Scrape American Presidency Project Approval Data

scrape-tidy-presidency-project-approval-data.R

library(rvest)
library(lubridate)
library(tidyverse)

Truman <- read_html("http://www.presidency.ucsb.edu/data/popularity.php?pres=33")

Truman %>%
  html_table(fill=T) -> Truman

Truman[[11]] -> Truman

Truman %>%
  select(X1:X3, X5:X7) %>%
  slice(7:n()) -> Truman


for (i in 34:45) {
  url <- paste0("http://www.presidency.ucsb.edu/data/popularity.php?pres=",i)
  url %>%
    read_html() %>%
    html_table(fill=TRUE) -> holdme
  holdme[[11]] -> holdme
  holdme %>%
    select(X1:X3, X5:X7) %>%
    slice(7:n()) -> holdme
  Truman <- rbind(Truman, holdme)
}

Truman %>%
  setNames(., c("potus", "stdate", "enddate", "approve", "disapprove", "unsure")) %>%
  mutate(stdate = mdy(stdate),
         enddate = mdy(enddate),
         potus = ifelse(potus == "", NA, potus),
         approve = as.integer(approve),
         disapprove = as.integer(disapprove),
         unsure = as.integer(unsure),
         netapprove = approve - disapprove) %>%
  tidyr::fill(potus) %>% arrange(stdate) -> Approval



write_csv(Approval, "potus-approval.csv")