varas_corporativo.R

gistfile1.txt

# Endpoint for SOAP requests
endpoint_url <- 'https://www.cnj.jus.br/corregedoria/justica_aberta/ws.php'

# XML payload, replace the method name and parameters as per actual API
# This is a simplified example assuming a SOAP method called 'getServentiaJudicial' that accepts 'seq_orgao' as a parameter
xml_payload <- '<soapenv:Envelope xmlns:soapenv="http://schemas.xmlsoap.org/soap/envelope/" xmlns:cor="https://www.cnj.jus.br/corregedoria/justica_aberta/ws.php">
   <soapenv:Header/>
   <soapenv:Body>
      <cor:pesquisarServentiasJudiciais>
         <!--Optional:-->
         <cor:seq_orgao></cor:seq_orgao>
         <!--Optional:-->
         <cor:dat_inicio>01/01/2000</cor:dat_inicio>
         <!--Optional:-->
         <cor:dat_fim></cor:dat_fim>
      </cor:pesquisarServentiasJudiciais>
   </soapenv:Body>
</soapenv:Envelope>'

# HTTP headers
headers <- httr::add_headers(
  'Content-Type' = 'text/xml',
  'SOAPAction' = 'https://www.cnj.jus.br/corregedoria/justica_aberta/ws.php/pesquisarServentiasJudiciaisIn'
)

# Making the request
r <- httr::POST(
  endpoint_url, body = xml_payload, headers,
  httr::write_disk("data-raw/xml_varas_cnj.xml")
)

# Function to extract the text or return NA if the node doesn't exist
extract_text_or_na <- function(node, xpath) {
  found_node <- xml2::xml_find_first(node, xpath)
  if (is.null(found_node)) return(NA)
  xml2::xml_text(found_node)
}

# Function to extract information from a single 'item' node
extract_item_to_df_row <- function(item) {
  tibble::tibble(
    seq_orgao = as.integer(extract_text_or_na(item, ".//seq_orgao")),
    dsc_orgao = extract_text_or_na(item, ".//dsc_orgao"),
    tip_orgao = extract_text_or_na(item, ".//tip_orgao"),
    seq_orgao_pai = as.integer(extract_text_or_na(item, ".//seq_orgao_pai")),
    seq_tribunal_pai = as.integer(extract_text_or_na(item, ".//seq_tribunal_pai")),
    cod_hierarquia = extract_text_or_na(item, ".//cod_hierarquia"),
    seq_cidade = as.integer(extract_text_or_na(item, ".//seq_cidade")),
    sig_uf = extract_text_or_na(item, ".//sig_uf"),
    dsc_cidade = extract_text_or_na(item, ".//dsc_cidade"),
    cod_ibge = extract_text_or_na(item, ".//cod_ibge"),
    flg_ativo = extract_text_or_na(item, ".//flg_ativo"),
    cep_serventia = is.na(extract_text_or_na(item, ".//cep_serventia")),
    endereco_serventia = is.na(extract_text_or_na(item, ".//endereco_serventia")),
    telefone_serventia = is.na(extract_text_or_na(item, ".//telefone_serventia")),
    dat_alteracao = extract_text_or_na(item, ".//dat_alteracao"),
    dsc_email_secretaria = extract_text_or_na(item, ".//dsc_email_secretaria")
  )
}

safe <- purrr::possibly(extract_item_to_df_row, tibble::tibble(erro = "erro"))

# Find the 'item' nodes and get the text content
future::plan(future::multicore, workers = 8)
aux_varas_corporativo <- r |>
  xml2::read_xml() |>
  xml2::xml_find_all(".//item") |>
  furrr::future_map(safe, .progress = TRUE) |>
  purrr::list_rbind()

readr::write_rds(aux_varas_corporativo, "data-raw/aux_varas_corporativo.rds")