ISP DIGIMIND PICTURE PULL

This is R Markdown Notebook is written by Alf Molinas for his ISP in April 2020 as part of the INSEAD MBA program.

library(rvest)  
library(stringr)
library(httr)




#extract links from file
url <- read.csv(file.choose())
linklist <- url$Link
#create data frame for the extracted image urls
df <- data.frame(1:100)

for (item in linklist) {
  if (item == ""){
    return()
  }
  if (http_status(GET(item))$category == "Client error"){
    imgsrc <- "NA"
  }
  else {
  print(item)

  
  
#collect the src (image URLs) of all the images on the website
imgsrc <- read_html(item
) %>%
  html_nodes(xpath = '//*/img') %>%
  html_attr('src')
imgsrc


#save on to 1 column of a table where each URL is in a different row
column <- 1
add.col<-function(df, new.col) {n.row<-dim(df)[1]
           length(new.col)<-n.row
           cbind(df, new.col)
}
df<-add.col(df,imgsrc)
length(imgsrc)
  }
}

write.csv(df, file = "pulledimages.csv")

Upload the pulled images from the csv file to an online table like Google spreadsheet or Airtable, and the links will convert to the images.