Before we scrape all of the Pokemon data, let’s start by building the table of just Pokemon and their number, again using the PokemonDB site.
¶Load Libraries
Again, we’ll primarily use the rvest package, along with dplyr and tidyr for some additional common functions.
# Load packages library(rvest) library(dplyr) library(tidyr)
¶Load National Pokedex Page
Let’s load the page data from the National Pokedex page, which has a table of all Pokemon, their number, and a link to their page.
# Set the URL to fetch data from url <- "https://pokemondb.net/pokedex/national" # Read the body from the page body <- url %>% read_html() %>% html_nodes("body") # Get the info cards for each Pokemon infocards <- html_nodes(body, "span.infocard-lg-data.text-muted")
¶Get the Initial Pokedex Data
Using the tags for each “infocard” which contains the information we want for each Pokemon, get the numbers, names, and URLs for each Pokemon.
# Fetch the Pokemon numbers numbers <- infocards %>% html_element("small") %>% html_text() # Fetch the Pokemon names names <- infocards %>% html_element("a") %>% html_text() # Fetch the Pokemon URLs urls <- infocards %>% html_element("a") %>% html_attr("href") urls <- paste0("https://pokemondb.net", urls)
¶Assemble Initial Pokedex Dataframe
Finally, let’s put all of this data into a dataframe.
# Create tibble for Pokedex data_tbl <- tibble(numbers, names, urls) %>% rename(Number = numbers, Name = names, URLs = urls) data_tbl$Number <- substring(data_tbl$Number, 2) %>% as.numeric() glimpse(data_tbl)
Rows: 1,010 Columns: 3 $ Number <dbl> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, … $ Name <chr> "Bulbasaur", "Ivysaur", "Venusaur", "Charmander", "Charmeleon",… $ URLs <chr> "https://pokemondb.net/pokedex/bulbasaur", "https://pokemondb.n…
This initial table will serve as the initial table for scraping all of the Pokemon data.