Recent Data Carpentry Genomics workshops

mine.R

suppressPackageStartupMessages({
    library(tidyverse)
    library(rvest)                      # Webscraping
    library(stringr)
})

workshops_url <- read_html("http://www.datacarpentry.org/workshops-past/")
workshops <- tibble(
    date = html_nodes(workshops_url, "td[class='date']") %>% html_text(),
    name = html_nodes(workshops_url, "td[class='link']") %>% html_text(),
    url = html_nodes(workshops_url, "td[class='link'] a") %>% html_attr("href")
)

## Handle missing pages (HTTP 404 error) using `try()`.
try_read_html <- function(url) try(read_html(url))
pages <- lapply(workshops$url, try_read_html)
is_error <- function(x) inherits(x, "try-error")
workshops$page <- pages
workshops <- filter(workshops, ! sapply(page, is_error))

## Label official genomics lessons
url_grepl <- function(x, pattern, ...) {
    x %>%
        html_nodes("a") %>%
        html_attr("href") %>%
        grepl(pattern = pattern, ignore.case = TRUE, ...) %>%
        sum > 0
}
official <- mutate(workshops,
                   lesson_intro = sapply(
                       page, url_grepl, "introduction-genomics"),
                   lesson_cloud = sapply(
                       page, url_grepl, "cloud-genomics"),
                   lesson_shell =  sapply(
                       page, url_grepl, "shell-genomics"),
                   lesson_wrangling =  sapply(
                       page, url_grepl, "wrangling-genomics"),
                   lesson_r =  sapply(
                       page, url_grepl, "R-genomics"))

## Count how many genomics lessons in these workshops
sums <- select(official, starts_with("lesson_")) %>% rowSums %>% as.integer
official <- mutate(official, lessons = sums)
## Show with at least 1 lesson, sorted by relevance
genomics_official <- filter(official, lessons > 0) %>%
    arrange(-lessons) %>% select(lessons, url)
genomics_official

output.txt

 > genomics_official
 # A tibble: 13 × 2
    lessons                                                       url
      <int>                                                     <chr>
 1        5           https://ryanpeek.github.io/2017-01-22-stanford/
 2        5     https://tracykteal.github.io/2016-11-21-genomics-unm/
 3        5 https://uio-carpentry.github.io/2016-03-15-Oslo-data-bio/
 4        4  https://nwu-eresearch.github.io/2016-09-26-nwu-genomics/
 5        4           https://datacarpentry.github.io/2016-05-26-NIH/
 6        4                   https://iglpdc.github.io/2016-04-11-bu/
 7        4              http://www.datacarpentry.org/2016-01-19-sbu/
 8        4          http://www.datacarpentry.org/2015-09-22-UCDavis/
 9        4             http://www.datacarpentry.org/2015-07-30-ASPB/
 10       2   https://vlsci.github.io/datacarpentry_2015-11-23_VLSCI/
 11       1      https://markrobinsonuzh.github.io/2016-07-18-zurich/
 12       1              https://lmweber.github.io/2016-05-30-Zurich/
 13       1              http://www.datacarpentry.org/2015-08-24-ISU/
 >