Last active
July 15, 2024 18:42
-
-
Save knzai/75702a336a25646e6c0039f96d5732b9 to your computer and use it in GitHub Desktop.
curlable bash script to grab google drive file exports from their api, eg grabbing pdfs of gdocs
This file contains hidden or 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
#!/usr/bin/env bash | |
set -Eeo pipefail | |
#============================ | |
# CONSTANTS & DEFAULTS | |
#============================ | |
#constants | |
readonly VERSION_NUM='1.2.0' | |
readonly SCRIPT='ggdrive.sh' | |
#in case terminal doesn't support colors - readonly after setup_colors runs | |
RESET='' RED='' GREEN='' BLUE='' PURPLE='' CYAN='' YELLOW='' | |
#environment variables | |
#G_API_KEY | |
#IFS # shell built-in Internal Field Separator | |
#defaults | |
#unset csv_file | |
export=false | |
g_api='https://www.googleapis.com/drive/v2' | |
tempfile='tempfile' | |
user_agent='gist.github.com/knzai/75702a336a25646e6c0039f96d5732b9' | |
#============================ | |
# USAGE & METADATA | |
#============================ | |
usage() { | |
cat <<-EOF | |
${CYAN}Name:${RESET} $(script_name) ($VERSION_NUM) | |
${CYAN}Description:${RESET} Download google drive file exports, eg gdocs -> pdf | |
${CYAN}Usage:${RESET} | |
${RED}<G_API_KEY=XXXX>${RESET} ./$(script_name) ${YELLOW}[-h, --help] [-v] [-e] [-g ${RED}<g_api>${YELLOW}] [-t ${RED}<tempfile>${YELLOW}] [-u ${RED}<user_agent>${YELLOW}] [csv_file]${RESET} | |
EOF | |
for i in "$@"; do | |
case $i in | |
vars) cat <<-EOF | |
${CYAN}Environoment variables:${RESET} | |
${RED}G_API_KEY${RESET} REQUIRED Google Cloud API Key with access to Google Drive API | |
${CYAN}Arguments:${RESET} | |
${YELLOW}[csv_file]${RESET} Path/to/file.csv. Leave blank for NOOP. | |
${CYAN}Flags:${RESET} | |
${YELLOW}[-e, --export]${RESET} Export functions. Use w/o [csv_file] for custom handling | |
${YELLOW}[-v, --version] ${RESET} Output version info. Long form provides more metadata | |
${YELLOW}[-h, --help]${RESET} Output help. Long form provides more info, examples | |
${CYAN}Options${RESET} | |
${BLUE}#Specify endpoint of the google drive api${RESET} | |
${YELLOW}[-g, --g_api] ${RED}<arg>${RESET} {'https://www.googleapis.com/drive/v2'} | |
${BLUE}#If you want to be particular about the temporary file${RESET} | |
${YELLOW}[-t, --tempfile] ${RED}<arg>${RESET} {tempfile} | |
${BLUE}#I don't think Google actually cares, but hey${RESET} | |
${YELLOW}[-u, --user_agent] ${RED}<arg>${RESET} {'gist.github.com/knzai/75702a336a25646e6c0039f96d5732b9'} | |
EOF | |
shift ;; | |
eg) cat <<-EOF | |
${CYAN}Examples${RESET} | |
${BLUE}# Standard usage${RESET} | |
./$(script_name) path/to/csv | |
${BLUE}# Do nothing except export functions for your own use${RESET} | |
./$(script_name) -e | |
${BLUE}# Specify a different version of the google drive api${RESET} | |
./$(script_name) -g https://www.googleapis.com/drive/v3 path/to/csv | |
${CYAN}Curl examples${RESET} | |
${BLUE}#standard run directly from the pipe | |
curl -s -L https://gist.github.com/knzai/75702a336a25646e6c0039f96d5732b9/raw | bash -s -- gdrive_files.csv | |
${BLUE}#only download if it doesn't exist, then run it${RESET} - script_name harcoded for ease of copying from gist. Update if needed | |
[ -f ggdrive.sh ] || curl -s -L https://gist.github.com/knzai/75702a336a25646e6c0039f96d5732b9/raw > ggdrive.sh && bash ggdrive.sh gdrive_files.csv | |
${BLUE}#my fave bootstrapping: if there isn't a tempfile, download to one and run; easy csv_file path at front${RESET} | |
csv_file=gdrive_files.csv && [[ -f \$ggdrivetemp || ggdrivetemp=\$(mktemp -t ggdriveXXXXXXXXXX.sh) ]] \\ | |
&& [[ -s \$ggdrivetemp ]] || curl -s -L https://gist.github.com/knzai/75702a336a25646e6c0039f96d5732b9/raw \\ | |
> \$ggdrivetemp && bash \$ggdrivetemp \$csv_file | |
EOF | |
shift ;; | |
esac | |
done | |
} | |
version() { | |
msg "$(script_name) $VERSION_NUM" | |
if [ ! $# -eq 0 ]; then | |
cat <<-EOF | |
${CYAN}Authour & Copyright:${RESET} | |
${BLUE}version${RESET} $(script_name) $VERSION_NUM | |
${BLUE}author${RESET} Kenzi Connor | |
${BLUE}copyright${RESET} Copyright (c) Public Domain | |
${BLUE}license${RESET} Public Domain via Unlicense (see footer) | |
${BLUE}site${RESET} knz.ai/ggdrive | |
${BLUE}source${RESET} gist.github.com/knzai/75702a336a25646e6c0039f96d5732b9 | |
${CYAN}Version history:${RESET} | |
${BLUE}2024/07/10${RESET} : 0.0.1 : Script creation | |
${BLUE}2024/07/11${RESET} : 0.0.2 : Cleaned up, comment, add help and usage | |
${BLUE}2024/07/12${RESET} : 0.0.3 : Simplify usage() to make curling easier | |
${BLUE}2024/07/12${RESET} : 1.0.0 : BREAKING Rename env var for clarity | |
${BLUE}2024/07/12${RESET} : 1.1.0 : Changed --help and --version usage | |
${BLUE}2024/07/13${RESET} : 1.2.0 : More usage() improvements | |
EOF | |
fi | |
} | |
#============================ | |
# MESSAGING & COLORS | |
#============================ | |
die() { echo "$*" >&2; exit 2; } | |
msg() { echo >&2 -e "${1-}"; } | |
script_name() { echo "${GREEN}$SCRIPT${RESET}"; } | |
setup_colors() { | |
if [[ -t 2 ]] && [[ -z "${NO_COLOR-}" ]] && [[ "${TERM-}" != "dumb" ]]; then | |
RESET=$(tput setaf 7) RED=$(tput setaf 1) GREEN=$(tput setaf 2) BLUE=$(tput setaf 4) CYAN=$(tput setaf 6) YELLOW=$(tput setaf 3) | |
fi | |
readonly RESET RED GREEN BLUE PURPLE CYAN YELLOW | |
} | |
#============================ | |
# PARSE PARAMETERS | |
#============================ | |
parse_params() { | |
if [ $# -eq 0 ]; then usage && exit; fi; | |
#flags and options | |
while getopts eg:t:u:hv-: OPT; do | |
# support long options: https://stackoverflow.com/a/28466267/519360 | |
if [ "$OPT" = "-" ]; then # long option: reformulate OPT and OPTARG | |
OPT="${OPTARG%%=*}" # extract long option name | |
OPTARG="${OPTARG#"$OPT"}" # extract long option argument (may be empty) | |
OPTARG="${OPTARG#=}" # if long option argument, remove assigning `=` | |
fi | |
case "$OPT" in | |
e|export ) export=true;; | |
g|g_api ) g_api="$OPTARG";; | |
t|tempfile ) tempfile="$OPTARG";; | |
u|user_agent) user_agent="$OPTARG";; | |
h ) usage 'vars' ;; | |
help ) usage 'vars' 'eg' ;; | |
v ) version ;; | |
version ) version 'full' ;; | |
* ) exit 2;; | |
esac | |
done | |
shift $((OPTIND-1)) # remove parsed options and args from $@ list | |
#positional args | |
csv_file=$1 | |
return 0 | |
} | |
#============================ | |
# ALIASES AND FUNCTIONS | |
#============================ | |
get_gdrive_files() { | |
if [ ! -f $1 ]; then die "$1 file not found"; fi | |
oldifs=$IFS | |
IFS=',' | |
while read gd_id mime dest min_size | |
do | |
gdrive_export $gd_id $mime | |
replace_if_valid $dest $min_size | |
done < $1 | |
IFS=$oldifs | |
} | |
gdrive_export() { | |
#$1: google_file_id | |
#$2: mime_type | |
wget -nv -O $tempfile --user-agent=$user_agent "$g_api/files/$1/export?mimeType=$2&key=$G_API_KEY" | |
} | |
replace_if_valid() { | |
#$1: dest | |
#$2: min_size | |
if [ $(du -k $tempfile | cut -f1) -gt $2 ]; then | |
mv $tempfile "$1" | |
else | |
die "Problem fetching file" | |
fi | |
} | |
#============================ | |
# MAIN | |
#============================ | |
main() { | |
if [ $csv_file ]; then | |
get_gdrive_files $csv_file | |
elif $export; then | |
export -f get_gdrive_files | |
export -f gdrive_export | |
export -f replace_if_valid | |
fi | |
} | |
setup_colors | |
parse_params "$@" | |
main | |
#=============================================================================== | |
# LICENSE: Public Domain via Unlicense | |
# | |
# This is free and unencumbered software released into the public domain. | |
# | |
# Anyone is free to copy, modify, publish, use, compile, sell, or | |
# distribute this software, either in source code form or as a compiled | |
# binary, for any purpose, commercial or non-commercial, and by any | |
# means. | |
# | |
# In jurisdictions that recognize copyright laws, the author or authors | |
# of this software dedicate any and all copyright interest in the | |
# software to the public domain. We make this dedication for the benefit | |
# of the public at large and to the detriment of our heirs and | |
# successors. We intend this dedication to be an overt act of | |
# relinquishment in perpetuity of all present and future rights to this | |
# software under copyright law. | |
# | |
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, | |
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF | |
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. | |
# IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR | |
# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, | |
# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR | |
# OTHER DEALINGS IN THE SOFTWARE. | |
# | |
# For more information, please refer to <http://unlicense.org/> |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Maybe I'll crack the curl usage without having to pipe into a tempfile (head calls used to parse the usage info easier with a file to aim it at), or at least make and cleanup the tmpfile within the script if called from a pipe. But not today.
ETA: Or I'll just strip out the complexity for a simple usage() function instead, which I did.