blogpost-parser.cs

blogpost-parser.cs

using System.Text.RegularExpressions;

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);
}

foreach (var author in authors.GroupBy(g => g).OrderByDescending(g => g.Count()))
{
    Console.WriteLine(author.Key.PadRight(
        authors.Select(a => a.Length).Max() + 1) + " -- " + author.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
fanyang-mono        -- 4
GrabYourPitchforks  -- 4
AlekseyTs           -- 4
eerhardt            -- 4
jakobbotsch         -- 3
echesakov           -- 3
steveharter         -- 3
alexcovington       -- 3
SwapnilGaikwad      -- 3
NewellClark         -- 3
filipnavara         -- 3
TrayanZapryanov     -- 3
CodeBlanch          -- 3
BrzVlad             -- 2
mkhamoyan           -- 2
huoyaoyuan          -- 2
SergeiPavlov        -- 2
am11                -- 2
gfoidl              -- 2
veanes              -- 2
Clockwork-Muse      -- 2
lateapexearlyspeed  -- 2
bgrainger           -- 2
MihaZupan           -- 2
geoffkizer          -- 2
kronic              -- 2
Cosifne             -- 2
hez2010             -- 1
anthonycanino       -- 1
pentp               -- 1
SeanWoo             -- 1
janvorli            -- 1
weilinwa            -- 1
JulieLeeMSFT        -- 1
Wraith2             -- 1
mangod9             -- 1
radekdoulik         -- 1
VSadov              -- 1
AntonLapounov       -- 1
CarlVerret          -- 1
madelson            -- 1
MichalPetryka       -- 1
key-moon            -- 1
sakno               -- 1
nietras             -- 1
yesmey              -- 1
a74nh               -- 1
cston               -- 1
YairHalberstadt     -- 1
RikkiGibson         -- 1
grbell-ms           -- 1
RaymondHuy          -- 1
johnthcall          -- 1
deeprobin           -- 1
pedrobsaila         -- 1
rzikm               -- 1
onehourlate         -- 1
krwq                -- 1
strobelt            -- 1
chrisdcmoore        -- 1
SteveDunn           -- 1
schuettecarsten     -- 1
Bibletoon           -- 1
BrennanConroy       -- 1
CollinAlpert        -- 1
buyaa-n             -- 1
chucker             -- 1
wzchua              -- 1
pawchen             -- 1
marek-safar         -- 1
*/