Code to scrape data from a PDF

camp_participants.R

library(dplyr, warn.conflicts = FALSE)
library(tidyr)     
library(readr)     # For read_lines(), read_fwf(), etc.
library(stringr)   # For str_c(), str_detect()
library(pdftools)  # For pdf_text()
library(lubridate) # For ymd()
library(ggplot2)

url <- paste0("https://aaahq.org/portals/0/documents/meetings/2023/RC/",
              "2023%20Rookie%20Camp%20Alphabetical%20Presentation%20Schedule.pdf")

skip_rows <- 6

col_names <-  c("name", "school", "room", "start", 
                "end", "method", "interest", "area")

camp_data_raw <- 
  pdf_text(url) |> read_lines(skip = skip_rows) |>
  tibble(temp = _)

regex <- str_c("^",
               "(.*?)\\s{2,}",  
               "(.*?)\\s{2,}",
               "(Cityview [0-9])\\s+",
               "([0-9]{1,2}:[0-9]{2} [AP]M)\\s+",
               "([0-9]{1,2}:[0-9]{2} [AP]M)\\s+",
               "(.*?)\\s{2,}",
               "(.*?)\\s{2,}",
               "(.*)$")

camp_data <-
  camp_data_raw |> 
  extract(temp, col_names, regex) 

camp_data

camp_data |> count()

camp_data |> count(school, sort = TRUE)

camp_data |>
  ggplot(aes(x = method, fill = method)) +
  geom_bar()

camp_data |>
  ggplot(aes(x = area, fill = area)) +
  geom_bar()

camp_data |>
  ggplot(aes(x = interest, fill = interest)) +
  geom_bar()