extractdata.py
| 1 | from lxml import html |
| 2 | import requests |
| 3 | import json |
| 4 | |
| 5 | data = [] |
| 6 | |
| 7 | tplist = requests.get("https://translationproject.org/domain/index.html") |
| 8 | if(tplist.status_code == 200): |
| 9 | tree = html.fromstring(tplist.content) |
| 10 | domains = tree.xpath('//table/tr/td[1]/a/text()') |
| 11 | for d in domains: |
| 12 | data.append({"name": d, "system": 0}) |
| 13 | |
| 14 | transifexlist = { |
| 15 | 'openstreetmap': ['id-editor', 'osmybiz', 'openinghoursfragment', |
| 16 | 'presets', 'vespucci'], |
| 17 | } |
| 18 | for k in transifexlist: |
| 19 | for proj in transifexlist[k]: |
| 20 | data.append({'name': proj, 'system': 1, 'organisation': k}) |
| 21 | |
| 22 | with open('offlate/data.json', 'w') as f: |
| 23 | f.write(json.dumps(data)) |
| 24 |