/// <summary>
/// 保存本子信息
/// </summary>
/// <param name="Book"></param>
private static void saveBook(AsmBook Book)
{
string savePath = BookRootPath + Book.bookID + ".txt";
if (!Directory.Exists(BookRootPath))
{
Directory.CreateDirectory(BookRootPath);
}
if (!File.Exists(savePath))
{
using (FileStream fs = File.Create(savePath))
{
BinaryFormatter bf = new BinaryFormatter();
bf.Serialize(fs, Book);
}
}
else
{
using (FileStream fs = new FileStream(savePath, FileMode.Open))
{
BinaryFormatter bf = new BinaryFormatter();
bf.Serialize(fs, Book);
}
}
}
static Queue <string> downloadWaitQ = new Queue <string>(); // 等待下载队列
public AsmDownloadControl()
{
// 添加BookID线程
Task.Run(() =>
{
while (!parsingQueue.IsCompleted)
{
string bookID = "";
bookID = parsingQueue.Take();
string html = askBookURL(bookID);
AsmBook book = Parsing(html, bookID);
if (book == null)
{
return;
}
saveBook(book);
downloadWaitQ.Enqueue(bookID);
}
}
);
}
/// <summary>
/// 解析本子网站获取信息并保存入book
/// </summary>
/// <param name="html"></param>
/// <param name="bookID"></param>
/// <returns></returns>
private static AsmBook Parsing(string html, string bookID)
{
if (html.Equals("Error"))
{
return(null); // 如果html为空则直接退出
}
AsmBook book = new AsmBook();
book.bookID = bookID;
Regex findTitle1 = new Regex(@"<h1>(?<Title1>[\s\S]*?)</h1>");
Match match1 = findTitle1.Match(html);
if (match1.Success)
{
book.title1 = match1.Groups["Title1"].Value;
//book.downloadPath += ("/" + book.title1);
}
Regex findTitle2 = new Regex(@"<h2>(?<Title2>[\s\S]*?)</h2>");
Match match2 = findTitle2.Match(html);
if (match2.Success)
{
book.title2 = match2.Groups["Title2"].Value;
}
// new Regex里表示要匹配的字符串
// (?<saveID>[\s\S]*?)表示要匹配的字符串中可变的格式
Regex findSaveID = new Regex(@"images.asmhentai.com/(?<saveID>[\s\S]*?)/" + book.bookID + "/cover.jpg");
Match match3 = findSaveID.Match(html);
if (match3.Success)
{
book.saveID = match3.Groups["saveID"].Value;
}
Regex findPage = new Regex(@"<h3>Pages: (?<Page>[\s\S]*?)</h3>");
Match match4 = findPage.Match(html);
if (match4.Success)
{
book.page = match4.Groups["Page"].Value;
}
// 用@时""表示" 不用@时\"表示"
Regex findArtist = new Regex(@"href=""/artists/name/(?<Artist>[\s\S]*?)/"">");
MatchCollection match5 = findArtist.Matches(html);
book.artists = new string[match5.Count];
for (int i = 0; i < match5.Count; i++)
{
book.artists[i] = match5[i].Groups["Artist"].Value;
}
Regex findTags = new Regex(@"href=""/tags/name/(?<Tag>[\s\S]*?)/"">");
MatchCollection match6 = findTags.Matches(html);
book.tags = new string[match6.Count];
for (int i = 0; i < match6.Count; i++)
{
book.tags[i] = match6[i].Groups["Tag"].Value;
}
int pageCount = int.Parse(book.page) + 1;
book.downloadPageURL = new string[pageCount];
book.downloadPageURL[0] = "https://images.asmhentai.com/" + book.saveID + "/" + book.bookID + "/cover.jpg";
for (int i = 1; i < pageCount; i++)
{
book.downloadPageURL[i] = "https://images.asmhentai.com/" + book.saveID + "/" + book.bookID + "/" + i.ToString() + ".jpg";
}
return(book);
}
