jbothma

# python scrape_wikipedia.py countries.json intros flags
#
# countries.json is countries search facet.

import requests
from lxml import html
import json
from sys import argv
import re
from normality.cleaning import collapse_spaces

jbothma

{"countries":{"us":{"positions":{"plural-3dd261998008c07e480fd7b0c70d73321d64dd20":{"id":"plural-3dd261998008c07e480fd7b0c70d73321d64dd20","name":"Member of the New Jersey Senate","categories":[],"topics":[],"counts":{"total":52,"current":40,"ended":12,"unknown":0}},"Q13218630":{"id":"Q13218630","name":"United States representative","categories":[],"topics":[],"counts":{"total":1200,"current":426,"ended":356,"unknown":418}},"plural-7522a42ade1387949ba0195e68636df4f7f010b0":{"id":"plural-7522a42ade1387949ba0195e68636df4f7f010b0","name":"Governor of Nebraska","categories":[],"topics":[],"counts":{"total":1,"current":0,"ended":1,"unknown":0}},"us-congress-d50d35cd1e6958979e846398314ffa63f0b6760c":{"id":"us-congress-d50d35cd1e6958979e846398314ffa63f0b6760c","name":"United States senator","categories":[],"topics":[],"counts":{"total":122,"current":100,"ended":22,"unknown":0}},"plural-8c7da9224053deecd023a2962fd131393e6220fd":{"id":"plural-8c7da9224053deecd023a2962fd131393e6220fd","name":"Member of the California S

jbothma

{
  "ocid": "ocds-0E7232F7-67EC-42BD-B081-3370171F20B7",
  "id": "ocds-0E7232F7-67EC-42BD-B081-3370171F20B7-2022-03-30 13:40:05.8245389",
  "date": "2022-03-30T13:40:05",
  "initiationType": "tender",
  "tender": {
    "id": "3622",
    "title": "LMN 03/2021",
    "status": "active",
    "mainProcurementCategory": "Administrative and support activities",

jbothma

{
  "countries": {
    "af": {
      "positions": {
        "us-cia-b1efcaa124e747b3612a9e4191f58ecef8d4f0e2": {
          "position_name": "Deputy Prime Minister",
          "counts": {
            "total": 3,
            "current": 3,
            "ended": 0,

jbothma

{
  "$schema": "https://vega.github.io/schema/vega/v5.json",
  "description": "A basic grouped bar chart example.",
  "width": 300,
  "height": 240,
  "padding": 5,
  "data": [
    {
      "name": "table",
      "values": [

jbothma

API data practice tasks

This task will give you practice

• making sense of an unfamiliar API using its documentation
• handling, transforming and combining data, and coming up with data structures that enable you to present it easily
• dealing with interdependent API responses that complete in an arbitrary order, and ideally presenting progressively more information to the user as more data becomes available

Focus on logic and clean understandable code rather than visual design.

jbothma

Every country probably has its own chart of accounts.

Most of the south african chart doesn't fit in the open fiscal data package standard.

Sometimes you want to impose an ordering on items in a summary. Often the account numbering isn't the correct ordering for long. On muni money we captured that ordering alongside the codes and dimensions.

jbothma

https://docs.google.com/presentation/d/1tWw1N-LB6FYrHfXs9jM0P0x8ajMQgk53ESMCCpbSaAE/edit?usp=sharing

jbothma

[
  {
    "question_id": "surname",
    "answer": [
      {
        "language": "en",
        "value": "Bothma"
      },
      {
        "language": "fr",

jbothma

select p.family_name as "Apellido",
       p.given_name as "Nombre",
       p.gender as "sexo",
       '' as "cargoTipo",
       '' as "cargoClase",
       m.role as "cargoNominal", 
       o.name as "Organizacion", 
       '' as "parentOrg",
       '' as "duracionCargo",
       a.name as territorio,