scrape.R

rm(list=ls())

########################
# Web Scraping
# @jorandradefig
########################

# instalar paquete
install.packages("rvest")

# cargar paquete
library("rvest")

# guardar la url
url <- 'http://www.imdb.com/search/title?count=100&release_date=2016,2016&title_type=feature'

# guardar el html de la url
webpage <- read_html(url)

# ranking

# extraer los nodos que tienen la clase text-primary
rank_data_html <- html_nodes(webpage, '.text-primary')

# extraer el texto
rank_data <- html_text(rank_data_html)

# imprimir los primeros valores
head(rank_data)

# convertir a numérico
rank_data <- as.numeric(rank_data)

# imprimir los primeros valores
head(rank_data)

# títulos

title_data_html <- html_nodes(webpage, '.lister-item-header a')

title_data <- html_text(title_data_html)

head(title_data)

########################################
# clasificaciones

########################################

# ganancias

gross_data_html <- html_nodes(webpage,'.ghost~ .text-muted+ span')

gross_data <- html_text(gross_data_html)

head(gross_data)

gross_data <- gsub("M", "", gross_data)

gross_data <- gsub(",", "", gross_data)

gross_data <- substring(gross_data, 2, 6)

head(gross_data)

rank_data <- rank_data[c(-91:-100)]
title_data <- title_data[c(-91:-100)]

install.packages("rlist")
library("rlist")

rank_data <- list.reverse(rank_data)

length(rank_data)
length(gross_data)
length(title_data)

movies <- data.frame(Rank = rank_data, Title = title_data, Gross = gross_data)

movies

install.packages('ggplot2')

library(ggplot2)

qplot(movies$Rank, geom="histogram", binwidth = 5, fill=I("blue"))

ggplot(movies, aes(Rank, Gross, colour = I("blue"), label = Title)) +
    geom_point() +
    guides(fill=FALSE, color=FALSE) +
    geom_text()