public static List <string> GetPageDownUrlAuto(string baseUrl)
{
//自动获取翻页
//1、直接在url后面加 _page
//2、将url最后一段转换成数字加1
List <string> list = new List <string>();
var urlSuffix = baseUrl.Substring(baseUrl.LastIndexOf("."));
var subUrl = baseUrl.Substring(baseUrl.LastIndexOf("/") + 1).Replace(urlSuffix, "");
var resultUrl = "";
var pageStr = "";
var page = 0;
//获取最后一段数字区域
pageStr = RegexUtil.ExtractDigit(subUrl);
if (int.TryParse(pageStr, out page) == true)
{
resultUrl = subUrl.Replace(pageStr, (++page).ToString());
}
resultUrl = baseUrl.Replace(subUrl, resultUrl);
//添加到url列表中
list.Add(resultUrl);
resultUrl = subUrl + "_2";
resultUrl = baseUrl.Replace(subUrl, resultUrl);
//添加到url列表中
list.Add(resultUrl);
return(list);
}
public static string GetPageDownUrlManual(string baseUrl, string pageDownUrl)
{
//目前只考虑简单的翻页，太复杂的翻页还是具体情况具体分析
var url = "";
int i;
for (i = 0; i < baseUrl.Length; i++)
{
if (baseUrl[i] == pageDownUrl[i])
{
continue;
}
break;
}
url = pageDownUrl.Substring(i);
//补齐
baseUrl = baseUrl.PadLeft(pageDownUrl.Length, ' ');
for (i = pageDownUrl.Length - 1; i >= 0; i--)
{
if (pageDownUrl[i] == baseUrl[i])
{
continue;
}
break;
}
url = pageDownUrl.Substring(i);
var pageStr = RegexUtil.ExtractDigit(url);
if (string.IsNullOrEmpty(pageStr))
{
return(pageDownUrl);
}
var page = 0;
int.TryParse(pageStr, out page);
url = url.Replace(pageStr, (++page).ToString());
//防止前面有数字重合的，再获取最后一段url
var subUrl = pageDownUrl.Substring(pageDownUrl.LastIndexOf("/") + 1);
url = pageDownUrl.Replace(subUrl, subUrl.Replace(pageStr, url));
return(url);
}
