Exports *all* issues from a github repository into a `pickle` file

github-issues-export.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
import cPickle as pickle


GITHUB_USER = ''
GITHUB_PASSWORD = ''
REPO = ''  # format is username/repo
ISSUES_FOR_REPO_URL = 'https://api.github.com/repos/%s/issues?state=all' % REPO
AUTH = (GITHUB_USER, GITHUB_PASSWORD)

f = open('issues-dump.p', 'wb')

def write_issues(response):
    "output a list of issues to csv"
    if not r.status_code == 200:
        raise Exception(r.status_code)
    print 'writing ...'
    print len(r.json())
    pickle.dump(r.json(), f)


r = requests.get(ISSUES_FOR_REPO_URL, auth=AUTH)
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:
        print 'getting page : ' + pages['next']
        r = requests.get(pages['next'], auth=AUTH)
        write_issues(r)
        pages = dict(
            [(rel[6:-1], url[url.index('<')+1:-1]) for url, rel in
                [link.split(';') for link in
                    r.headers['link'].split(',')]])

f.close()