R for Web Scraping
sileshi
4/8/2022
#install.packages("rvest")
#install.packages("plotly")
library(plotly)## Warning: package 'plotly' was built under R version 4.1.3## Loading required package: ggplot2## Warning: package 'ggplot2' was built under R version 4.1.3##
## 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#4. Scraping a webpage using R
#Loading the rvest package
library('rvest')## Warning: package 'rvest' was built under R version 4.1.3#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)#Step 3: Once you know the CSS selector that contains the rankings, you can use this simple R code to get all the rankings:
#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."#Step 4: Once you have the data, make sure that it looks in the desired format. I am preprocessing my data to convert it to numerical format.
#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#Step 5: Now you can clear the selector section and select all the titles. You can visually inspect that all the titles are selected. Make any required additions and deletions with the help of your curser. I have done the same here.
#Step 6: Again, I have the corresponding CSS selector for the titles – .lister-item-header a. I will use this selector to scrape all the titles using the following code.
#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] "Fantastic Beasts and Where to Find Them"
## [2] "Batman v Superman: Dawn of Justice Ultimate Edition"
## [3] "Suicide Squad"
## [4] "Doctor Strange"
## [5] "Deadpool"
## [6] "The Handmaiden"#Step 7: In the following code, I have done the same thing for scraping – Description, Runtime, Genre, Rating, Metascore, Votes, Gross_Earning_in_Mil , Director and Actor data.
#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] "\nThe adventures of writer Newt Scamander in New York's secret community of witches and wizards seventy years before Harry Potter reads his book in school."
## [2] "\nBatman is manipulated by Lex Luthor to fear Superman. Superman´s existence is meanwhile dividing the world and he is framed for murder during an international crisis. The heroes clash and force the neutral Wonder Woman to reemerge."
## [3] "\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."
## [4] "\nWhile on a journey of physical and spiritual healing, a brilliant neurosurgeon is drawn into the world of the mystic arts."
## [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 woman is hired as a handmaiden to a Japanese heiress, but secretly she is involved in a plot to defraud her."#Data-Preprocessing: removing '\n'
description_data<-gsub("\n","",description_data)#Let's have another look at the description data
head(description_data)## [1] "The adventures of writer Newt Scamander in New York's secret community of witches and wizards seventy years before Harry Potter reads his book in school."
## [2] "Batman is manipulated by Lex Luthor to fear Superman. Superman´s existence is meanwhile dividing the world and he is framed for murder during an international crisis. The heroes clash and force the neutral Wonder Woman to reemerge."
## [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 on a journey of physical and spiritual healing, a brilliant neurosurgeon is drawn into the world of the mystic arts."
## [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 woman is hired as a handmaiden to a Japanese heiress, but secretly she is involved in a plot to defraud her."#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] "132 min" "182 min" "123 min" "115 min" "108 min" "145 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] 132 182 123 115 108 145#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] "\nAdventure, Family, Fantasy "
## [2] "\nAction, Adventure, Sci-Fi "
## [3] "\nAction, Adventure, Fantasy "
## [4] "\nAction, Adventure, Fantasy "
## [5] "\nAction, Adventure, Comedy "
## [6] "\nDrama, Romance, 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] Adventure Action Action Action Action Drama
## 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" "7.9" "5.9" "7.5" "8.0" "8.1"#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 7.9 5.9 7.5 8.0 8.1#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] "449,828" "16,327" "670,006" "688,717" "990,752" "137,185"#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] 449828 16327 670006 688717 990752 137185#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] "David Yates" "David Ayer" "Scott Derrickson" "Tim Miller"
## [5] "Park Chan-wook" "Zack Snyder"#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] "David Yates" "David Ayer" "Scott Derrickson" "Tim Miller"
## [5] "Park Chan-wook" "Zack Snyder"#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] "Eddie Redmayne" "Will Smith" "Benedict Cumberbatch"
## [4] "Ryan Reynolds" "Kim Min-hee" "Ben Affleck"#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] "66 " "40 " "72 " "65 " "84 "
## [6] "44 "#Data-Preprocessing: removing extra space in metascore
metascore_data<-gsub(" ","",metascore_data)
#Lets check the length of metascore data
length(metascore_data)## [1] 97#Step 9: It is a practical situation which can arise while scraping any website. Unfortunately, if we simply add NA’s to last 4 entries, it will map NA as Metascore for movies 96 to 100 while in reality, the data is missing for some other movies. After a visual inspection, I found that the Metascore is missing for movies 39, 73, 80 and 89. I have written the following function to get around this problem.
for (i in c( 23.00, 47.75,62.00,60.56,74.00,99.00,11)){
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
## 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] 102#Let's look at summary statistics
summary(metascore_data)## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 23.00 48.00 62.00 60.78 74.00 99.00 7#Step 10: The same thing happens with the Gross variable which represents gross earnings of that movie in millions. I have use the same solution to work my way around:
#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] "$234.04M" "$325.10M" "$232.64M" "$363.07M" "$2.01M" "$330.36M"#Data-Preprocessing: removing '$' 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(17,39,49,52,57,64,66,73,76,77,80,87,88,89)){
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
## 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] 104summary(gross_data)## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 0.18 26.84 56.95 95.85 126.20 532.10 14#Step 11: Now we have successfully scraped all the 11 features for the 100 most popular feature films released in 2016. Let’s combine them to create a dataframe and inspect its structure.
#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,
Votes = votes_data)#,Gross_Earning_in_Mil = gross_data)
#Structure of the data frame
str(movies_df)## 'data.frame': 100 obs. of 7 variables:
## $ Rank : num 1 2 3 4 5 6 7 8 9 10 ...
## $ Title : chr "Fantastic Beasts and Where to Find Them" "Batman v Superman: Dawn of Justice Ultimate Edition" "Suicide Squad" "Doctor Strange" ...
## $ Description: chr "The adventures of writer Newt Scamander in New York's secret community of witches and wizards seventy years bef"| __truncated__ "Batman is manipulated by Lex Luthor to fear Superman. Superman´s existence is meanwhile dividing the world and "| __truncated__ "A secret government agency recruits some of the most dangerous incarcerated super-villains to form a defensive "| __truncated__ "While on a journey of physical and spiritual healing, a brilliant neurosurgeon is drawn into the world of the mystic arts." ...
## $ Runtime : num 132 182 123 115 108 145 152 108 144 133 ...
## $ Genre : Factor w/ 8 levels "Action","Adventure",..: 2 1 1 1 1 7 1 3 1 1 ...
## $ Rating : num 7.3 7.9 5.9 7.5 8 8.1 6.5 7.1 6.9 7.8 ...
## $ Votes : num 449828 16327 670006 688717 990752 ...#Gross_Earning_in_Mil
#Metascore = metascore_datamovies_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) # I removed director and actor data from the dataframe since they currently only have 99 observations #Director = directors_data, Actor = actors_data
#Structure of the data frame str(movies_df)
#6. Analyzing scraped data from the web
library('ggplot2')
qplot(data = movies_df,Runtime,fill = Genre,bins = 30)
#Question 1: Based on the above data, which movie from which Genre had the longest runtime?
p1 <- qplot(data = movies_df,Runtime,fill = Genre,bins = 30)
p1 <- movies_df %>%
ggplot(aes(x=Runtime, fill = Genre)) +
geom_histogram(position="identity", alpha=0.5, binwidth = 5, color = "white")+
scale_fill_discrete(name = "Genre") +
labs(title = "Top 100 Movies of 2016 Runtime by Genre")
ggplotly(p1)ggplot(movies_df,aes(x=Runtime,y=Rating))+
geom_point(aes(size=Votes,col=Genre))
#Question 2: Based on the above data, in the Runtime of 130-160 mins, which genre has the highest votes?
ggplot(movies_df,aes(x=Runtime,y=Rating))+
geom_point(aes(size=Rating,col=Genre))
p2 <- movies_df%>%ggplot(aes(x=Runtime,y=Rating))+
geom_point(aes(size=Votes,col=Genre, text = paste("Movie Title:", title_data)), alpha = 0.7) +
labs(title = "Top 100 Movies of 2016 Runtime by Ratings") ## Warning: Ignoring unknown aesthetics: text##Question 3: Based on the above data, across all genres which genre has the highest average gross earnings in runtime 100 to 120. # Ididn’t plot for Question #3 because of gross Earning in millions = gross_data #[104] it means no y value.
p3 <- movies_df %>%
ggplot(aes(x=Runtime,y=Gross_Earnings_in_Millions))+
geom_point(aes(size = Rating,col = Genre), alpha = 0.5) +
labs(title = "Top 100 Movies of 2016 Runtime by Gross Earnings in Millions") +
scale_y_continuous("Gross Earnings in Millions", limits =c(-10, 600))
#ggplotly(p3)