public WebpageScraper_Stocklink(string url)
: base(url, PageProcessingOptions.SimplifyPage)
{
var titleNode = base._headNode.Descendants()
.Where(n => n.Name == "title").SingleOrDefault();
var title = titleNode.InnerText.Replace("Stocklink.no", string.Empty).Replace("-", string.Empty).Trim();
var descriptionNode = base._headNode.Descendants()
.Where(n => n.Name == "meta" && n.Attributes.Contains("name") && n.Attributes["name"].Value.Split().Contains("description")).SingleOrDefault();
var description = descriptionNode.Attributes["content"].Value;
var keywordsNode = base._headNode.Descendants()
.Where(n => n.Name == "meta" && n.Attributes.Contains("name") && n.Attributes["name"].Value.Split().Contains("keywords")).SingleOrDefault();
var keyWords = keywordsNode.Attributes["content"].Value.Split(',').ToList();
//<span id="ctl00_MainArea_m_ArticleContentLbl">
var contentNode = base._bodyNode.Descendants()
.Where(x => x.Name == "span" && x.Attributes.Contains("id")
&& x.Attributes["id"].Value.Split().Contains("ctl00_MainArea_m_ArticleContentLbl") // TODO: redefine this weak check
).SingleOrDefault();
// Get all paragraphs within node
var paragraphs = contentNode.Descendants().Where(n => n.Name == "p").ToList();
string content = string.Empty;
foreach (var item in paragraphs)
content += item.InnerText;
//<td class="articleByline">
//<div id="ctl00_MainArea_m_BylineDiv">
// Av:
// <a id="ctl00_MainArea_m_ArticleAuthorEmail" href="mailto:[email protected]">Asgeir Nilsen</a>
// - StockLink.no</div>
//<span id="ctl00_MainArea_m_ArticlePublishedDateLbl">Publisert: 07.08.2015 09:55:46</span><span id="ctl00_MainArea_m_ArticleUpdatedDateLbl"> - Oppdatert: 07.08.2015 09:58:
var bylineNode = _bodyNode.Descendants().Where(n => n.Name == "a" && n.Attributes.Contains("id") && n.Attributes["id"].Value.Split().Contains("ctl00_MainArea_m_ArticleAuthorEmail")).SingleOrDefault();
var author = new Author()
{
Email = bylineNode.Attributes["href"].Value,
Name = bylineNode.InnerText
};
var publishedNode = _bodyNode.Descendants().Where(n => n.Name == "span" && n.Attributes.Contains("id") && n.Attributes["id"].Value.Split().Contains("ctl00_MainArea_m_ArticlePublishedDateLbl")).SingleOrDefault();
var publishedDate = Convert.ToDateTime(publishedNode.InnerText.Replace("Publisert: ", string.Empty));
var updatedNode = _bodyNode.Descendants().Where(n => n.Name == "span" && n.Attributes.Contains("id") && n.Attributes["id"].Value.Split().Contains("ctl00_MainArea_m_ArticleUpdatedDateLbl")).SingleOrDefault();
var updatedDate= Convert.ToDateTime(updatedNode.InnerText.Replace(" - Oppdatert: ", string.Empty));
base.SetArticleData(title, description, null, content, new List<Author>() {author}, publishedDate, updatedDate);
}
public WebpageScraper_Hegnar(string url)
: base(url, PageProcessingOptions.SimplifyPage)
{
var titleNode = base._headNode.Descendants()
.Where(n => n.Name == "meta" && n.Attributes.Contains("property") && n.Attributes["property"].Value.Split().Contains("og:title")).SingleOrDefault();
var title = titleNode.Attributes["content"].Value;
var descriptionNode = base._headNode.Descendants()
.Where(n => n.Name == "meta" && n.Attributes.Contains("property") && n.Attributes["property"].Value.Split().Contains("og:description")).SingleOrDefault();
var description = descriptionNode.Attributes["content"].Value;
var contentNode = base._bodyNode.Descendants()
.Where(x => x.Name == "div" && x.Attributes.Contains("class")
&& x.Attributes["class"].Value.Split().Contains("body") // TODO: redefine this weak check
).SingleOrDefault();
// Get all paragraphs within node
var paragraphs = contentNode.Descendants().Where(n => n.Name == "p").ToList();
string content = string.Empty;
foreach (var item in paragraphs)
{
content += item.InnerText;
}
//<p class="byline">
//Artikkel av:
//Stein Ove Haugen
//(Hegnar.no - 26.4.15 08:01)
//</p>
var bylineNode = _bodyNode.Descendants().Where(n => n.Name == "p" && n.Attributes.Contains("class") && n.Attributes["class"].Value.Split().Contains("byline")).SingleOrDefault();
var refined = bylineNode.InnerText.Replace("Artikkel av:", string.Empty).Replace("Hegnar.no - ", string.Empty);
var authorString = refined.Split('(')[0].Replace(Environment.NewLine, string.Empty);
var author = new Author() { Email = "NA", Name = authorString };
var publishedString = refined.Split('(')[1].Replace(Environment.NewLine, string.Empty).Replace("(", string.Empty);
var publishedDate = Convert.ToDateTime(publishedString);
base.SetArticleData(title, description, null, content, new List<Author>() { author}, publishedDate, null);
}
