Website: Analytics Vidhya URL: https://www.analyticsvidhya.com/blog/2017/03/beginners-guide-on-web-scraping-in-r-using-rvest-with-hands-on-knowledge/
#install.packages('rvest')
#Loading the rvest pacakge
library('rvest')
#Specigying the url for desired website to be scraped
url <- 'https://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] "Arrival" "Suicide Squad"
## [3] "Train to Busan" "Ghostbusters: Answer the Call"
## [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] "\nA linguist works with the military to communicate with alien lifeforms after twelve mysterious spacecraft appear around the world."
## [2] "\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."
## [3] "\nWhile a zombie virus breaks out in South Korea, passengers struggle to survive on the train from Seoul to Busan."
## [4] "\nFollowing 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."
## [5] "\nEd 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] "\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 linguist works with the military to communicate with alien lifeforms after twelve mysterious spacecraft appear around the world."
## [2] "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."
## [3] "While a zombie virus breaks out in South Korea, passengers struggle to survive on the train from Seoul to Busan."
## [4] "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."
## [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 atthe runtime
head(runtime_data)
## [1] "116 min" "123 min" "118 min" "117 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] 116 123 118 117 134 82
#Using CSS selectors to screape 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, Sci-Fi "
## [2] "\nAction, Adventure, Fantasy "
## [3] "\nAction, Horror, Thriller "
## [4] "\nAction, Comedy, Fantasy "
## [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] Drama 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] "7.9" "5.9" "7.6" "6.5" "7.3" "6.6"
#Data-Preprocessing: converting ratings to numerical
rating_data<-as.numeric(rating_data)
#Let's have nother look at the ratings data
head(rating_data)
## [1] 7.9 5.9 7.6 6.5 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] "644,825" "655,642" "194,001" "214,998" "251,992" "119,754"
#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] 644825 655642 194001 214998 251992 119754
#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] "Denis Villeneuve" "David Ayer" "Sang-ho Yeon" "Paul Feig"
## [5] "James Wan" "Mike Flanagan"
#Data-Preprocessing: converting direcotrs 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" "Will Smith" "Gong Yoo"
## [4] "Melissa McCarthy" "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
head(metascore_data)
## [1] "81 " "40 " "72 " "60 " "65 "
## [6] "67 "
#Data-Preprocessing: removing extra space removing extra space in metascore
metascore_data<-gsub(" ","",metascore_data)
#Let's check the length of metascore data
length(metascore_data)
## [1] 96
for (i in c(34,43,80,96)){
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
## 18.00 47.00 62.00 60.43 74.25 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] "$100.55M" "$325.10M" "$2.13M" "$128.34M" "$102.47M" "$89.22M"
#Data_Preprocessing: removing '$' 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] 89
#Filling missing entries with NA
for (i in c(6,25,34,43,50,66,73,77,80,86,99)){
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
## Warning: NAs introduced by coercion
#Let's have another look at the length of gross data
length(gross_data)
## [1] 100
summary(gross_data)
## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 0.18 14.27 54.65 96.38 125.00 532.10 11
#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 "Arrival" "Suicide Squad" "Train to Busan" "Ghostbusters: Answer the Call" ...
## $ Description : chr "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__ "While a zombie virus breaks out in South Korea, passengers struggle to survive on the train from Seoul to Busan." "Following a ghost invasion of Manhattan, paranormal enthusiasts Erin Gilbert and Abby Yates, nuclear engineer J"| __truncated__ ...
## $ Runtime : num 116 123 118 117 134 82 88 132 108 116 ...
## $ Genre : Factor w/ 8 levels "Action","Adventure",..: 7 1 1 1 8 8 6 1 1 7 ...
## $ Rating : num 7.9 5.9 7.6 6.5 7.3 6.6 7.1 6.9 8 7.5 ...
## $ Metascore : num 81 40 72 60 65 67 71 54 65 67 ...
## $ Votes : num 644825 655642 194001 214998 251992 ...
## $ Gross_Earning_in_Mil: num 100.5 325.1 2.13 128.3 102.4 ...
## $ Director : Factor w/ 97 levels "Adam Wingard",..: 30 26 83 71 43 61 33 9 91 93 ...
## $ Actor : Factor w/ 92 levels "Aamir Khan","Adam Driver",..: 4 92 38 68 90 48 83 21 78 4 ...
library('ggplot2')
qplot(data = movies_df,Runtime,fill = Genre,bins = 30)
Answer: Drama and Action movies timed for the longest runtime at 160 minutes.
ggplot(movies_df,aes(x=Runtime, y=Rating))+
geom_point(aes(size=Votes,col=Genre))
Answer: Action movies has the highest votes at 160 minutes.
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).
#### Question 3: Based on the above data, across all genres which genre has the highest average gross earnings in runtime 100 to 120. Answer: Action,Adventure, and Animation tie with Gross Earnings at 350 million with runtimes between 100 to 120 minutes.