/// <summary>
/// Fetches content for the specified URL and analyze it.
/// </summary>
/// <returns><see cref="PageData"></see> object</returns>
/// <remarks>
/// <p>
/// This method fetches content from the specified URL and then analyzes it to put
/// data into respective components like <see cref="HeaderData"></see>, <see cref="LinkDataCollection"></see> etc.
/// inside <see cref="PageData"></see> object.
/// </p>
/// </remarks>
public PageData AnalyzePage()
{
PageExtractor obPageExtractor = new PageExtractor(this);
PageData obPageData = obPageExtractor.GetPageData();
return(obPageData);
}
public void ExtractLinks_Should_Succeed()
{
var extractor = new PageExtractor();
var pageInfo = extractor.Extract("<link href=\"https:\\\\website.com\"");
Assert.AreEqual(1, pageInfo.links.Count());
Assert.AreEqual("https:\\\\website.com", pageInfo.links.First());
}
static void Main(string[] args)
{
db = new PageInfoContext();
pExtractor = new PageExtractor();
// Create a Timer object that knows to call our TimerCallback
// method once every 2000 milliseconds.
Timer t = new Timer(TimerCallback, null, 0, 10000);
// Wait for the user to hit <Enter>
Console.ReadLine();
}
public void ExtractContent_Should_AsExpected()
{
var extractor = new PageExtractor();
var pageInfo = extractor.Extract(@"
<html>
<head>
<style></style>
</head>
<body>
<div>Something</div>
<script>var abc = function()</script>
</body>
</html>
");
Assert.AreEqual("Something", pageInfo.content.Trim());
}
public DZoneProxy()
{
fetcher = new PageFetcher();
extractor = new PageExtractor();
}
