public void RepFile()
{
try {
List <string> list = FileAction.ReadToArr(file.FullName);
string p = file.FullName.Replace(path, outpath);
// 匹配注释正则
string regNotes = "([/]{2,}|[*]+).*";
// 匹配中文正则
string regChinese = @"([\u4e00-\u9fa5]{1,}[\s，,‘“;(（）)：、:.&\\-a-zA-Z0-9\u4e00-\u9fa5]{0,}[。”’！0-9\u4e00-\u9fa5]{1,})|([\u4e00-\u9fa5]{1})";
int index = 0;
foreach (var item in list)
{
index++;
// 去掉注释
string str = DataCheck.RepStr(item.Trim(), regNotes, "");
//是否包含中文
if (!DataCheck.CheckReg(str, regChinese))
{
FileAction.AppendStr(p, item + "\n");
}
else
{
// 取出中文
string[] strArr = DataCheck.GetRegStrArr(str, regChinese);
string temp = str;
string get = "";
// 在语言包中寻找匹配
foreach (var chinese in strArr)
{
// 如果没有包含汉字，查找下一个
if (!DataCheck.CheckReg(chinese, "[\u4e00-\u9fa5]+"))
{
continue;
}
// 若语言包中存在对应中文，直接替换
if (dic.ContainsKey(chinese))
{
get = dic[chinese];
temp = temp.Replace(chinese, DataCheck.RepLanguage(dic[chinese], false));
errInfo.Add($"{chinese}\t{dic[chinese]}\t{file.FullName}");
}
// 否则，去寻找最类似的中文
else
{
// 获取极限长度
int min = chinese.Length - 2;
int max = chinese.Length + 2;
// 判断是否替换
bool bl = false;
// 循环字典
foreach (var key in dic.Keys)
{
// 超出极限长度，则跳出
if (max < key.Length || key.Length < min)
{
continue;
}
// 若符合极限长度，且包含当前文字
if (key.Contains(chinese))
{
// 进行替换
temp = temp.Replace(chinese, DataCheck.RepLanguage(dic[key], false));
errInfo.Insert(0, $"^{chinese}：{index}行\t{dic[key]}\t{file.FullName}");
bl = true;
}
}
if (!bl)
{
errInfo.Insert(0, $"^^{chinese}：{index}行\t{file.FullName}");
}
}
}
// 将当前行写入文件
FileAction.AppendStr(p, item.Replace(str, temp) + "\n");
}
}
}
catch (Exception e) {
errInfo.Add("错误：" + file.FullName + "\t" + e.Message);
}
}
/// <summary>
///
/// </summary>
/// <param name="sender"></param>
/// <param name="e"></param>
private void Crawler_OnCompleted(OnCompletedEventArgs e, int layer, string Title = "")
{
SetLog($"读取网站：{e.Uri.ToString()}\n\t\t\t\t深度：{layer}\t用时：{e.Milliseconds} 毫秒\t线程ID：{e.TreadID}", Color.Gray);
UpAll(1);
urlList.Add(e.Uri.ToString());
HtmlDocument doc = new HtmlDocument();
doc.LoadHtml(e.PageSource);
ConReg = "//div[@id='endText']";
// 查看是否存在内容
HtmlNode conNode = doc.DocumentNode.SelectSingleNode(ConReg);
if (conNode != null)
{
string url = e.Uri.ToString();
// 判断此超链接是否已经读取
if (_GSQ_NewsService.Exists(c => c.url == url))
{
return;
}
if (!string.IsNullOrEmpty(conNode.InnerHtml))
{
GSQ_News _News = new GSQ_News();
_News.title = Title;
_News.url = e.Uri.ToString();
_News.sourcewebsite = conNode.InnerHtml;
_News.num = 0;
_News.CreateDate = DateTime.Now;
_GSQ_NewsService.AddEntity(_News);
UpCon(1);
UpNum(1);
SetLog($"抓取新闻《{Title}》，用时：{e.Milliseconds} 毫秒", Color.Gray);
}
return;
}
if (layer >= 4)
{
return;
}
// 获取所有a标签
var AList = doc.DocumentNode.Descendants("a");
foreach (var item in AList)
{
// 爬虫类
Crawler crawler = new Crawler();
Operation operation = new Operation()
{
Action = (x) => { },
Condition = (x) => { return(true); },
timeout = 5000
};
crawler.OnError += Crawler_OnError;
crawler.OnCompleted += (s, ex) => {
Crawler_OnCompleted(ex, layer + 1, item.InnerText);
};
string url = Utils.DelLastChar(e.Uri.ToString(), "/", 0);
string href = item.Attributes["href"]?.Value;
if (!string.IsNullOrEmpty(href) && !urlList.Contains(href) &&
DataCheck.CheckReg(href, DataCheck.Reg_Url) &&
href.Contains(url))
{
crawler.Start(href, operation, null).Wait();
}
}
}
