/// <summary>
/// 构造方法
/// </summary>
/// <param name="paginationStr">分页信息片段： http://a.com?p=40 PaginationStr: p=40</param>
/// <param name="termination">中止器</param>
protected PaginationTargetUrlsExtractor(string paginationStr, ITargetUrlsExtractorTermination termination = null)
{
if (string.IsNullOrWhiteSpace(paginationStr))
{
throw new SpiderException("paginationStr should not be null or empty");
}
PaginationStr = paginationStr;
PaginationPattern = new Regex($"{RegexUtil.Number.Replace(PaginationStr, @"\d+")}");
TargetUrlsExtractorTermination = termination;
}
/// <summary>
/// 构造方法
/// </summary>
/// <param name="paginationStr">URL中分页的部分, 如: www.a.com/content_1.html, 则可以填此值为 content_1.html, tent_1.html等, 框架会把数据部分改成\d+用于正则匹配截取</param>
/// <param name="interval">每次自增的间隔</param>
/// <param name="termination">中止器, 用于判断是否已到最后一个需要采集的链接</param>
public AutoIncrementTargetUrlsExtractor(string paginationStr, int interval = 1, ITargetUrlsExtractorTermination termination = null) : base(paginationStr, termination)
{
_interval = interval;
}
