Created
August 26, 2020 11:45
-
-
Save aleszu/84f5671781debe1c554fc33554b31f6e to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
library(rvest) | |
library(tidyRSS) | |
library(tidyverse) | |
library(stringr) | |
# https://www.cjr.org/analysis/as-election-looms-a-network-of-mysterious-pink-slime-local-news-outlets-nearly-triples-in-size.php | |
pinkslimesites <- read.csv("pinkslimesites.csv", stringsAsFactors = F) | |
all_pinkslimesites <- pinkslimesites %>% | |
mutate(Rss = paste0(Domain,"/stories.rss")) | |
all_RSS_urls <- all_pinkslimesites$Rss | |
RSS_function <- function(all_RSS_urls) { | |
stories <- tidyfeed(all_RSS_urls, | |
config = list(), clean_tags = TRUE, | |
list = FALSE, parse_dates = TRUE ) | |
} | |
# run with safely() to store error mssgs | |
safe_scrape <- safely(RSS_function) | |
# Pull in RSS feed for last 20 articles! | |
all_titles <- map(all_RSS_urls, safe_scrape) | |
glimpse(all_titles) | |
all_titles_mapped <- all_titles %>% # Put the result from RSS feed into a dataframe | |
map_df(~ .x[["result"]]) | |
glimpse(all_titles_mapped) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment