scrapes and visualizes ratings for Futurama from IMDB

futurama.py

import requests
from bs4 import BeautifulSoup
from pandas import DataFrame

url = 'http://www.imdb.com/title/tt0149460/eprate?ref_=ttep_sa_2'
soup = BeautifulSoup(requests.get(url).content)


def parse_table(soup, df):
    table = soup.find("table")
    for row in table.find_all("tr")[1:]:
        data = list(row.find_all("td"))
        for i in range(len(data)):
            data[i] = data[i].get_text(strip=True)
        df.append(data)
    return df


table = parse_table(soup, [])
df = DataFrame(table, columns=['episode', 'title', 'rating', 'votes', ''])
df = df.drop('', 1)
df.to_csv('futurama.csv', na_rep="NA", index=False, encoding="utf-8")

futurama.R

require(ggplot2)
require(plyr)

df <- read.csv("futurama.csv", colClasses = "character")
df[, c("season", "episode")] <- ldply(strsplit(as.character(df$episode), ".", fixed = TRUE))
ind <- by(df, list(df$season), function(x) {
  x <- x[order(as.integer(x$episode)), ]
  row.names(x)
})
df$title <- factor(df$title, levels = df$title[as.integer(unlist(ind))])
df$title <- factor(df$title, levels = rev(levels(df$title)))

p <- ggplot(df, aes(x = as.numeric(rating), y = title, colour = season))
p <- p + geom_point()
p <- p + labs(x = "user rating", y = "episode title", title = "Futurama Ratings via IMDB")
ggsave("futurama.png", height = 14, width = 6)