blog-parser.cs

blog-parser.cs

using System.Text.RegularExpressions;

/*

Top25 Authors of all 512 PRs in https://devblogs.microsoft.com/dotnet/performance_improvements_in_net_7/
(by count):

stephentoub         -- 148
EgorBo              -- 45
tannergooding       -- 26
vcsjones            -- 23
adamsitnik          -- 17
elinor-fung         -- 14
AndyAyersMS         -- 10
wfurt               -- 9
eiriktsarpalis      -- 9
TIHan               -- 8
jkoritzinsky        -- 8
AaronRobinsonMSFT   -- 7
bartonjs            -- 7
kunalspathak        -- 6
simonrozsival       -- 6
BruceForstall       -- 5
jkotas              -- 5
kouvel              -- 5
teo-tsirpanis       -- 5
olsaarik            -- 5
joperezr            -- 5
tmds                -- 5
SingleAccretion     -- 4
MichalStrehovsky    -- 4
vargaz              -- 4
*/


string file = await new HttpClient().GetStringAsync(
    "https://devblogs.microsoft.com/dotnet/performance_improvements_in_net_7/");

MatchCollection pullRequestUrls =
    Regex.Matches(file, @"https:\/\/github.com\/[a-zA-Z-]+\/[a-zA-Z-]+\/pull\/[0-9]+");
int total = pullRequestUrls.Count;
int i = 1;

List<string> authors = new();
foreach (var pullRequestUrl in pullRequestUrls.Select(m => m.ToString().Trim()).Distinct())
{
    string content = await new HttpClient().GetStringAsync(pullRequestUrl);
    string title = Regex.Match(content, @"<title>(.*?)<\/title>").Value
        .Replace("<title>", "")
        .Replace("</title>", "")
        .Trim();

    if (!title.Contains(" · Pull Request #"))
    {
        // there are 6 links which are github issues rather than PRs despite /pull/ in the url
        continue;
    }

    title = title.Substring(0, title.IndexOf(" · Pull Request #"));
    string nick = title.Substring(title.LastIndexOf(" by ") + " by ".Length).Trim();
    Console.WriteLine($"{i++}/{total}: {title}");
    authors.Add(nick);
}

// Print top25 most popular authors
foreach (var author in authors.GroupBy(g => g).OrderByDescending(g => g.Count()).Take(25))
{
    Console.WriteLine(author.Key.PadRight(
        authors.Select(a => a.Length).Max() + 1) + " -- " + author.Count());
}