scrape_graphics

library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

library(rvest)

graphics = data.frame()

for (page_result in seq(from = 0, to = 40, by = 10)) {
  link = paste0("https://www.columbiamissourian.com/search/?f=html&q=tag_section%3Avisuals%2Fgraphics&s=start_time&sd=desc&l=10&nsa=eedition&app%5B0%5D=editorial&o=", page_result)
  page = read_html(link)
  name = page %>% html_nodes(".tnt-headline .tnt-asset-link") %>% html_text()
  author = page %>% html_nodes(".tnt-byline") %>% html_text()
  graphics = rbind(graphics, data.frame(name, author, stringsAsFactors = FALSE))
  
  print(paste("Page:", page_result))
}

## [1] "Page: 0"
## [1] "Page: 10"
## [1] "Page: 20"
## [1] "Page: 30"
## [1] "Page: 40"

write.csv(graphics, "graphics.csv")