scraper do Tribunal de Justiça do Rio Grande do Sul

tjrsSG_meta.R

library(httr)
library(xml2)
library(stringr)
library(boilerpipeR)

tjrsSG_meta<-function(BuscaLivre="",quote=TRUE){
  
  if(quote==TRUE) BuscaLivre<-deparse(BuscaLivre)
  
  url<-"http://www.tjrs.jus.br/busca/search?"
  
  query<-list(q = "", proxystylesheet = "tjrs_index", getfields = "*", 
              entsp = "a__politica-site", wc = "200", wc_mc = "1", oe = "UTF-8", 
              ie = "UTF-8", ud = "1", sort = "date:D:S:d1", as_qj = "", 
              as_epq = "", as_oq = "", as_eq = "", as_q = "", ulang = "en", 
              ip = "", access = "p", entqr = "3", entqrm = "0", client = "tjrs_index", 
              filter = "0", start = "0", aba = "juris", site = "juris")
  
  query[[1]]<-BuscaLivre
  query[[11]]<-BuscaLivre
  
  a<-url %>% 
    GET(query=query) %>% 
    content("parsed")
  
  num<-a %>% xml_find_all("//*[@class='clearfix left']/div/*[@class='bold'][3]") %>% 
    xml_text() %>% 
    as.numeric()
  
  url1<-a %>% xml_find_all("//*[@class='pagination-control']/a[1]/@href") %>%
    xml_text() %>% 
    .[1] %>% 
    paste0("http://www.tjrs.jus.br/busca/",.)
  
  df<-data.frame()
  
  for (i in seq(0,num,10)){
    tryCatch({
      
      url1<-str_replace(url1,"(?<=start\\=)\\d+",as.character(i))
      
      b<-GET(url1) %>% 
        content("parsed")
      
      processo<-xml_find_all(b,"//*[@class='featured font-size-12']") %>% xml_text()
      data.julgamento<-
      
      orgao.julgador<- xml_find_all(b,"//*[@class='larguraUltColuna']") %>%
        xml_text(trim=T) %>% 
        str_replace(".*(:\\s)","")
      
      classe.processual<-xml_find_all(b,"//*[@id='table_resultado']//tr[2]/td[1]") %>% 
        xml_text(trim=T) %>% 
        str_replace(".*(:\\s)","")
      
      secao<-xml_find_all(b,"//*[@id='table_resultado']//tr[3]/td[2]") %>% 
        xml_text(trim=T) %>% 
        str_replace(".*(:\\s)","")
      
      relator<-xml_find_all(b,"//*[@id='table_resultado']//tr[5]/td[1]") %>% 
        xml_text(trim=T) %>% 
        str_replace(".*(:\\s)","")
      
      comarca.origem <-xml_find_all(b,"//*[@id='table_resultado']//tr[2]/td[2]") %>% 
        xml_text(trim=T) %>% 
        str_replace(".*(:\\s)","")
      
      classe.material<-xml_find_all(b,"//*[@id='table_resultado']//tr[4]/td[2]") %>% 
        xml_text(trim=T) %>% 
        str_replace(".*(:\\s)","")
      
      ementa<-xml_find_all(b,"//*[@class='ementa']") %>% 
        xml_text(trim=T) %>% 
        str_replace(".*(:\\s)","")
      
      linkHtml<-xml_find_all(b,"//*[@class='larguraPrimColuna']//a[2]/@href") %>%
        xml_text() %>% 
        str_c("http://www.tjrs.jus.br/busca/",.) %>% 
        str_replace_all("\\s+","%20")
      
      df1<-data.frame(processo,orgao.julgador,relator, classe.processual,classe.material,secao,comarca.origem,ementa, pagina=i,linkHtml,stringsAsFactors = F)
      df<-rbind(df,df1)
      
    }, error=function(m){
      m
    }, finally={
      next
    })
    
  }
  return(df)
}




inteiroRS<-dfrs$linkHtml %>% 
  map(function(x){
  GET(x) %>%
  content("text") %>%
  DefaultExtractor()
})