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.
"""
import csv
import requests


GITHUB_USER = ''
GITHUB_PASSWORD = ''
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, all_labels):
    "output a list of issues to csv"
    if not r.status_code == 200:
        raise Exception(r.status_code)
    for issue in r.json():
        title = issue['title'].encode('utf-8')
        labels = map(lambda l: l['name'], issue['labels'])
        if issue['body'] == None:
          body = ""
        else:
          body = issue['body'].encode('utf-8')

        print "Writing issue {}".format(title)
        if issue['milestone'] == None:
          milestone = ""
        else:
          milestone = issue['milestone']['title']
        row = [issue['number'], title, body, issue['created_at'], issue['updated_at'], milestone]
        for label in all_labels:
          if label in labels:
            row.append(label)
          else:
            row.append("")
        csvout.writerow(row)

# Get all the labels
r = requests.get("https://api.github.com/repos/%s/labels" % REPO, auth=AUTH).json()
labels = map(lambda l: l['name'], r)

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', 'Milestone'))
write_issues(r, labels)

#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:
        pages = dict(
            [(rel[6:-1], url[url.index('<')+1:-1]) for url, rel in
                [link.split(';') for link in
                    r.headers['link'].split(',')]])
        r = requests.get(pages['next'], auth=AUTH)
        write_issues(r, labels)
        if pages['next'] == pages['last']:
            break