/// <summary>
/// 抓取网页内容
/// </summary>
/// <param name="id">数据的ID，源自网页中的ID</param>
/// <param name="url">抓取的URl</param>
/// <returns></returns>
private bool CatchContent(long id, string url)
{
dataEncoding = cbbEncoding.Text;
data = WebAccess.Request(url, string.Empty, WebAccess.WebAccessMethod.POST, "text\\html", null, dataEncoding);
if (!string.IsNullOrEmpty(data) && data.Contains(txtFilter.Text) && !data.Contains(txtOppFilter.Text))
{
try
{
//匹配过滤
item.ID = id.ToString();
item.Title = FindText.Find(data, config.GetConfig("Title"));
item.Author = FindText.Find(data, config.GetConfig("Author"));
item.CreateDate = FindText.Find(data, config.GetConfig("CreateDate"));
item.ImageUrl = FindText.Find(data, config.GetConfig("ImageUrl"));
item.Content = FindText.Find(data, config.GetConfig("Content"));
//处理HTML内容
if (cbReplaceHtml.Checked)
{
item.Content = HtmlText.ToText(item.Content);
}
int contentLength = Convert.ToInt32(txtContentLength.Text);
if (!string.IsNullOrEmpty(item.Title) && item.Content.Length > contentLength)
{
resultFileName = string.Format("{0}//{1}.txt", OUTPUT_PATH, CommonFile.RemoveInvalidChar(item.Title));
System.IO.File.WriteAllText(resultFileName, item.ToString());
return(true);
}
}
catch (Exception ex)
{
txtMessage.Text = ex.Message;
}
}
return(false);
}