Introduction to Data Science Homework1

1. Scrape the table tall buildings (300m+) currently under construction from https://en.wikipedia.org/wiki/List_of_tallest_buildings_in_the_world Table: Denotes building that is or was once the tallest in the world.

url <-  "https://en.wikipedia.org/wiki/List_of_tallest_buildings_in_the_world"
 h <- read_html(url)
 tab <- h %>% html_nodes("table")
 tab <- tab[[2]] %>% html_table
#tab <- tab %>% setNames(c("Rank", "Name","Image" , "City","Country","Height (m)", "Height (ft)"  ,"Floors", "Years" , "Notes"))

names(tab) <- tab[1,]
tab <- tab[-1,]

tab

2. Scrape the table tall buildings (300m+) currently under construction from https://en.wikipedia.org/wiki/List_of_tallest_buildings_in_the_world Table: Denotes building with pinnacle height higher than architectural.

url <-  "https://en.wikipedia.org/wiki/List_of_tallest_buildings_in_the_world"
 h <- read_html(url)
 tab <- h %>% html_nodes("table")
 tab <- tab[[4]] %>% html_table
tab <- tab %>% setNames(c("Rank", "Building", "City" ,"Country", "Height (m)", "Height (ft)", "Floors" ,"Built"))
tab

3. Scrape the table tall buildings (300m+) currently under construction from https://en.wikipedia.org/wiki/List_of_tallest_buildings_in_the_world Table: Height to occupied floor

url <-  "https://en.wikipedia.org/wiki/List_of_tallest_buildings_in_the_world"
 h <- read_html(url)
 tab <- h %>% html_nodes("table")
 tab <- tab[[5]] %>% html_table
tab <- tab %>% setNames(c("Rank", "Building", "City" ,"Country", "Height ", "Floors" ,"Built"))
tab

4. Scrape the table tall buildings (300m+) currently under construction from https://en.wikipedia.org/wiki/List_of_tallest_buildings_in_the_world Table: Buildings under construction

url <-  "https://en.wikipedia.org/wiki/List_of_tallest_buildings_in_the_world"
 h <- read_html(url)
 tab <- h %>% html_nodes("table")
 tab <- tab[[6]] %>% html_table
tab <- tab %>% setNames(c("Building", "Planned architectural height", "Floors", "Planned completion" 
                           ,   "Country", "City" , "Ref."))
tab

5. Scrape the table tall buildings (300m+) currently under construction from https://en.wikipedia.org/wiki/List_of_tallest_buildings_in_the_world Table: List by continent

url <-  "https://en.wikipedia.org/wiki/List_of_tallest_buildings_in_the_world"
 h <- read_html(url)
 tab <- h %>% html_nodes("table")
 tab <- tab[[7]] %>% html_table
tab <- tab %>% setNames(c("Countinent", "Building", "height" , "Floors Count", "Completed" ,   "Country", "City" ))
tab

6. Scrape the table for editorial-board-members from http://www.ijeais.org/ijeais/index.php/editorial-board-members/

url <-  "http://www.ijeais.org/ijeais/index.php/editorial-board-members/"
 h <- read_html(url)
 tab <- h %>% html_nodes("table")
 tab <- tab[[1]] %>% html_table
tab <- tab %>% setNames(c("Name","Branch","Institution/Affiliation","Country" ))
tab

7. Scrap titles from this webpage https://www.imdb.com/search/title/?title_type=feature&num_votes=25000,&genres=adventure

 html_Content <- read_html("https://www.imdb.com/search/title/?title_type=feature&num_votes=25000,&genres=adventure") 
  
titles <-  html_Content %>% html_nodes(".lister-item-header") %>% html_node("a") %>%
    html_text()

library(stringr)
titles <- str_replace_all(titles, "[\r\n]" , "")
titles <- str_replace_all(titles, " " , "")


titles_data <- class.df<- data.frame(titles)
titles_data

8. Scrap Years from this webpage https://www.imdb.com/search/title/?title_type=feature&num_votes=25000,&genres=adventure

 
years <-  html_Content %>% html_nodes(".lister-item-year") %>%
    html_text()


  years_data <- class.df<- data.frame(years)
years_data

9. Scrap Ratings from this webpage https://www.imdb.com/search/title/?title_type=feature&num_votes=25000,&genres=adventure

 
 
ratings <-  html_Content %>% html_nodes(".ratings-imdb-rating") %>%
    html_text()

ratings <- str_replace_all(ratings, "[\r\n]" , "")
ratings <- str_replace_all(ratings, " " , "")

  ratings_data <- class.df<- data.frame(ratings)
ratings_data

10. Scrap the synopsis of the movies from this webpage https://www.imdb.com/search/title/?title_type=feature&num_votes=25000,&genres=adventure Use: .ratings-bar+ .text-muted

synopsis <-  html_Content %>% html_nodes(".ratings-bar+ .text-muted") %>%
    html_text()

synopsis <- str_replace_all(synopsis, "[\r\n]" , "")
synopsis <- str_replace_all(synopsis, " " , "")

synopsis_data <- class.df<- data.frame(synopsis)
synopsis_data

NA

11. Create a data frame using our variables as a column from #7…..#10

complete_data <- class.df<- data.frame(titles , years ,ratings ,  synopsis )
complete_data

NA