prep-otter-transcript.R

prep-otter-transcript.R

library(tidyverse)
library(googlesheets4)

# this is an example Google Sheet
d <- read_sheet("https://docs.google.com/spreadsheets/d/1kz2LlLgXkN_HaBEAiFETl59b09u9AwMIgrwQx6DCv8A/edit#gid=0", col_names = FALSE)

prep_otter_transcript <- function(d, length_less_than_100_min) {

  d <- d %>% rename(x1 = 1)

  d2 <- d %>% slice(-nrow(d))

  d3 <- d2 %>%
    filter(!is.na(x1)) %>%
    mutate(text = lead(x1)) %>%
    mutate(to_filter = rep(c(TRUE, FALSE), nrow(.)/2)) %>%
    filter(to_filter)

  if (length_less_than_100_min) {
    d3 %>%
      mutate(time = str_sub(x1, start = -5)) %>%
      mutate(speaker = str_sub(x1, end = -5)) %>%
      select(time, speaker, text) %>%
      mutate_all(str_trim)
  } else {
    d3 %>%
      mutate(time = str_sub(x1, start = -6)) %>%
      mutate(speaker = str_sub(x1, end = -6)) %>%
      select(time, speaker, text) %>%
      mutate_all(str_trim)
  }

}

prep_otter_transcript(d)