Created
August 23, 2018 19:43
-
-
Save imjakedaniels/57ee17ba0bf5e4b322d6a1e6610aa87d to your computer and use it in GitHub Desktop.
Arie sucks maybe?
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
library(rvest) | |
library(tidyverse) | |
library(magrittr) | |
library(scales) | |
library(knitr) | |
library(lubridate) | |
url <- "https://www.imdb.com/title/tt0313038/episodes?season=" | |
timevalues <- 13:22 | |
unitedata <- function(x){ | |
full_url <- paste0(url, x) | |
full_url | |
} | |
finalurl <- unitedata(timevalues) | |
finalurl | |
imdbScrape <- function(x){ | |
page <- x | |
name <- page %>% read_html() %>% html_nodes('#episodes_content strong a') %>% html_text() %>% as.data.frame() | |
rating <- page %>% read_html() %>% html_nodes('.ipl-rating-widget') %>% html_text() %>% as.data.frame() | |
details <- page %>% read_html() %>% html_nodes('.zero-z-index div') %>% html_text() %>% as.data.frame() | |
chart <- cbind(name, rating, details) | |
names(chart) <- c("Name", "Rating", "Details") | |
chart <- as.tibble(chart) | |
return(chart) | |
Sys.sleep(5) | |
} | |
bachelor <- map_df(finalurl, imdbScrape) | |
bachelor$Season <- str_extract(bachelor$Details, "S[0-9]+") | |
bachelor$Season <- as.numeric(str_extract(bachelor$Season, "[0-9]+")) | |
bachelor$Episode <- str_extract(bachelor$Details, "Ep[0-9]+") | |
bachelor$Episode <- as.numeric(str_extract(bachelor$Episode, "[0-9]+")) | |
bachelor$Details <- NULL | |
bachelor$Rating <- str_extract(bachelor$Rating, "[0-9].[0-9]") | |
na_index <- which(!is.na(bachelor$Rating)) | |
bachelor <- bachelor[na_index,] | |
bachelor$Rating <- as.numeric(bachelor$Rating) | |
bachelor_names <- c('Jason', 'Jake', 'Brad', 'Ben', 'Sean', 'Juan-Pablo', 'Chris', 'Ben', 'Nick', 'Arie') | |
bachelor %>% | |
group_by(Season) %>% | |
summarise(Rating = mean(Rating)) %>% | |
ggplot() + | |
geom_line(aes(x=Season, y=Rating), color = "Red", size = 1.1) + | |
scale_x_continuous(breaks=c(13:22), labels=bachelor_names, limits=c(13,22)) + | |
scale_y_continuous(breaks=c(1:10), labels=c(1:10), limits=c(1,10)) + | |
geom_line(aes(x=Season, y=mean(Rating)), linetype=2, color = "Black") + | |
annotate("text", x=27, y= 7.45, label = "avg", color = "black", size = 3) + | |
theme_bw() + | |
labs(title = "Is Arie the Worst Bachelor in Show History?", | |
subtitle = "Average Episode Ratings by Season", | |
caption = "Source: IMDB, August 2018", | |
x = "Seasons 13-22", | |
y = "Rating") + | |
theme(plot.title = element_text(family='', face = 'bold', colour = 'black', size = 20), | |
plot.subtitle = element_text(family='', face = 'italic', colour = 'black', size = 10), | |
plot.caption = element_text(family='', colour = 'black', size = 10), | |
axis.title.x = element_text(family='', face = 'bold', colour = 'black', size = 12), | |
axis.title.y = element_text(family='', colour = 'black', size = 12), | |
plot.background = element_rect(fill = "white")) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Since there were NA, i made the scrape for the rating less narrow so I still got a result for each row then extracted just the ranking out and dropped the ones with NA
You're not gonna like the results for Arie though.....