from lxml import html import requests import json data = [] tplist = requests.get("https://translationproject.org/domain/index.html") if(tplist.status_code == 200): tree = html.fromstring(tplist.content) domains = tree.xpath('//table/tr/td[1]/a/text()') for d in domains: data.append({"name": d, "system": 0}) transifexlist = { 'openstreetmap': ['id-editor', 'osmybiz', 'openinghoursfragment', 'presets', 'vespucci'], } for k in transifexlist: for proj in transifexlist[k]: data.append({'name': proj, 'system': 1, 'organisation': k}) with open('offlate/data.json', 'w') as f: f.write(json.dumps(data))