backup-github-loop.sh

#!/bin/bash 
# A simple script to backup an organization's GitHub repositories.

GHBU_BACKUP_DIR=${GHBU_BACKUP_DIR-"/media/github_backup/bash_backup"}                  # where to place the backup files
GHBU_ORG=${GHBU_ORG-"YOUR_ORG"}                                   # the GitHub organization whose repos will be backed up
                                                                     # (if you're backing up a user's repos instead, this should be your GitHub username)
GHBU_UNAME=${GHBU_UNAME-"YOUR_USERNAME"}                               # the username of a GitHub account (to use with the GitHub API)
GHBU_PASSWD=${GHBU_PASSWD-"YOUR_PASSWORD"}                             # the password for that account 
GHBU_GITHOST=${GHBU_GITHOST-"github.com"}                            # the GitHub hostname (see comments)
GHBU_PRUNE_OLD=${GHBU_PRUNE_OLD-true}                                # when `true`, old backups will be deleted
GHBU_PRUNE_AFTER_N_DAYS=${GHBU_PRUNE_AFTER_N_DAYS-30}                 # the min age (in days) of backup files to delete
GHBU_SILENT=${GHBU_SILENT-false}                                     # when `true`, only show error messages 
GHBU_API=${GHBU_API-"https://api.github.com"}                        # base URI for the GitHub API
#GHBU_GIT_CLONE_CMD="git clone --quiet --mirror git@${GHBU_GITHOST}:" # base command to use to clone GitHub repos
GHBU_GIT_CLONE_CMD="git clone --mirror git@${GHBU_GITHOST}:" # base command to use to clone GitHub repos
PERPAGE="?per_page=100"
TSTAMP=`date "+%Y%m%d-%H%M"`

# The function `check` will exit the script if the given command fails.
function check {
  "$@"
  status=$?
  if [ $status -ne 0 ]; then
    echo "ERROR: Encountered error (${status}) while running the following:" >&2
    echo "           $@"  >&2
    echo "       (at line ${BASH_LINENO[0]} of file $0.)"  >&2
    echo "       Aborting." >&2
    exit $status
  fi
}

# The function `tgz` will create a gzipped tar archive of the specified file ($1) and then remove the original
function tgz {
   check tar zcf $1.tar.gz $1 && check rm -rf $1
}

$GHBU_SILENT || (echo "" && echo "=== INITIALIZING ===" && echo "")

$GHBU_SILENT || echo "Using backup directory $GHBU_BACKUP_DIR"
check mkdir -p $GHBU_BACKUP_DIR

$GHBU_SILENT || echo -n "Fetching list of repositories for ${GHBU_ORG}..."

REPOCOUNT=100

until [ $REPOCOUNT -ne 100 ]; do
        ((PAGE++))
	echo "" && echo "=== Starting repo list of page $PAGE ==="
        REPOLIST=`check curl --silent -u $GHBU_UNAME:$GHBU_PASSWD "${GHBU_API}/orgs/${GHBU_ORG}/repos${PERPAGE}&page=${PAGE}" -q | check grep "\"name\"" | check awk -F': "' '{print $2}' | check sed -e 's/",//g'`
	REPOCOUNT=`echo $REPOLIST | wc -w`
        echo "=== Repos in page $PAGE: `echo $REPOCOUNT` ==="
        echo "=== List of Repos for page $PAGE ==="
	echo "" && echo $REPOLIST

		$GHBU_SILENT || echo "found `echo $REPOLIST | wc -w` repositories."


		$GHBU_SILENT || (echo "" && echo "=== BACKING UP $REPOCOUNT REPOS FROM PAGE $PAGE ===" && echo "")

	for REPO in $REPOLIST; do
		   $GHBU_SILENT || echo "Backing up ${GHBU_ORG}/${REPO}"
		   check ${GHBU_GIT_CLONE_CMD}${GHBU_ORG}/${REPO}.git ${GHBU_BACKUP_DIR}/${GHBU_ORG}-${REPO}-${TSTAMP}.git && tgz ${GHBU_BACKUP_DIR}/${GHBU_ORG}-${REPO}-${TSTAMP}.git

		   $GHBU_SILENT || echo "Backing up ${GHBU_ORG}/${REPO}.wiki (if any)"
		   ${GHBU_GIT_CLONE_CMD}${GHBU_ORG}/${REPO}.wiki.git ${GHBU_BACKUP_DIR}/${GHBU_ORG}-${REPO}.wiki-${TSTAMP}.git 2>/dev/null && tgz ${GHBU_BACKUP_DIR}/${GHBU_ORG}-${REPO}.wiki-${TSTAMP}.git

		   $GHBU_SILENT || echo "Backing up ${GHBU_ORG}/${REPO} issues"
		   check curl --silent -u $GHBU_UNAME:$GHBU_PASSWD ${GHBU_API}/repos/${GHBU_ORG}/${REPO}/issues -q > ${GHBU_BACKUP_DIR}/${GHBU_ORG}-${REPO}.issues-${TSTAMP} && tgz ${GHBU_BACKUP_DIR}/${GHBU_ORG}-${REPO}.issues-${TSTAMP}
	sleep 1
	done

	if $GHBU_PRUNE_OLD; then
		  $GHBU_SILENT || (echo "" && echo "=== Checking $REPOCOUNT REPOS for repos older than ${GHBU_PRUNE_AFTER_N_DAYS} from page $PAGE ===" && echo "")
		  $GHBU_SILENT || echo "Pruning backup files ${GHBU_PRUNE_AFTER_N_DAYS} days old or older."
		  $GHBU_SILENT || echo "Found `find $GHBU_BACKUP_DIR -name '*.tar.gz' -mtime +$GHBU_PRUNE_AFTER_N_DAYS | wc -l` files to prune."
		  find $GHBU_BACKUP_DIR -name '*.tar.gz' -mtime +$GHBU_PRUNE_AFTER_N_DAYS -exec rm -fv {} > /dev/null \;
	sleep 1
	fi

	echo "" && echo "=== Moving to next page ==="

        done

echo "=== Total number of pages was: $PAGE ==="
echo "=== Finishing up ==="

# NOTE: if you're backing up a *user's* repos, not an organizations, use this instead:
# REPOLIST=`check curl --silent -u $GHBU_UNAME:$GHBU_PASSWD ${GHBU_API}/user/repos -q | check grep "\"name\"" | check awk -F': "' '{print $2}' | check sed -e 's/",//g'`


$GHBU_SILENT || (echo "" && echo "=== DONE ===" && echo "")
$GHBU_SILENT || (echo "GitHub backup completed." && echo "")

*You must have SSH keys configured for your user in order to use this

Github by default pulls 30 repos each API call, but you can change this by adding "?per_page=100" to the call. However, you can only call a maximum of 100 repos per page, so it is necessary to parse multiple pages to complete all repos.

I added an until loop into this script to allow for parsing of all repos (it stops when the number of repos in a page is less than 100, i.e. the next page will be blank).