Created
June 15, 2019 19:19
-
-
Save benfb/0d007e114a9f0074561419800928ae33 to your computer and use it in GitHub Desktop.
A rough draft of a Julia script to create a DataFrame from Fangraphs data
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 Gumbo | |
using Cascadia | |
using Tables | |
using DataFrames | |
using CSV | |
import HTTP | |
r = HTTP.request("GET", "https://www.fangraphs.com/leaders.aspx?pos=all&stats=rel&lg=0&qual=10&type=c,-1,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,208,209,210,211,212,213,214,215,216,217,218,219,220,221,222,223,224,225,226,227,228,229,230,231,232,233,234,235,236,237,238,239,240,241,242,243,244,245,246,247,248,249,250,251,252,253,254,255,256,257,258,259,260,261,262,263,264,265,266,267,268,269,270,271,272,273,274,275,276,277,278,279,280,281,282,283,284,285,286,287,288,289,290,291,292,293,294,295,296,297,298,299&season=2019&month=0&season1=2019&ind=&team=&rost=&age=&filter=&players=&page=1_100000") | |
ht = parsehtml(String(r.body)) | |
tbl = eachmatch(Selector("table"),ht.root)[12] | |
mynames = [] | |
for e in eachmatch(Selector("th"),tbl) | |
if typeof(children(e)[1]) == HTMLElement{:a} | |
push!(mynames, children(e)[1][1]) | |
println(children(e)[1][1]) | |
println("") | |
end | |
end | |
namesstring = map(string, mynames) | |
replace(namesstring[length(namesstring)-1], "%" => "_pct") | |
# For each row in the stats table | |
matr2 = reshape([],0,300) | |
for row in children(eachmatch(Selector("tbody"),tbl)[1]) | |
created_row = Array{Any,1} | |
for (n, column) in enumerate(children(row)) | |
c = column[1] | |
if n == 1 | |
continue | |
end | |
if typeof(c) != HTMLText | |
c = c[1] | |
end | |
v = try | |
parse(Float64, string(c)) | |
catch ArgumentError | |
string(c) | |
end | |
created_row = [created_row v] | |
end | |
matr2 = [matr2;created_row] | |
end | |
symbolnames = map(Symbol, mynames) | |
tbbl = Tables.table(matr2) | |
df5 = DataFrame(tbbl) | |
deletecols!(df5, 1) | |
names!(df5, symbolnames, makeunique=true) | |
CSV.write("dataframetest1.csv", df5) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment