//This gives the crawler a starting point without user input.
public async Task <bool> crawlerStartingPoint()
{
bool completed = false;
//Starting point
try
{
//Crawler starting point
Debug.WriteLine("crawlerStartingPoint gets results");
httpClientRequest = new HTTPFactory();
string httpResponseBody = "";
string url = "https://www.youtube.com/";
httpResponseBody = await httpClientRequest.YoutubeCrawlRequest(url);
//Get the body from the HTTP response.
httpResponseBody = CrawlerRegex.regexContent(httpResponseBody);
lock (this.locker)
{
listResponses.Add(httpResponseBody);
completed = true;
}
}
catch (NullReferenceException e)
{
Debug.WriteLine("crawlerStartingPoint() geeft NullReferenceException: " + e.Message);
}
return(completed);
}
public async Task <string> getResponseBody(string url)
{
string replyBody = "";
//getResponseBody url
httpClientRequest = new HTTPFactory();
//Which URL to fetch
Debug.WriteLine("url in getResponseBody() = " + url);
try
{
replyBody = await httpClientRequest.YoutubeCrawlRequest(url); //await = wacht totdat antwoord is
}
catch (Exception ex)
{
//Give exception if HTTPRequest has bugged.
Debug.WriteLine("httpError: " + ex.StackTrace);
}
return(replyBody);
}
//Search with user input
static public async Task <string> crawlerSearchterm(string zoekterm)
{
HTTPFactory httpClientRequest = new HTTPFactory();
string httpResponseBody = await httpClientRequest.YoutubeSearchResults(zoekterm);
//Get results from response
httpResponseBody = CrawlerRegex.regexResults(httpResponseBody);
await Task.Factory.StartNew(async() =>
{
//Extract urls from response
List <string> urls = CrawlerRegex.regexUrls(httpResponseBody);
//Iterate on the extracted results
foreach (String url in urls)
{
//Extract body from URL
string body = "";
string response = "";
//getResponseBody url
httpClientRequest = new HTTPFactory();
await Task.Delay(1000);
//Crawl on URL
response = await httpClientRequest.YoutubeCrawlRequest(url);
//Extract content from string
body = CrawlerRegex.regexContent(response);
//Get keywords from body
CrawlerRegex.regexKeywords(body);
} //End code with URLS found
});
//return string from httpResponseBody
return(httpResponseBody);
}
