NEJM and pre-print policy

nejm_blog_post.R

## Code for the blog post here: 
## https://mathewkiang.com/2017/10/08/using-r-wikipedia-sherparomeo-show-new-england-journal-medicines-pre-print-statement-empirically-false
## You can download the original files from the blogpost.
## If downloading new files, you probably want to change the date in the file names.

## Imports
library(rvest)
library(tidyverse)

## Wiki data
if (!file.exists("./list_of_med_journals_20170906.RDS")) {
    list_url <- "https://en.wikipedia.org/wiki/List_of_medical_journals"
    
    list_df  <- list_url %>% 
        read_html() %>% 
        html_nodes("table") %>% 
        html_table(fill = TRUE) %>% 
        .[[1]]
    
    saveRDS(list_df, file = "./list_of_med_journals_20170906.RDS")
} else {
    list_df <- readRDS("./list_of_med_journals_20170906.RDS")
}

## RoMEO data
if (!file.exists("./romeo_colors_20170906.RDS")) {
    ## Make new columns (store ISSN for verification in future)
    romeo_df <- list_df %>% 
        mutate(romeo = NA, 
               issn = NA, 
               api_outcome = NA)
    
    for (i in seq_along(romeo_df$Name)) {
        print(romeo_df$Name[i])
        
        api_url <- "http://www.sherpa.ac.uk/romeo/api29.php?jtitle="
        api_req <- gsub(" ", "%20", sprintf("%s%s", api_url, romeo_df$Name[i]))
        request <- read_xml(api_req)
        
        temp_issn <- request %>% 
            xml_node("issn") %>% 
            xml_text()
        temp_color <- request %>% 
            xml_node("romeocolour") %>% 
            xml_text()
        
        romeo_df$issn[i]     <- ifelse(length(temp_issn > 0), temp_issn, NA)
        romeo_df$romeo[i]    <- ifelse(length(temp_color > 0), temp_color, NA)
        romeo_df$api_outcome <- request %>% xml_node("outcome") %>% xml_text()
    }
    saveRDS(romeo_df, file = "./romeo_colors_20170906.RDS")
} else {
    romeo_df <- readRDS("./romeo_colors_20170906.RDS")
}