fetch-gh-issues-as-csv.py

# https://gist.github.com/unbracketed/3380407
"""
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.
"""
import sys
import csv
import requests


GITHUB_USER = ''
GITHUB_PASSWORD = ''
REPO = ''  # format is username/repo
LABEL = ''

PARAMS = ['GITHUB_USER', 'GITHUB_PASSWORD', 'REPO', 'LABEL']

# Add args -- user, pass, repo
for arg, name in zip(sys.argv[1:], PARAMS):
    globals()[name] = arg

if not all([globals()[x] for x in PARAMS]):
    print("You need to pass user, password, repo, label")
    sys.exit(1)


ISSUES_FOR_REPO_URL = 'https://api.github.com/repos/%s/issues' % REPO
AUTH = (GITHUB_USER, GITHUB_PASSWORD)

SEEN_ISSUES = set()
ISSUE_COUNT = 0

def write_issues(response):
    "output a list of issues to csv"
    global ISSUE_COUNT
    if not r.status_code == 200:
        raise Exception(r.status_code)
    for issue in r.json():
        if issue['id'] in SEEN_ISSUES:
            print "Already seen", issue['id'], "!!"
            sys.exit(1)
        SEEN_ISSUES.add(issue['id'])
        labels = issue['labels']
        if LABEL in [x['name'] for x in issue['labels']]:
            ISSUE_COUNT += 1
            sys.stderr.write("Wrote {} issues to CSV...\r".format(ISSUE_COUNT))
            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 = {}
    def update_pages(headers):
        links = headers['link'].split(',')
        link_pairs = [link.split(';') for link in links]
        kvs = [(rel[6:-1], url[url.index('<')+1:-1]) for url, rel in link_pairs]
        pages.update(dict(kvs))

    update_pages(r.headers)
    while ('last' in pages and 'next' in pages and pages['next'] != pages['last']):
        update_pages(r.headers)
        r = requests.get(pages['next'], auth=AUTH)
        write_issues(r)

print "\nDone! Output in", csvfile