Week 9 Hw
Tiffany King
11/3/2020
#Loading the rvest package
library('rvest')## Loading required package: xml2#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] "Split" "Ghostbusters: Answer the Call"
## [3] "Suicide Squad" "Train to Busan"
## [5] "The Conjuring 2" "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] "\n Three girls are kidnapped by a man with a diagnosed 23 distinct personalities. They must try to escape before the apparent emergence of a frightful new 24th."
## [2] "\n Following a ghost invasion of Manhattan, paranormal enthusiasts Erin Gilbert and Abby Yates, nuclear engineer Jillian Holtzmann, and subway worker Patty Tolan band together to stop the otherworldly threat."
## [3] "\n 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."
## [4] "\n While a zombie virus breaks out in South Korea, passengers struggle to survive on the train from Seoul to Busan."
## [5] "\n Ed and Lorraine Warren travel to North London to help a single mother raising four children alone in a house plagued by a supernatural spirit."
## [6] "\n 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."#Data-Preprocessing: removing '\n'
description_data<-gsub("\n","",description_data)
#Let's have another look at the description data
head(description_data)## [1] " Three girls are kidnapped by a man with a diagnosed 23 distinct personalities. They must try to escape before the apparent emergence of a frightful new 24th."
## [2] " Following a ghost invasion of Manhattan, paranormal enthusiasts Erin Gilbert and Abby Yates, nuclear engineer Jillian Holtzmann, and subway worker Patty Tolan band together to stop the otherworldly threat."
## [3] " 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."
## [4] " While a zombie virus breaks out in South Korea, passengers struggle to survive on the train from Seoul to Busan."
## [5] " Ed and Lorraine Warren travel to North London to help a single mother raising four children alone in a house plagued by a supernatural spirit."
## [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] "117 min" "117 min" "123 min" "118 min" "134 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] 117 117 123 118 134 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] "\nHorror, Thriller "
## [2] "\nAction, Comedy, Fantasy "
## [3] "\nAction, Adventure, Fantasy "
## [4] "\nAction, Horror, Thriller "
## [5] "\nHorror, Mystery, Thriller "
## [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] Horror Action Action Action Horror 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] "7.3" "6.5" "6.0" "7.6" "7.3" "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] 7.3 6.5 6.0 7.6 7.3 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] "413,332" "201,708" "591,548" "158,286" "221,162" "100,258"#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] 413332 201708 591548 158286 221162 100258#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] "M. Night Shyamalan" "Paul Feig" "David Ayer"
## [4] "Sang-ho Yeon" "James Wan" "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] "James McAvoy" "Melissa McCarthy" "Will Smith"
## [4] "Yoo Gong" "Vera Farmiga" "John Gallagher Jr."#Data-Preprocessing: converting actors data into factors
actors_data<-as.factor(actors_data)#Using CSS selectors to scrape the metascore section
metascore_data_html <- html_nodes(webpage,'.metascore')
#Converting the runtime data to text
metascore_data <- html_text(metascore_data_html)
#Let's have a look at the metascore data
head(metascore_data)## [1] "62 " "60 " "40 " "72 " "65 "
## [6] "67 "#Data-Preprocessing: removing extra space in metascore
metascore_data<-gsub(" ","",metascore_data)
#Lets check the length of metascore data
length(metascore_data)## [1] 96for (i in c(33,58,74,89)){
a<-metascore_data[1:(i-1)]
b<-metascore_data[i:length(metascore_data)]
metascore_data<-append(a,list("NA"))
metascore_data<-append(metascore_data,b)
}
#Data-Preprocessing: converting metascore to numerical
metascore_data<-as.numeric(metascore_data)## Warning: NAs introduced by coercion
## Warning: NAs introduced by coercion
## Warning: NAs introduced by coercion
## Warning: NAs introduced by coercion#Let's have another look at length of the metascore data
length(metascore_data)## [1] 100#Let's look at summary statistics
summary(metascore_data)## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 22.00 47.00 60.00 59.54 72.00 99.00 4#Using CSS selectors to scrape the gross revenue section
gross_data_html <- html_nodes(webpage,'.ghost~ .text-muted+ span')
#Converting the gross revenue data to text
gross_data <- html_text(gross_data_html)
#Let's have a look at the votes data
head(gross_data)## [1] "$138.29M" "$128.34M" "$325.10M" "$2.13M" "$102.47M" "$6.86M"#Data-Preprocessing: removing '$' and 'M' signs
gross_data<-gsub("M","", gross_data)
gross_data<-substring(gross_data,2,6)
#Let's check the length of gross data
length(gross_data)## [1] 90#Filling missing entries with NA
for (i in c(6,11,33,53,58,80,85,86,88,94)){
a<-gross_data[1:(i-1)]
b<-gross_data[i:length(gross_data)]
gross_data<-append(a,list("NA"))
gross_data<-append(gross_data,b)
}
#Data-Preprocessing: converting gross to numerical
gross_data<-as.numeric(gross_data)## Warning: NAs introduced by coercion
## Warning: NAs introduced by coercion
## Warning: NAs introduced by coercion
## Warning: NAs introduced by coercion
## Warning: NAs introduced by coercion
## Warning: NAs introduced by coercion
## Warning: NAs introduced by coercion
## Warning: NAs introduced by coercion
## Warning: NAs introduced by coercion
## Warning: NAs introduced by coercion#Let's have another look at the length of gross data
length(gross_data)## [1] 100summary(gross_data)## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 0.02 10.71 53.75 86.42 101.92 532.10 10#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 "Split" "Ghostbusters: Answer the Call" "Suicide Squad" "Train to Busan" ...
## $ Description : chr " Three girls are kidnapped by a man with a diagnosed 23 distinct personalities. They must try to escape befo"| __truncated__ " Following a ghost invasion of Manhattan, paranormal enthusiasts Erin Gilbert and Abby Yates, nuclear engine"| __truncated__ " A secret government agency recruits some of the most dangerous incarcerated super-villains to form a defens"| __truncated__ " While a zombie virus breaks out in South Korea, passengers struggle to survive on the train from Seoul to Busan." ...
## $ Runtime : num 117 117 123 118 134 82 83 108 144 107 ...
## $ Genre : Factor w/ 8 levels "Action","Adventure",..: 8 1 1 1 8 8 1 1 1 3 ...
## $ Rating : num 7.3 6.5 6 7.6 7.3 6.6 6.2 8 6.9 7.6 ...
## $ Metascore : num 62 60 40 72 65 67 44 65 52 81 ...
## $ Votes : num 413332 201708 591548 158286 221162 ...
## $ Gross_Earning_in_Mil: num 138.2 128.3 325.1 2.13 102.4 ...
## $ Director : Factor w/ 96 levels "Adam Wingard",..: 54 69 21 79 40 61 52 90 12 76 ...
## $ Actor : Factor w/ 91 levels "Aamir Khan","Adam Sandler",..: 38 60 90 91 88 42 76 74 38 7 ...library('ggplot2')
qplot(data = movies_df,Runtime,fill = Genre,bins = 30)
# Q1 Based on the above data, which movie from which Genre had the longest runtime? Based on the plot I think Drama and Action had the longest run time.
ggplot(movies_df,aes(x=Runtime,y=Rating))+
geom_point(aes(size=Votes,col=Genre))
#Q2 Based on the above data, in the Runtime of 130-160 mins, which genre has the highest votes? I believe action has the highest votes.
ggplot(movies_df,aes(x=Runtime,y=Gross_Earning_in_Mil))+
geom_point(aes(size=Rating,col=Genre))## Warning: Removed 10 rows containing missing values (geom_point).
# Q3 Based on the above data, across all genres which genre has the highest average gross earnings in runtime 100 to 120. I think Action, Adventure & Animation has the highest average gross earnings.