Web scrape and display top charities for hurricane relief.

Top_Charities_Hurricane_X.R

## Top Charities for Hurricane Harvey Relief
## According to both Charity Navigator and Charity Watch
## Approach:
##  Scrape data from Charity Navigator and Charity Watch.
##  Merge and display the intersection (common entries) of 
##  the two data sets.
## ** BROKEN ** As of 2017-10-29, Charity Navigator has changed their page
##              and the organization of the table of charities.

## Libraries ####
library(rvest)  # Web scraping
library(dplyr)  # Data wrangling

## Download and clean the data ####
cn_url <- "https://www.charitynavigator.org/index.cfm?bay=content.view&cpid=5356&from=homepage"
cw_url <- "https://www.charitywatch.org/charitywatch-hot-topic/hurricane-maria-relief/81"

cn_df <- read_html(cn_url) %>% 
  html_node(xpath = '//*[@id="list-right"]/table') %>% 
  html_table() %>% 
  setNames(c("Charity", "Rating")) %>% 
  arrange(Charity)
cw_df <- read_html(cw_url) %>% 
  html_node(xpath = '//*[@id="main_wrapper"]/div/table') %>% 
  html_table() %>% 
  setNames(c("Charity", "Rating")) %>% 
  arrange(Charity)

## Manually fix mismatched charity names
rename_vec <- c(`Direct Relief & Direct Relief Foundation` = "Direct Relief")
cw_df$Charity[cw_df$Charity == names(rename_vec)] <- na.omit(rename_vec[cw_df$Charity])

## Display intersection of results ####
cn_df %>% inner_join(cw_df, by = "Charity") %>% select(Charity)