Last active
September 28, 2023 10:58
-
-
Save ptupitsyn/187bcb657047e98d10a9ec00dbb3b54e to your computer and use it in GitHub Desktop.
Bamboo directory parser
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
<Project Sdk="Microsoft.NET.Sdk"> | |
<PropertyGroup> | |
<OutputType>Exe</OutputType> | |
<TargetFramework>net7.0</TargetFramework> | |
<ImplicitUsings>enable</ImplicitUsings> | |
<Nullable>enable</Nullable> | |
</PropertyGroup> | |
<ItemGroup> | |
<None Update="bamboo-directory.html"> | |
<CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory> | |
</None> | |
</ItemGroup> | |
<ItemGroup> | |
<PackageReference Include="CsvHelper" Version="30.0.1" /> | |
<PackageReference Include="HtmlAgilityPack" Version="1.11.53" /> | |
</ItemGroup> | |
</Project> |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
using System.Globalization; | |
using CsvHelper; | |
using HtmlAgilityPack; | |
const string file = "bamboo-directory.html"; | |
var html = File.ReadAllText(file); | |
var doc = new HtmlDocument(); | |
doc.LoadHtml(html); | |
var employeeCards = SelectDivByClass(doc.DocumentNode, "EmployeeCardContainer__infoContainer").ToList(); | |
var employees = employeeCards.Select(ParseEmployeeCard).ToList(); | |
employees.ForEach(Console.WriteLine); | |
// Save to CSV | |
using (var writer = new StreamWriter("bamboo-directory.csv")) | |
using (var csv = new CsvWriter(writer, CultureInfo.InvariantCulture)) | |
{ | |
csv.WriteRecords(employees); | |
} | |
Console.WriteLine($"CSV saved: {employees.Count} employees"); | |
static Employee ParseEmployeeCard(HtmlNode employeeCard) | |
{ | |
var name = SelectDivTextByClass(employeeCard, "JobInfo__name").Single(); | |
var jobInfo = SelectDivTextByClass(employeeCard, "JobInfo__text").ToList(); | |
var reports = SelectDivTextByClass(employeeCard, "ReportsTo__item").ToList(); | |
var contactInfo = SelectDivTextByClass(employeeCard, "ContactInfo__text").ToList(); | |
return new Employee( | |
Name: name, | |
Title: jobInfo[0].Replace("&", "&"), | |
Email: contactInfo[0], | |
Phone: contactInfo.FirstOrDefault(x => x.StartsWith("+")) ?? string.Empty, | |
SupervisorName: reports.First().Replace("Reports to ", string.Empty), | |
Location: jobInfo[1].Split('|', StringSplitOptions.TrimEntries)[0], | |
Team: jobInfo[2].Replace("&", "&")); | |
} | |
static IEnumerable<string> SelectDivTextByClass(HtmlNode node, string cls) => | |
SelectDivByClass(node, cls).Select(x => x.InnerText); | |
static HtmlNodeCollection SelectDivByClass(HtmlNode node, string cls) => | |
node.SelectNodes($".//div[contains(@class, '{cls}')]"); | |
public record Employee( | |
string Name, | |
string Title, | |
string Email, | |
string Phone, | |
string SupervisorName, | |
string Location, | |
string Team); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment