdbParserStr[12]); // <small>(
parser.extractTo(vdbParserStr[13], ref role); // ,
if (role != string.Empty)
{
name += " - " + role;
}
name = new HTMLUtil().ConvertHTMLToAnsi(name);
name = Util.Utils.RemoveParenthesis(name).Trim();
IMDBUrl newUrl = new IMDBUrl("http://www.imdb.com" + url, name, "IMDB");
_elements.Add(newUrl);
parser.skipToEndOf(vdbParserStr[14]); // </tr>
}
}
parser = new HTMLParser(strBody);
if (parser.skipToStartOfNoCase(vdbParserStr[15])) // Exact Matches
{
parser.skipToEndOf(vdbParserStr[16]); // <table>
parser.extractTo(vdbParserStr[17], ref exactBody); // </table>
}
else if (parser.skipToStartOfNoCase(vdbParserStr[18])) // Approx Matches
{
parser.skipToEndOf(vdbParserStr[19]); // <table>
parser.extractTo(vdbParserStr[20], ref exactBody); // </table>
}
else
{
return;
}
parser = new HTMLParser(exactBody);
url = string.Empty;
name = string.Empty;
role = string.Empty;
while (parser.skipToStartOf(vdbParserStr[21])) // href="/name/
{
parser.skipToEndOf(vdbParserStr[22]); // href="
parser.extractTo(vdbParserStr[23], ref url); // "
parser.skipToEndOf(vdbParserStr[24]); // Image()).src='/rg/find-name-
parser.skipToEndOf(vdbParserStr[25]); // ';">
parser.extractTo(vdbParserStr[26], ref name); // </a>
parser.skipToEndOf(vdbParserStr[27]); // <small>(
parser.extractTo(vdbParserStr[28], ref role); // ,
if (role != string.Empty)
{
name += " - " + role;
}
name = new HTMLUtil().ConvertHTMLToAnsi(name);
name = Util.Utils.RemoveParenthesis(name).Trim();
IMDBUrl newUrl = new IMDBUrl("http://www.imdb.com" + url, name, "IMDB");
_elements.Add(newUrl);
parser.skipToEndOf(vdbParserStr[29]); // </tr>
}
}
catch (Exception ex)
{
Log.Error("exception for imdb lookup of {0} err:{1} stack:{2}", strURL, ex.Message, ex.StackTrace);
}
}