-
-
Save gzt/85dcb4df806aaf906a942b4894bbae51 to your computer and use it in GitHub Desktop.
get PDFs from some site
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
####### This presumes you have a .bib file which has, for each | |
####### bibliography entry, a legal file name as a key and a DOI | |
####### and that you have a directory you want to save the files in. | |
####### If your bibtex entry is like | |
####### @Article{Bob_1980, ..... } | |
####### then the file will be saved as Bob_1980.pdf. | |
####### You must have a DOI for each entry. | |
bibfile = "/path/to/bib/file.bib" | |
savedir = "/path/to/save/dir/" | |
tags = gsub("^.*\\{(.*),", "\\1", grep("@", readLines(bibfile), value = TRUE)) | |
doilist = gsub("^.*\\{(.*)\\},", "\\1", grep("doi.*=", readLines(bibfile), value = TRUE)) | |
filelist = paste0(savedir, tags, ".pdf") | |
urllist = paste0("https://sci-hub.tw/", doilist) | |
pdfpattern = "https://.*pdf\\?download=true" | |
if (length(doilist) != length(tags)) stop("Error: missing DOIs") | |
for (i in 1:length(doilist)) { | |
if (!file.exists(filelist[i])) { | |
scihubhtml = readLines(urllist[i]) | |
pdfurl = gsub("^.*(https.*true).*", "\\1", grep(pdfpattern, scihubhtml, value = TRUE)) | |
####### skip file if no pdf found | |
if(length(pdfurl) > 0) download.file(pdfurl, destfile = filelist[i], method = "auto") | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment