#install.packages('rvest')
library('rvest')
library(tidyverse)
## -- Attaching packages --------------------------------------- tidyverse 1.3.1 --
## v ggplot2 3.3.5 v purrr 0.3.4
## v tibble 3.1.4 v dplyr 1.0.7
## v tidyr 1.1.3 v stringr 1.4.0
## v readr 2.0.1 v forcats 0.5.1
## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x readr::guess_encoding() masks rvest::guess_encoding()
## x dplyr::lag() masks stats::lag()
library(dplyr)
library(plotly)
##
## Attaching package: 'plotly'
## The following object is masked from 'package:ggplot2':
##
## last_plot
## The following object is masked from 'package:stats':
##
## filter
## The following object is masked from 'package:graphics':
##
## layout
library(scales)
##
## Attaching package: 'scales'
## The following object is masked from 'package:purrr':
##
## discard
## The following object is masked from 'package:readr':
##
## col_factor
library(highcharter)
## Registered S3 method overwritten by 'quantmod':
## method from
## as.zoo.data.frame zoo
library(RColorBrewer)
#Specifying the url for desired website to be scraped
url <- 'http://www.imdb.com/search/title?count=100&release_date=2016,2016&title_type=feature'
#Reading the HTML code from the website
webpage <- read_html(url)
#Using CSS selectors to scrape the rankings section
rank_data_html <- html_nodes(webpage,'.text-primary')
#Converting the ranking data to text
rank_data <- html_text(rank_data_html)
#Let's have a look at the rankings
head(rank_data)
## [1] "1." "2." "3." "4." "5." "6."
#Data-Preprocessing: Converting rankings to numerical
rank_data<-as.numeric(rank_data)
#Let's have another look at the rankings
head(rank_data)
## [1] 1 2 3 4 5 6
#Using CSS selectors to scrape the title section
title_data_html <- html_nodes(webpage,'.lister-item-header a')
#Converting the title data to text
title_data <- html_text(title_data_html)
#Let's have a look at the title
head(title_data)
## [1] "Nocturnal Animals" "Train to Busan" "Arrival"
## [4] "Suicide Squad" "Deadpool" "Hush"
#Using CSS selectors to scrape the description section
description_data_html <- html_nodes(webpage,'.ratings-bar+ .text-muted')
#Converting the description data to text
description_data <- html_text(description_data_html)
#Let's have a look at the description data
head(description_data)
## [1] "\nA wealthy art gallery owner is haunted by her ex-husband's novel, a violent thriller she interprets as a symbolic revenge tale."
## [2] "\nWhile a zombie virus breaks out in South Korea, passengers struggle to survive on the train from Seoul to Busan."
## [3] "\nA linguist works with the military to communicate with alien lifeforms after twelve mysterious spacecraft appear around the world."
## [4] "\nA secret government agency recruits some of the most dangerous incarcerated super-villains to form a defensive task force. Their first mission: save the world from the apocalypse."
## [5] "\nA wisecracking mercenary gets experimented on and becomes immortal but ugly, and sets out to track down the man who ruined his looks."
## [6] "\nA deaf and mute writer who retreated into the woods to live a solitary life must fight for her life in silence when a masked killer appears at her window."
#Data-Preprocessing: removing '\n'
description_data<-gsub("\n","",description_data)
#Let's have another look at the description data
head(description_data)
## [1] "A wealthy art gallery owner is haunted by her ex-husband's novel, a violent thriller she interprets as a symbolic revenge tale."
## [2] "While a zombie virus breaks out in South Korea, passengers struggle to survive on the train from Seoul to Busan."
## [3] "A linguist works with the military to communicate with alien lifeforms after twelve mysterious spacecraft appear around the world."
## [4] "A secret government agency recruits some of the most dangerous incarcerated super-villains to form a defensive task force. Their first mission: save the world from the apocalypse."
## [5] "A wisecracking mercenary gets experimented on and becomes immortal but ugly, and sets out to track down the man who ruined his looks."
## [6] "A deaf and mute writer who retreated into the woods to live a solitary life must fight for her life in silence when a masked killer appears at her window."
#Using CSS selectors to scrape the Movie runtime section
runtime_data_html <- html_nodes(webpage,'.text-muted .runtime')
#Converting the runtime data to text
runtime_data <- html_text(runtime_data_html)
#Let's have a look at the runtime
head(runtime_data)
## [1] "116 min" "118 min" "116 min" "123 min" "108 min" "82 min"
#Data-Preprocessing: removing mins and converting it to numerical
runtime_data<-gsub(" min","",runtime_data)
runtime_data<-as.numeric(runtime_data)
#Let's have another look at the runtime data
head(runtime_data)
## [1] 116 118 116 123 108 82
#Using CSS selectors to scrape the Movie genre section
genre_data_html <- html_nodes(webpage,'.genre')
#Converting the genre data to text
genre_data <- html_text(genre_data_html)
#Let's have a look at the runtime
head(genre_data)
## [1] "\nDrama, Thriller "
## [2] "\nAction, Horror, Thriller "
## [3] "\nDrama, Sci-Fi "
## [4] "\nAction, Adventure, Fantasy "
## [5] "\nAction, Adventure, Comedy "
## [6] "\nHorror, Thriller "
#Data-Preprocessing: removing \n
genre_data<-gsub("\n","",genre_data)
#Data-Preprocessing: removing excess spaces
genre_data<-gsub(" ","",genre_data)
#taking only the first genre of each movie
genre_data<-gsub(",.*","",genre_data)
#Convering each genre from text to factor
genre_data<-as.factor(genre_data)
#Let's have another look at the genre data
head(genre_data)
## [1] Drama Action Drama Action Action Horror
## Levels: Action Adventure Animation Biography Comedy Crime Drama Horror
#Using CSS selectors to scrape the IMDB rating section
rating_data_html <- html_nodes(webpage,'.ratings-imdb-rating strong')
#Converting the ratings data to text
rating_data <- html_text(rating_data_html)
#Let's have a look at the ratings
head(rating_data)
## [1] "7.5" "7.6" "7.9" "5.9" "8.0" "6.6"
#Data-Preprocessing: converting ratings to numerical
rating_data<-as.numeric(rating_data)
#Let's have another look at the ratings data
head(rating_data)
## [1] 7.5 7.6 7.9 5.9 8.0 6.6
#Using CSS selectors to scrape the votes section
votes_data_html <- html_nodes(webpage,'.sort-num_votes-visible span:nth-child(2)')
#Converting the votes data to text
votes_data <- html_text(votes_data_html)
#Let's have a look at the votes data
head(votes_data)
## [1] "254,744" "192,162" "640,355" "654,312" "954,445" "118,602"
#Data-Preprocessing: removing commas
votes_data<-gsub(",","",votes_data)
#Data-Preprocessing: converting votes to numerical
votes_data<-as.numeric(votes_data)
#Let's have another look at the votes data
head(votes_data)
## [1] 254744 192162 640355 654312 954445 118602
#Using CSS selectors to scrape the directors section
directors_data_html <- html_nodes(webpage,'.text-muted+ p a:nth-child(1)')
#Converting the directors data to text
directors_data <- html_text(directors_data_html)
#Let's have a look at the directors data
head(directors_data)
## [1] "Tom Ford" "Sang-ho Yeon" "Denis Villeneuve" "David Ayer"
## [5] "Tim Miller" "Mike Flanagan"
#Data-Preprocessing: converting directors data into factors
directors_data<-as.factor(directors_data)
#Using CSS selectors to scrape the actors section
actors_data_html <- html_nodes(webpage,'.lister-item-content .ghost+ a')
#Converting the gross actors data to text
actors_data <- html_text(actors_data_html)
#Let's have a look at the actors data
head(actors_data)
## [1] "Amy Adams" "Gong Yoo" "Amy Adams"
## [4] "Will Smith" "Ryan Reynolds" "John Gallagher Jr."
ratings_bar_data <- html_nodes(webpage,'.ratings-bar') %>%
# scrape the ratings bar and convert to text
html_text2()
head(ratings_bar_data) # look at the ratings bar
## [1] "7.5\nRate this\n 1 2 3 4 5 6 7 8 9 10 7.5/10 X \n67 Metascore"
## [2] "7.6\nRate this\n 1 2 3 4 5 6 7 8 9 10 7.6/10 X \n72 Metascore"
## [3] "7.9\nRate this\n 1 2 3 4 5 6 7 8 9 10 7.9/10 X \n81 Metascore"
## [4] "5.9\nRate this\n 1 2 3 4 5 6 7 8 9 10 5.9/10 X \n40 Metascore"
## [5] "8.0\nRate this\n 1 2 3 4 5 6 7 8 9 10 8/10 X \n65 Metascore"
## [6] "6.6\nRate this\n 1 2 3 4 5 6 7 8 9 10 6.6/10 X \n67 Metascore"
metascore_data <- str_match(ratings_bar_data, "\\d{2} Metascore") %>%
# extract Metascore
str_match("\\d{2}") %>%
as.numeric() # convert to number
length(metascore_data)
## [1] 100
metascore_data
## [1] 67 72 81 40 65 67 81 65 71 71 72 62 60 81 48 84 44 94 79 75 65 72 51 54 52
## [26] 78 66 25 82 74 70 35 76 51 81 49 57 74 58 51 48 65 41 65 59 NA 68 99 96 44
## [51] 57 62 42 NA 64 42 35 58 88 78 32 81 66 42 42 46 79 69 65 32 58 33 77 47 23
## [76] NA 59 64 52 68 78 77 68 49 61 36 70 76 66 33 65 18 58 NA 40 80 60 55 44 55
summary(metascore_data)
## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 18.00 48.75 64.00 60.78 72.50 99.00 4
# scrape the votess bar and convert to text
votes_bar_data <- html_nodes(webpage,'.sort-num_votes-visible') %>%
html_text2()
head(votes_bar_data) # look at the votes bar data
## [1] "Votes: 254,744 | Gross: $10.64M" "Votes: 192,162 | Gross: $2.13M"
## [3] "Votes: 640,355 | Gross: $100.55M" "Votes: 654,312 | Gross: $325.10M"
## [5] "Votes: 954,445 | Gross: $363.07M" "Votes: 118,602"
gross_data <- str_match(votes_bar_data, "\\$.+$") # extract the gross earnings
gross_data <- gsub("M","",gross_data) # clean data: remove 'M' sign
gross_data <- substring(gross_data,2,6) %>% # clean data: remove '$' sign
as.numeric()
length(gross_data)
## [1] 100
#Combining all the lists to form a data frame
movies_df<-data.frame(Rank = rank_data, Title = title_data,
Description = description_data, Runtime = runtime_data,
Genre = genre_data, Rating = rating_data,
Metascore = metascore_data, Votes = votes_data, Gross_Earning_in_Mil = gross_data,
Director = directors_data, Actor = actors_data)
#Structure of the data frame
str(movies_df)
## 'data.frame': 100 obs. of 11 variables:
## $ Rank : num 1 2 3 4 5 6 7 8 9 10 ...
## $ Title : chr "Nocturnal Animals" "Train to Busan" "Arrival" "Suicide Squad" ...
## $ Description : chr "A wealthy art gallery owner is haunted by her ex-husband's novel, a violent thriller she interprets as a symbol"| __truncated__ "While a zombie virus breaks out in South Korea, passengers struggle to survive on the train from Seoul to Busan." "A linguist works with the military to communicate with alien lifeforms after twelve mysterious spacecraft appea"| __truncated__ "A secret government agency recruits some of the most dangerous incarcerated super-villains to form a defensive "| __truncated__ ...
## $ Runtime : num 116 118 116 123 108 82 99 134 88 139 ...
## $ Genre : Factor w/ 8 levels "Action","Adventure",..: 7 1 7 1 1 8 7 8 6 4 ...
## $ Rating : num 7.5 7.6 7.9 5.9 8 6.6 7 7.3 7.1 8.1 ...
## $ Metascore : num 67 72 81 40 65 67 81 65 71 71 ...
## $ Votes : num 254744 192162 640355 654312 954445 ...
## $ Gross_Earning_in_Mil: num 10.64 2.13 100.5 325.1 363 ...
## $ Director : Factor w/ 97 levels "Aisling Walsh",..: 94 84 27 23 92 60 49 42 31 58 ...
## $ Actor : chr "Amy Adams" "Gong Yoo" "Amy Adams" "Will Smith" ...
#Create First Visualization
qplot(data = movies_df,Runtime,fill = Genre,bins = 30)
movies_df %>%
select(Title, Genre, Runtime)%>%
filter(Runtime > 150)
## Title Genre Runtime
## 1 Batman v Superman: Dawn of Justice Action 152
## 2 The Wailing Horror 156
## 3 Silence Drama 161
## 4 Dangal Action 161
## 5 American Honey Adventure 163
ggplot(movies_df,aes(x=Runtime,y=Rating))+
geom_point(aes(size=Votes,col=Genre))
intmoviedf <- movies_df %>%
filter(Runtime >= 130 & Runtime <= 160) %>%
ggplot(aes(Runtime,Rating, colour=Genre))+
geom_point(aes(size=Votes, col=Genre))+
scale_color_discrete(name = " ")+
labs(x="Runtime", y="Rating", size="Genre: Sized by Qty of Votes")
intmoviedf <- ggplotly(intmoviedf)
intmoviedf
ggplot(movies_df,aes(x=Runtime,y=Gross_Earning_in_Mil))+
geom_point(aes(size=Rating,col=Genre))
## Warning: Removed 11 rows containing missing values (geom_point).
gen100_120 <- movies_df %>%
select(Genre, Runtime, Rating, Gross_Earning_in_Mil)%>%
filter(Runtime>=100 & Runtime <=120)%>%
arrange(Runtime)
cols <- brewer.pal(8, "Dark2")
highchart() %>%
hc_add_series(data = gen100_120, type = "bubble",
hcaes(x=Runtime,y=Gross_Earning_in_Mil, group= Genre))%>%
hc_colors(cols)%>%
hc_title(text="Gross Earnings")%>%
hc_xAxis(title=list(text="Runtime" ))%>%
hc_yAxis(title=list(text="Gross Earning in Millions"))%>%
hc_legend(align = "right", verticalAlign="top")%>%
hc_tooltip(shared=TRUE, borderColor = "black", pointFormat="{point.y}")