public async Task CanLoadRequestWithPostData(string url)
{
const string data = "Testing123";
//To use LoadRequest we must first load a web page
using (var browser = new ChromiumWebBrowser(new HtmlString("Testing")))
{
await browser.LoadPageAsync();
var request = new Request();
request.Url = "http://httpbin.org/post";
request.Method = "POST";
var postData = new PostData();
postData.AddElement(new PostDataElement
{
Bytes = Encoding.UTF8.GetBytes(data)
});
request.PostData = postData;
await browser.LoadRequestAsync(request);
var mainFrame = browser.GetMainFrame();
Assert.Equal(url, mainFrame.Url);
var navEntry = await browser.GetVisibleNavigationEntryAsync();
Assert.Equal((int)HttpStatusCode.OK, navEntry.HttpStatusCode);
Assert.True(navEntry.HasPostData);
var source = await browser.GetTextAsync();
Assert.Contains(data, source);
}
}
public async Task CanLoadRequestWithPostData(string url)
{
const string data = "Testing123";
//When Chromium Site Isolation is enabled we must first navigate to
//a web page of the same origin to use LoadRequest
//When Site Isolation is disabled we can navigate to any web page
//https://magpcss.org/ceforum/viewtopic.php?f=10&t=18672&p=50266#p50249
using (var browser = new ChromiumWebBrowser("http://httpbin.org/"))
{
var response = await browser.LoadUrlAsync();
Assert.True(response.Success);
var request = new Request
{
Url = "http://httpbin.org/post",
Method = "POST"
};
var postData = new PostData();
postData.AddElement(new PostDataElement
{
Bytes = Encoding.UTF8.GetBytes(data)
});
request.PostData = postData;
await browser.LoadRequestAsync(request);
var mainFrame = browser.GetMainFrame();
Assert.Equal(url, mainFrame.Url);
var navEntry = await browser.GetVisibleNavigationEntryAsync();
Assert.Equal((int)HttpStatusCode.OK, navEntry.HttpStatusCode);
Assert.True(navEntry.HasPostData);
var source = await browser.GetTextAsync();
Assert.Contains(data, source);
}
}
public string[] ExtractSearchResults(string[] topics, string searchURL)
{
PostData pd = new PostData();
foreach (string topic in topics)
{
pd.AddElement("topicBeanCount.topicString", topic);
}
string response = wb.Navigate(pd, searchURL);
//Log("Parsez rezultatele cautarii: ");
//aflam numarul maxim de articole gasite
Regex r = new Regex(@"startValue=(.*?)\""");
string[] pagini_cautare = ExtractDataUsingRegex(r, response);
int maxPage = 0;
List <string> url_cautare = new List <string>();
List <string> verificate = new List <string>();
foreach (string tmp in pagini_cautare)
{
string ps = tmp.Substring(tmp.LastIndexOf('=') + 1);
ps = ps.Substring(0, ps.Length - 1);
int pag = int.Parse(ps);
if (pag > maxPage)
{
maxPage = pag;
}
if (!verificate.Contains(pag.ToString()))
{
verificate.Add(pag.ToString());
url_cautare.Add("http://www.europarl.europa.eu/news/archive/search/topicSearch.do?language=RO&startValue=" + pag);
}
}
//Log("\tPagina maxima de cautare este :" + maxPage.ToString() + " => 30*" + maxPage.ToString() + "=" + 30 * maxPage + " articole");
//Log("\tGenerez lista de cautare:");
//foreach (string s in url_cautare) {
// Log("\t\t" + s);
//}
List <string> articole = new List <string>();
//Log("\tGenerez lista de articole pentru fiecare pagina:");
r = new Regex(@"pubRef=(.*?)&", RegexOptions.IgnoreCase);
string[] tmpList = ExtractDataUsingRegex(r, response);
//articole.AddRange(tmpList);
//Log("\t\tPagina 1:");
foreach (string s in tmpList)
{
if (!articole.Contains(s))
{
//Log("\t\t\t" + s);
articole.Add(s);
}
}
int i = 1;
foreach (string s in url_cautare)
{
response = wb.Navigate(pd, s);
r = new Regex(@"pubRef=(.*?)&", RegexOptions.IgnoreCase);
tmpList = ExtractDataUsingRegex(r, response);
//articole.AddRange(tmpList);
i++;
//Log("\t\tPagina " + i + ":");
foreach (string surl in tmpList)
{
if (!articole.Contains(surl))
{
//Log("\t\t\t" + surl);
articole.Add(surl);
}
}
}
//postprocesare linkuri
for (int idx = 0; idx < articole.Count; idx++)
{
string s = "http://www.europarl.europa.eu/sides/getDoc.do?pubRef=" + articole[idx].Substring(7, articole[idx].Length - 14);
articole[idx] = s;
}
return(articole.ToArray());
}