/// <summary>
/// Parses the list.
/// </summary>
/// <returns>The list.</returns>
/// <param name="Html">Html.</param>
/// <param name="Pattern">Pattern.</param>
/// <param name="Url">URL.</param>
/// <param name="RecogNextPage">If set to <c>true</c> recog next page.</param>
public static ArticleList ParseList(string Html, string Pattern, string Url = null, bool RecogNextPage = true)
{
//输入检查
if (string.IsNullOrWhiteSpace(Html) || string.IsNullOrWhiteSpace(Pattern))
{
return(null);
}
ArticleList articleList = new ArticleList();
//处理繁体字先
Html = TextCleaner.ToSimplifyString(Html);
#region Item集合
List <Article> Items = null;
#if !NET40
MatchCollection Matches = Regex.Matches(Html, Pattern, RegexOptions.IgnoreCase | RegexOptions.Multiline, new TimeSpan(0, 0, 10));
#else
MatchCollection Matches = RegexUtility.Matches(Html, Pattern, RegexOptions.IgnoreCase | RegexOptions.Multiline, 10);
#endif
if (Matches == null)
{
Logger.Warn(string.Format("正则ParseList失败,Url={0}", Url));
}
int MatchesCount = 0;
try
{
MatchesCount = Matches.Count;
}
#if !NET40
catch (RegexMatchTimeoutException e)
#else
catch (Exception e)
#endif
{
Logger.Error(string.Format("正则ParseList超时,Url={0}", Url), e);
Matches = null;
}
if (Matches != null && Matches.Count > 0)
{
Items = new List <Article>(Matches.Count);
//去重，唯一ItemID
HashSet <string> ItemIDs = new HashSet <string>();
foreach (Match m in Matches)
{
Article Item = new Article();
Match2Item(m, ref Item, Url, true);
if (Item != null)
{
Items.Add(Item);
}
}
}
articleList.Articles = Items;
articleList.Count = Items.Count;
articleList.CurrentPage = 1;
#endregion Item集合
return(articleList);
}
