/// <summary> /// Gets all the page urls from the first page /// the value of all of the urls will be used to grab /// all the html pages /// </summary> /// <param name="baseUrl"></param> /// <param name="paginatorXpath"></param> /// <param name="builder"></param> /// <returns></returns> public bool FetchPageUrls(string baseUrl, string paginatorXpath, ElementBuilder builder) { var document = new Document(); document.StartPage(baseUrl); var doc = document.Pages[0]; var links = doc.DocumentNode.SelectNodes(paginatorXpath); if (!LinksExists(paginatorXpath, doc)) { return(false); } GetNodes(builder, links.Select(x => x.Attributes["href"].Value).ToArray()); return(true); }
// Builder uses a complex series of steps public void Construct(ElementBuilder YelpBuilder) { YelpBuilder.BuildElementDictonary(); }