Created
July 21, 2020 00:45
-
-
Save benmarwick/9d827978712f3e80250e608380e2d21b to your computer and use it in GitHub Desktop.
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(tidyverse) | |
library(rvest) | |
# what quarter and year do we want to check for the availability of DSM courses? | |
qrt_year <- "AUT2020" | |
# this is the URL to our canonical list of DSM courses | |
webpage <- "https://www.washington.edu/uaa/advising/single-pages/data-science-minor/" | |
# scrape text from DSM list --------------------------------------- | |
dsm_courses <- | |
webpage %>% | |
read_html() %>% | |
html_nodes("blockquote li") %>% | |
html_text() | |
# tidy DSM course list -------------------------------------------- | |
# get course prefix | |
dsm_courses_prefix <- | |
dsm_courses %>% | |
str_match("[A-Z]+") %>% | |
as.vector() | |
# get course number | |
dsm_courses_number <- | |
dsm_courses %>% | |
str_match("[0-9]+") %>% | |
as.vector() | |
# search course catalog & time schedule ---------------------------- | |
# search course catalog to get URL | |
crscat_url <- "https://www.washington.edu/students/crscat/" | |
dsm_crscat_url <- str_c(crscat_url, str_to_lower(dsm_courses_prefix), ".html") | |
# get URL to time schedule | |
timeschd_url <- "https://www.washington.edu/students/timeschd/" | |
# the timeschd_url prefixes are not identical to the course prefixes :( | |
cas_programs <- | |
timeschd_url %>% | |
str_c(qrt_year) %>% | |
read_html() %>% | |
html_nodes("ul:nth-child(34) a") %>% | |
html_text() | |
cas_program_urls <- | |
timeschd_url %>% | |
str_c(qrt_year) %>% | |
read_html() %>% | |
html_nodes("ul:nth-child(34) a") %>% | |
html_attr('href') | |
# note that we may miss some things like JSIS A | |
cas_program_names_and_urls <- | |
tibble(cas_programs = cas_programs, | |
cas_prefix = as.vector(str_match(cas_programs, "[A-Z]{3,4}")), | |
cas_program_urls = str_c(timeschd_url, qrt_year, "/", cas_program_urls)) %>% | |
drop_na(cas_prefix) | |
# get time schedule classes for prefixes listed on the dsm website | |
get_stuff <- function(x){ | |
read_html(x) %>% | |
html_nodes("br+ table a:nth-child(1)") %>% | |
html_text() %>% | |
str_squish() | |
} | |
get_stuff_safe <- safely(get_stuff, otherwise = NA_real_) | |
# this will take a few seconds to get all the courses on the current time schedule | |
courses_from_timeschd <- | |
map(cas_program_names_and_urls$cas_program_urls, | |
~.x %>% | |
get_stuff_safe() | |
) | |
cas_program_names_and_urls_offered <- | |
cas_program_names_and_urls %>% | |
mutate(courses_from_timeschd_result = | |
transpose(courses_from_timeschd)[["result"]]) | |
# combine into data frame ----------------------------------------------- | |
# make a table of course prefix, number, URL to course catalog, | |
# and time schedule courses | |
dsm_courses_prefix_and_number <- | |
tibble(dsm_courses_prefix = dsm_courses_prefix, | |
dsm_courses_number = dsm_courses_number, | |
dsm_crscat_url = dsm_crscat_url) %>% | |
mutate(dsm_course_linked_text = | |
str_c("<a href='", dsm_crscat_url, "'>", | |
dsm_courses_prefix, " ", | |
dsm_courses_number, "</a>")) %>% | |
left_join(cas_program_names_and_urls_offered, | |
by = c("dsm_courses_prefix" = "cas_prefix")) | |
# check to see if the dsm course is offered in the term? | |
dsm_courses_prefix_and_number_offered <- | |
dsm_courses_prefix_and_number %>% | |
mutate(course_offered_yes_no = | |
str_detect(courses_from_timeschd_result, | |
dsm_courses_number)) | |
dsm_courses_prefix_and_number_offered %>% | |
filter(course_offered_yes_no) %>% | |
distinct(dsm_course_linked_text, .keep_all = TRUE) %>% | |
select(dsm_courses_prefix, | |
dsm_courses_number, | |
dsm_crscat_url, | |
dsm_course_linked_text) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment