markasoftware

#!/bin/bash

# This file is released under the GNU Public License v3

# ACM scraper during coronavirus
# Will skip existing PDFs to speed up a resumed download
# Get the link to the first issue in the journal/SIG/etc, then the scraper will use "next" links to traverse
# Usage: ./acm.bash first_issue_link output_dir
# Eg, ./acm.bash https://dl.acm.org/toc/siggraph/1969/3/3 /media/mass/siggraph to download all SIGGRAPH PDFs
# note: acm does BLOCK IPs after a few hundred PDFs! Uncommenting the sleep statement below to slow things down may help, but I haven't tested

markasoftware

;; Copyright (c) 2020 Mark Polyakov
;; Released under the WTFPL (Do What The Fuck You Want To Public License)

(defvar *html-void-tags* '(:area :base :br :col :embed :hr :img :input :link
                              :meta :param :source :track :wbr)
  "String designators for self-closing/void tags.
https://html.spec.whatwg.org/multipage/syntax.html#void-elements")

(defvar *html-escapes*
  '(#\> ">"

markasoftware

############ If you are using DOCKER all-in-one image, create Dockerfile like:         ################
############ FROM openproject/openproject:16                                           ################
############ COPY ./enterprise_token.rb app/models/enterprise_token.rb                 ################

############ If you are runing a manual installation:                                  ################
############ REPLACE app/models/enterprise_token.rb in the source code with this file! ################
############ also be sure to RESTART OpenProject after replacing the file.             ################

############ If using some other set up (eg docker-compose), read the comments on      ################
############ https://gist.github.com/markasoftware/f5b2e55a2c2e3abb1f9eefcdf0bfff45    ################

markasoftware

#!/bin/bash

# Use input redirection. Copies straight to clipboard.
# Can paste into spreadsheet applications directly.
# MIT licensed.

gawk '
BEGIN { FPAT = "([^,]*)|(\"[^\"]+\")" }
NR>1 { print "" }
{