Created
January 23, 2015 16:16
-
-
Save lmullen/1b71a7e8df1f1755ab9c to your computer and use it in GitHub Desktop.
Scraping the Joseph Smith papers
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(dplyr) | |
| library(magrittr) | |
| # First find the list of people and parse out their names and urls. | |
| base <- "http://josephsmithpapers.org" | |
| list_of_people <- "/reference/people#a::" | |
| results <- paste0(base, list_of_people) %>% | |
| html() %>% | |
| html_nodes(".alphaItem") | |
| names <- results %>% | |
| html_text() %>% | |
| unlist() | |
| path <- results %>% | |
| html_attr("href") %>% | |
| unlist() | |
| people <- data_frame(names, path) | |
| get_person_data <- function(url) { | |
| result <- html(url) | |
| full_name <- result %>% | |
| html_node(".metadata:nth-child(1) dd") %>% | |
| html_text() | |
| gender <- result %>% | |
| html_node(".metadata:nth-child(2) dd") %>% | |
| html_text() | |
| bio <- result %>% | |
| html_nodes("p") %>% | |
| .[3] %>% | |
| html_text() | |
| mentions <- result %>% | |
| html_nodes("#paper-link a") %>% | |
| as.list() | |
| data_frame(full_name, gender, bio) %>% | |
| bind_cols(mentions) | |
| } | |
| temp <- paste0(base, people[1,2]) %>% | |
| get_person_data() | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment