# load packages
library(httr)
library(tidyverse)
library(stringr)
library(xml2)
library(viridis)
library(knitr)

# knitr options
opts_chunk$set(cache = TRUE, warning = FALSE, message = FALSE)

# API_KEY <- "XXXXXXXXXXXXX"
# GR_ID   <- "XXXXXXXXXXXXX"

URL <- "https://www.goodreads.com/review/list?"

get_shelf <- function(GR_ID) {
    shelf <- GET(URL, query = list(
    	v = 2, key = API_KEY, id = GR_ID, shelf = "read", per_page = 200))
    shelf_contents <- content(shelf, as = "parsed")
    return(shelf_contents)
}

shelf <- get_shelf(GR_ID)

get_df <- function(shelf) {

    title <- shelf %>% 
        xml_find_all("//title") %>% 
        xml_text()
    
    rating <- shelf %>% 
        xml_find_all("//rating") %>% 
        xml_text()
    
    added <- shelf %>% 
        xml_find_all("//date_added") %>% 
        xml_text()
    
    started <- shelf %>% 
        xml_find_all("//started_at") %>% 
        xml_text()
    
    read <- shelf %>% 
        xml_find_all("//read_at") %>% 
        xml_text()
    
    df <- tibble(
        title, rating, added, started, read)
    
    return(df)
}

df <- get_df(shelf)

get_books <- function(df) {

    books <- df %>% 
        gather(date_type, date, -title, -rating) %>% 
        separate(date, 
            into = c("weekday", "month", "day", "time", "zone", "year"), 
            sep = "\\s", fill = "right") %>% 
        mutate(date = str_c(year, "-", month, "-", day)) %>% 
        select(title, rating, date_type, date) %>% 
        mutate(date = as.Date(date, format = "%Y-%b-%d")) %>% 
        spread(date_type, date) %>% 
        mutate(title = str_replace(title, "\\:.*$|\\(.*$|\\-.*$", "")) %>% 
        mutate(started = ifelse(
        	is.na(started), as.character(added), as.character(started))) %>% 
        mutate(started = as.Date(started)) %>% 
        mutate(rating = as.integer(rating))
    
    return(books)
}

books <- get_books(df)