List of English contractions from Wikipedia

english_contractions_dataset.js

script = document.createElement('script');script.src = "https://ajax.googleapis.com/ajax/libs/jquery/1.6.3/jquery.min.js";document.getElementsByTagName('head')[0].appendChild(script);
function download(name,jsonObject) {
    var fileContents = JSON.stringify(jsonObject, null, 2);
    var pp = document.createElement('a');
    pp.setAttribute('href', 'data:text/plain;charset=utf-8,' + encodeURIComponent(fileContents));
    pp.setAttribute('download', name+'.json');
    pp.click();
}
df={}
$( $('.wikitable')[0] ).find('tr').each((index,item) => {
    if(index==0) return
    cntrc=$($(item).find('td')[0]).text().replace(/\n|\[.+\]|\(.+\)/g,'').replace(/\s+/g, ' ').replace(/^\s+|\s+$/g, '')
    // remove links in expanded words
    $($(item).find('td')[1]).find('a').remove();
    // return the first match in the expansion and return the first comma separated value
    // (this accounts for Scottish <a> and "'s" mapping to "is, has, does, or us" vs. just "is"
    expnd=$($(item).find('td')[1]).text().replace(/\n|\[.+\]|\(.+\)/g,'').replace(/\s+/g, ' ').replace(/^\s+|\s+$/g, '').split('/')[0].trim().split(',')[0].trim();
    df[cntrc]=expnd
})
download("english_contractions_ds",df)

Run the code in a JavaScript console of the Wikipedia page: https://en.wikipedia.org/wiki/Wikipedia:List_of_English_contractions
Generated dataset of English Contractions from Wikipedia:
https://gist.github.com/loretoparisi/db70e9b91c7f2363a8dc9ecd80d58ce6

What about handling

    "noun's": "noun is",
    "noun're": "noun"

(Also shouldn't that last one be "noun are"?)

Thanks, fixed that!

@loretoparisi can you modify it per below? (remove the <a> tags in the second <td>):

script = document.createElement('script');script.src = "https://ajax.googleapis.com/ajax/libs/jquery/1.6.3/jquery.min.js";document.getElementsByTagName('head')[0].appendChild(script);
function download(name,jsonObject) {
    var fileContents = JSON.stringify(jsonObject, null, 2);
    var pp = document.createElement('a');
    pp.setAttribute('href', 'data:text/plain;charset=utf-8,' + encodeURIComponent(fileContents));
    pp.setAttribute('download', name+'.json');
    pp.click();
}
df={}
$( $('.wikitable')[0] ).find('tr').each((index,item) => {
    if(index==0) return
    cntrc=$($(item).find('td')[0]).text().replace(/\n|\[.+\]|\(.+\)/g,'').replace(/\s+/g, ' ').replace(/^\s+|\s+$/g, '')
    // remove links in expanded words
    $($(item).find('td')[1]).find('a').remove();
    // return the first match in the expansion and return the first comma separated value
    // (this accounts for Scottish <a> and "'s" mapping to "is, has, does, or us" vs. just "is"
    expnd=$($(item).find('td')[1]).text().replace(/\n|\[.+\]|\(.+\)/g,'').replace(/\s+/g, ' ').replace(/^\s+|\s+$/g, '').split('/')[0].trim().split(',')[0].trim();
    df[cntrc]=expnd
})
download("english_contractions_ds",df)

@titanism fixed to your version, thank you!