Last active
September 27, 2017 14:43
-
-
Save jeremiahlangner/005759a73f55167ace270ff7186338b6 to your computer and use it in GitHub Desktop.
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
(function() { | |
/* WIP for scraping table data from rendered Wikipedia and copying JSON to clipboard;*/ | |
var headlineEls = document.getElementsByClassName('mw-headline'); | |
var headlines = {}; | |
[].forEach.call(headlineEls, function(headline, i) { | |
var headline = headline.innerHTML; | |
headlines[headline] = i; | |
}); | |
var tables = document.getElementsByClassName('wikitable'); | |
[].forEach.call(tables, function(table, n) { | |
var tableObject = []; | |
var tableKeys = []; | |
var rows = table.getElementsByTagName('tr'); | |
[].forEach.call(rows, function(row, i) { | |
var rowObject = {}; | |
if(i == 0) { | |
var columns = row.getElementsByTagName('th'); | |
[].forEach.call(columns, function(column, j) { | |
var columnData = column.innerHTML; | |
columnData = columnData.replace(/<\/?[^>]+(>|$)/g, '').replace(/ *\([^)]*\) */g, '').replace(/\n/g, ''); | |
tableKeys[j] = columnData; | |
}); | |
} | |
if(i > 0) { | |
var columns = row.getElementsByTagName('td'); | |
[].forEach.call(columns, function(column, q) { | |
var columnData = column.innerHTML; | |
columnData = columnData.replace(/<\/?[^>]+(>|$)/g, '').replace(/\n/g, ''); | |
rowObject[tableKeys[q]] = columnData; | |
}); | |
tableObject.push(rowObject); | |
} | |
}); | |
for(var headline in headlines) { | |
if(headlines[headline] == n) { | |
headlines[headline] = tableObject; | |
} | |
} | |
}); | |
for(var headline in headlines) { | |
if(typeof(headlines[headline]) == 'number') { | |
delete(headlines[headline]); | |
} | |
} | |
copy(headlines); | |
})(); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment