Convert HTML table with a header to Json - Python

Answer 1

You can use soup.find_all:

from bs4 import BeautifulSoup as soup
s = soup(html, 'html.parser').table
h, [_, *d] = [i.text for i in s.tr.find_all('th')], [[i.text for i in b.find_all('td')] for b in s.find_all('tr')]
result = [dict(zip(h, i)) for i in d]

Output:

[{'Name': 'John', 'Age': '28', 'License': 'Y', 'Amount': '12.30'}, {'Name': 'Kevin', 'Age': '25', 'License': 'Y', 'Amount': '22.30'}, {'Name': 'Smith', 'Age': '38', 'License': 'Y', 'Amount': '52.20'}, {'Name': 'Stewart', 'Age': '21', 'License': 'N', 'Amount': '3.80'}]

Answer 2

This code does exactly what you want

from bs4 import BeautifulSoup
import json

xml_data = """
[[your xml data]]"""


if __name__ == '__main__':
    model = BeautifulSoup(xml_data, features='lxml')
    fields = []
    table_data = []
    for tr in model.table.find_all('tr', recursive=False):
        for th in tr.find_all('th', recursive=False):
            fields.append(th.text)
    for tr in model.table.find_all('tr', recursive=False):
        datum = {}
        for i, td in enumerate(tr.find_all('td', recursive=False)):
            datum[fields[i]] = td.text
        if datum:
            table_data.append(datum)

    print(json.dumps(table_data, indent=4))