Scrape crime data from São Paulo State's Institute

ssp_scraper.R

library(rvest)
ssp_url = 'http://www.ssp.sp.gov.br/estatistica/pesquisa.aspx'

## get the region/municipality form
sess = html_session(ssp_url)
form = html_form(sess)[[2]]
## see form options
head(form$fields$`ctl00$conteudo$ddlRegioes`$options)
head(form$fields$`ctl00$conteudo$ddlMunicipios`$options)
## submit the form to get a new page
form = form %>% set_values('ctl00$conteudo$ddlRegioes' = 3)
sess = submit_form(sess, form)
sess %>%
  html_node("#conteudo_repAnos_gridDados_0") %>%
  html_table() %>%
  head()

ssp_scraper_output.txt

R version 3.6.1 (2019-07-05) -- "Action of the Toes"
Copyright (C) 2019 The R Foundation for Statistical Computing
Platform: x86_64-pc-linux-gnu (64-bit)

R is free software and comes with ABSOLUTELY NO WARRANTY.
You are welcome to redistribute it under certain conditions.
Type 'license()' or 'licence()' for distribution details.

  Natural language support but running in an English locale

R is a collaborative project with many contributors.
Type 'contributors()' for more information and
'citation()' on how to cite R or R packages in publications.

Type 'demo()' for some demos, 'help()' for on-line help, or
'help.start()' for an HTML browser interface to help.
Type 'q()' to quit R.

> library(rvest)
Loading required package: xml2
> ssp_url = 'http://www.ssp.sp.gov.br/estatistica/pesquisa.aspx'
> 
> ## get the region/municipality form
> sess = html_session(ssp_url)
> form = html_form(sess)[[2]]
> ## see form options
> head(form$fields$`ctl00$conteudo$ddlRegioes`$options)
                              Todos                             Capital 
                                "0"                                 "1" 
Grande São Paulo (exclui a Capital)                 São José dos Campos 
                                "2"                                 "3" 
                           Campinas                      Ribeirão Preto 
                                "4"                                 "5" 
> head(form$fields$`ctl00$conteudo$ddlMunicipios`$options)
           Todos       Adamantina           Adolfo            Aguaí 
             "0"              "1"              "2"              "3" 
  Águas da Prata Águas de Lindóia 
             "4"              "5" 
> ## submit the form to get a new page
> form = form %>% set_values('ctl00$conteudo$ddlRegioes' = 3)
> sess = submit_form(sess, form)
Submitting with 'ctl00$conteudo$btnExcel'
> sess %>%
+   html_node("#conteudo_repAnos_gridDados_0") %>%
+   html_table() %>%
+   head()
                                      Natureza Jan Fev Mar Abr Mai Jun Jul Ago
1        OCORRÊNCIAS DE PORTE DE ENTORPECENTES 110  89  69  76  87  60  91  89
2      OCORRÊNCIAS DE TRÁFICO DE ENTORPECENTES 247 249 228 211 242 240 258 309
3 OCORRÊNCIAS DE APREENSÃO DE ENTORPECENTES(1)  11  11  18  10  13  12  16  22
4          OCORRÊNCIAS DE PORTE ILEGAL DE ARMA  43  43  44  59  55  35  40  53
5              Nº DE ARMAS DE FOGO APREENDIDAS 101  90 100  90 102  89  79 109
6                    Nº DE FLAGRANTES LAVRADOS 542 461 476 465 497 442 503 482
  Set Out Nov Dez   Total
1  94 ... ... ... 765.000
2 244 ... ... ...   2.228
3  18 ... ... ... 131.000
4  51 ... ... ... 423.000
5  93 ... ... ... 853.000
6 474 ... ... ...   4.342
>