Export Issues from Github repo to CSV (API v3)

.gitignore

user_data.sh

export_repo_issues_to_csv.py

"""
Exports Issues from a specified repository to a CSV file

Uses basic authentication (Github username + password) to retrieve Issues
from a repository that username has access to. Supports Github API v3.
"""
from __future__ import print_function
import csv
import requests
import sys
import os

GITHUB_USER = os.environ["GITHUB_USER"]
GITHUB_PASSWORD = os.environ["GITHUB_PASSWORD"]
REPO = os.environ["REPO"]  # format is username/repo
ISSUES_FOR_REPO_URL = 'https://api.github.com/repos/%s/issues' % REPO
AUTH = (GITHUB_USER, GITHUB_PASSWORD)


def write_issues(response):
    "output a list of issues to csv"
    response.raise_for_status()
    for issue in response.json():
        csvout.writerow(
            [issue['number'],
             issue['title'].encode('utf-8'),
             issue['body'].encode('utf-8'),
             issue['created_at'],
             issue['updated_at']])


r = requests.get(ISSUES_FOR_REPO_URL, auth=AUTH)
csvfile = '%s-issues.csv' % (REPO.replace('/', '-'))
csvout = csv.writer(open(csvfile, 'wb'))
csvout.writerow(('id', 'Title', 'Body', 'Created At', 'Updated At'))
write_issues(r)

# more pages? examine the 'link' header returned
if 'link' in r.headers:
    pages = dict(
        [(rel[6:-1], url[url.index('<')+1:-1]) for url, rel in
            [link.split(';') for link in
                r.headers['link'].split(',')]])
    while 'last' in pages and 'next' in pages:
        r = requests.get(pages['next'], auth=AUTH)
        try:
            write_issues(r)
        except requests.HTTPError as err:
            print(err, file=sys.stderr)
        if pages['next'] == pages['last']:
            break

export_repo_issues_to_csv.sh

#!/bin/bash

scriptdir=`dirname $(readlink -f $0)`
source "$scriptdir"/user_data.sh;
export REPO="$1";  # format is username/repo
python "$scriptdir"/export_repo_issues_to_csv.py

user_data_skeleton.sh

export GITHUB_USER=
export GITHUB_PASSWORD=