Skip to content

Improve GWAS Catalog scraping robustness and documentation #24

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
Copilot wants to merge 2 commits into
base: main
Choose a base branch
from
Draft

Improve GWAS Catalog scraping robustness and documentation #24

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
fa7b4e0
Initial plan
Copilot Jan 6, 2026
9b66810
Fix GWAS catalog scraping helper
Copilot Jan 6, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
35 changes: 29 additions & 6 deletions R/gwas-catalog.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,6 +3,10 @@
#' @param study_id A single character string with study ID, e.g. "GCST90475332"
#' @param quiet TRUE/FALSE - controls progress bar for downloading
#'
#' @details Uses internal scraping helpers to locate harmonised summary
#' statistics when they are available; otherwise falls back to any matching
#' summary statistics in the study directory.
#'
#' @returns a filepath to downloaded summary statistics
#' @export
#'
Expand Down Expand Up @@ -58,27 +62,46 @@ from_gwas_catalog <- function(study_id, quiet = FALSE) {
gwas_file
}

#' Scrape a directory listing and return matching entries
#'
#' @param url The directory URL to inspect.
#' @param pattern Regex pattern of file names to keep (set to NULL to keep all
#' files). Directory entries are always retained to allow recursive scraping.
#'
#' @return Character vector of matching file names and subdirectories.
#' @noRd
.href_drop_pattern <- "^\\?|^\\.{2}/|^/pub|^$"
.scrape <- function(url, pattern = "\\.(gz|tsv|yaml|tbi|log|txt)$") {
html_raw <- curl::curl_fetch_memory(url)$content
page <- xml2::read_html(rawToChar(html_raw))
hrefs <- rvest::html_attr(rvest::html_nodes(page, "a"), "href")
hrefs <- hrefs[!grepl("^\\?|^\\.{2}/|^/pub|^$", hrefs)]
hrefs <- hrefs[!is.na(hrefs) & !grepl(.href_drop_pattern, hrefs)]

dirs <- stringr::str_subset(hrefs, "/$")
files <- hrefs[!grepl("/$", hrefs)]

matches <- if (is.null(pattern)) files else stringr::str_subset(files, pattern)

unique(c(dirs, matches))
}


scrape_dir <- function(url, pattern = "\\.(gz|tsv|yaml|tbi|log|txt)$") {
files <- .scrape(url)
files <- .scrape(url, pattern)

if(any(grepl("harmonised/", files))) {
harmonised <- .scrape(file.path(url, files[grepl("harmonised/", files)]))
harmonised <- file.path(url, files[grepl("harmonised/", files)], harmonised)
harmonised_dir <- files[grepl("harmonised/", files)][1]
harmonised <- .scrape(
file.path(url, harmonised_dir),
pattern
)
harmonised <- file.path(url, harmonised_dir, harmonised)
files <- c(file.path(url, files[!grepl("harmonised/", files)]), harmonised)
} else {
files <- file.path(url, files)

}
files

files
}

check_sumstats_avail <- function(
Expand Down
4 changes: 4 additions & 0 deletions man/from_gwas_catalog.Rd
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

50 changes: 50 additions & 0 deletions tests/testthat/test-gwas-catalog.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,3 +10,53 @@ test_that("multiplication works", {


})

test_that(".scrape keeps directories and filters by pattern", {
html <- paste0(
"<html><body>",
"<a href=\"harmonised/\">harmonised</a>",
"<a href=\"results.tsv\">results</a>",
"<a href=\"notes.pdf\">notes</a>",
"<a href=\"../parent\">parent</a>",
"<a href=\"?query\">query</a>",
"</body></html>"
)

mock_fetch <- function(url) list(content = charToRaw(html))

result <- with_mocked_bindings(
tidyGWAS:::`.scrape`("http://example.com", pattern = "\\.(tsv|yaml)$"),
curl::curl_fetch_memory = mock_fetch
)

expect_equal(result, c("harmonised/", "results.tsv"))
})

test_that("scrape_dir retains harmonised files and applies patterns", {
base_links <- c("harmonised/", "main.tsv", "main.tbi", "readme.txt")
harmonised_links <- c("harmonised.tsv.gz", "meta.yaml", "other.log")

mock_scrape <- function(url, pattern) {
if (grepl("/harmonised/?$", url)) {
return(harmonised_links)
}
base_links
}

files <- with_mocked_bindings(
tidyGWAS:::scrape_dir("http://example.com"),
tidyGWAS:::`.scrape` = mock_scrape
)

expect_equal(
files,
c(
"http://example.com/main.tsv",
"http://example.com/main.tbi",
"http://example.com/readme.txt",
"http://example.com/harmonised/harmonised.tsv.gz",
"http://example.com/harmonised/meta.yaml",
"http://example.com/harmonised/other.log"
)
)
})