Last active
November 3, 2019 12:52
-
-
Save ganzuul/fe95abc1ea2f4f5e97d050c1694671c9 to your computer and use it in GitHub Desktop.
edges case is broken
This file contains hidden or 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
#install.packages("httr") | |
#install.packages("jsonlite") | |
#install.packages("tidyverse") | |
#install.packages("stringr") | |
require(httr) | |
require(jsonlite) | |
require(tidyverse) | |
require(stringr) | |
base <- "https://en.wikipedia.org/w/api.php?action=query&format=json&prop=linkshere&lhlimit=500" | |
articles <- c("Maximal and minimal elements", "Maxima and minima") | |
titles <- function(v){paste("&titles=", v, sep="")} | |
ids <- function(v){paste("&pageids=", v, sep="")} | |
query <- function(v){paste(base,v, sep="")} | |
getLh <- function(v){as.data.frame(fromJSON(content(GET(v),"text"), flatten=FALSE))} | |
map(articles, URLencode) %>% | |
map(titles) %>% | |
map(query) %>% | |
map(getLh) %>% | |
map(~select(.x, c(4,5,7,8))) %>% | |
map(~as_tibble(.x, .name_repair="minimal")) -> tibs | |
map(tibs, function(v){filter(v, complete.cases(v))}) %>% # Convenient NAs in data. | |
map(~select(.x, c(2))) %>% | |
map(flatten_chr) %>% | |
map(ids) %>% | |
map(as.list) %>% | |
map(query) %>% | |
map(as.list) -> urls | |
map(urls, function(v){v %>% map(getLh)}) -> df1 | |
#edges <- function(v){ v %>% map(~select(.x,c(4,7)))}; df <- map(df1,edges) #broken | |
#edges <- function(v){ v %>% map(~pluck(.x,7))}; df <- map(df1,edges) #works but single-column | |
e <- function(v){select(v,c(4,7))}; df <- map(df1[[1]],e) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment