public static string GetJobDescription(string url, string xpath)
{
var htmlDoc = CustomWebClient.GetHtmlDocument(url);
var htmlBody = htmlDoc?.DocumentNode.SelectSingleNode(xpath);
if (htmlDoc == null || htmlBody == null)
{
return(string.Empty);
}
return(htmlBody.InnerText.Trim());
}
// Initiate scraping procedure.
public static void StartScraping()
{
Website = new Website(Form1.UrlBox.Text);
do
{
var htmlBody = CustomWebClient.GetHtmlDocument(Website.Url.AbsoluteUri);
var newJobs = GetJobs(htmlBody, Constants.WebsiteXpaths[Website.Url.Host], Options.DescriptionScraping);
// If we have limited jobs on a website,
// check if we are not past them.
if (newJobs.Count == 0)
{
break;
}
else if (Website.MaxWebsiteJobs.HasValue)
{
if (Website.MaxWebsiteJobs.Value <= Jobs.Count)
{
break;
}
}
// Get the end of the parsing if we know total job count before hand.
if (Website.MaxWebsiteJobs.HasValue == false &&
Website.Url.Host == Constants.Website.CVbankas)
{
Website.MaxWebsiteJobs = GetCVbankasScrapingEnd(htmlBody,
Constants.WebsiteXpaths[Website.Url.Host]);
}
Jobs.AddRange(newJobs);
Form1.Grid.Rows.AddRange(newJobs.Select(x => x.GetDataGridViewRow()).ToArray());
// Increment URL parameter by one.
Website.Url = Website.Url.IncreaseQueryIntegerValue(Constants.WebsiteParam.Page);
Statistics.DisplayTotalJobCount(Jobs.Count);
Thread.Sleep(Constants.SleepTime);
}while (Options.ScrapAllPages);
}
