private static void getSites(TweetDataEntities db, params string[] query)
{
HashSet<string> seenUrls = new HashSet<string>();
var twitter = new TwitterSearch();
int count = 0;
foreach (var tweet in twitter.Search(100, 10, query)) {
Debug.Print("Tweet number: " + (++count).ToString());
if (db.Tweets.Any(i => i.TweetID == tweet.TweetID)) {
continue;
}
Tweet t = new Tweet() { Text = tweet.Text, TweetID = tweet.TweetID };
Debug.Print("Tweet: " + tweet.Text);
Regex linkParser = new Regex(@"\b(?:http://|www\.)\S+\b", RegexOptions.Compiled | RegexOptions.IgnoreCase);
foreach (Match m in linkParser.Matches(tweet.Text)) {
string fullUrl = "";
try {
fullUrl = m.Value.ExpandUrl();
} catch {
continue;
}
if (db.Websites.Any(i => i.Url == fullUrl)) {
continue;
}
Debug.Print("Website: " + fullUrl);
var page = new PageScraper(fullUrl);
var website = new Website() { Url = page.Url, Title = page.Title() };
db.Websites.AddObject(website);
foreach (var m2 in page.Media()) {
if (db.Media.Any(i => i.Url == m2.Link)) {
continue;
}
Medium media = new Medium() { Type = m2.Type, Url = m2.Link, SourceSite = website.Url };
if (m2.Type == "image") {
var request = WebRequest.Create(m2.Link);
using (var response = request.GetResponse())
using (var stream = response.GetResponseStream())
using (var b = Bitmap.FromStream(stream)) {
int area = b.Width * b.Height;
media.ImageArea = area;
}
}
db.Media.AddObject(media);
Debug.Print("Media element: " + m2.Link);
}
t.LinkSite = website.Url;
}
db.Tweets.AddObject(t);
db.SaveChanges();
}
}
static void Main(string[] args)
{
var twitter = new TwitterSearch();
foreach (var tweet in twitter.Search(100, "data","visualization")) {
Console.WriteLine(tweet);
Regex linkParser = new Regex(@"\b(?:http://|www\.)\S+\b", RegexOptions.Compiled | RegexOptions.IgnoreCase);
foreach (Match m in linkParser.Matches(tweet.Text)) {
var fullUrl = m.Value.ExpandUrl();
var scraper = new PageScraper(fullUrl);
foreach (var img in scraper.GetImages()) {
Debug.Print(img);
}
}
}
}
public IEnumerable<PageScraper> GetSites(params string[] query)
{
HashSet<string> seenUrls = new HashSet<string>();
var twitter = new TwitterSearch();
foreach (var tweet in twitter.Search(10, 1, query)) {
Regex linkParser = new Regex(@"\b(?:http://|www\.)\S+\b", RegexOptions.Compiled | RegexOptions.IgnoreCase);
foreach (Match m in linkParser.Matches(tweet.Text)) {
var fullUrl = m.Value.ExpandUrl();
Debug.Print(fullUrl);
if (seenUrls.Contains(fullUrl)) {
continue;
}
yield return new PageScraper(fullUrl);
}
}
}