Start of webscraping

This commit is contained in:
2021-08-01 14:13:49 -04:00
parent 122d50dd33
commit ffcb6a12df
2 changed files with 61 additions and 0 deletions

60
Posting.cs Normal file
View File

@ -0,0 +1,60 @@
using System.Net.Http;
using System.Net.Http.Headers;
using System.Threading.Tasks;
using System.Net;
using System.Text;
using System.IO;
using System;
using HtmlAgilityPack;
public class Address
{
public string Street { get; set; }
public string City { get; set; }
public string State { get; set; }
public string ZipCode { get; set; }
}
public class Posting
{
public string Agency { get; set; }
public string Title { get; set; }
public string OccupationalCategory { get; set; }
public string SalaryGrade { get; set; }
public string BargainingUnit { get; set; }
public string SalaryRange { get; set; }
public string EmploymentType { get; set; }
public string AppointmentType { get; set; }
public string JurisdictionalClass { get; set; }
public string TravelPercentage { get; set; }
public string MinimumQualifications { get; set; }
public string DutiesDescription { get; set; }
public string ContactName { get; set; }
public string ContactEmailAddress { get; set; }
public Address LocationAddress { get; set; }
public Address ContactAddress { get; set; }
public string NotesOnApplying { get; set; }
public string VacancyID { get; set; }
public DateTime DatePosted { get; set; }
public DateTime DateDue { get; set; }
public Posting(string id)
{
string fullUrl = $"https://statejobs.ny.gov/employees/vacancyDetailsView.cfm?id={id}";
using (var client = new HttpClient())
{
var response = client.GetAsync(fullUrl).Result;
if (response.IsSuccessStatusCode)
{
var responseContent = response.Content;
// by calling .Result you are synchronously reading the result
string responseString = responseContent.ReadAsStringAsync().Result;
HtmlDocument htmlDoc = new HtmlDocument();
htmlDoc.LoadHtml(responseString);
}
}
}
}

View File

@ -5,6 +5,7 @@
</PropertyGroup>
<ItemGroup>
<PackageReference Include="HtmlAgilityPack" Version="1.11.34" />
<PackageReference Include="Newtonsoft.Json" Version="13.0.1" />
</ItemGroup>