export-issues.py

"""
ref. https://gist.github.com/mike-ward/23dab967feaf71bde2c1

Exports Issues from a specified repository to a CSV file

- Github API v3: https://developer.github.com/v3/gists/
- ZenHub API: https://github.com/ZenHubIO/API
"""
import csv
import requests
import sys

GH_REPO = '<repo name>'  # format is username/repo
GH_ISSUES_URL = 'https://api.github.com/repos/%s/issues' % GH_REPO
GH_TOKEN = '<github personal access token>'
GH_HEADERS = { 'Authorization': 'token %s' % GH_TOKEN }
GH_PARAMS = { 'state': 'open' }

ZH_REPO = '<repo id in zenhub>'
ZH_TOKEN = '<zenhub api token>'
ZH_ISSUE_URL = 'https://api.zenhub.io/p1/repositories/%s/issues' % ZH_REPO
ZH_HEADERS = { 'X-Authentication-Token': ZH_TOKEN }

def write_issues(gh_response):
    "output a list of issues to csv"
    if not gh_response.status_code == 200:
        print(gh_response.text, flush=True)
        raise Exception(gh_response.status_code)
    for issue in gh_response.json():
        labels = [x['name'] for x in issue['labels']]
        pipeline = pipeline_from_zenhub(issue['number'])
        print((issue['number'], labels, pipeline))
        csvout.writerow([pipeline, issue['number'], issue['title'], issue['body'], issue['created_at'], issue['updated_at'], *labels])

def pipeline_from_zenhub(issue_no):
    zh_url = ZH_ISSUE_URL + '/%d' % issue_no
    zh_res = requests.get(zh_url, headers=ZH_HEADERS)
    if not zh_res.status_code == 200:
        print('zenhub api with %s' % zh_url, flush=True)
        raise Exception(zh_res.status_code)
    return zh_res.json()['pipeline']['name']

def extract_paging(gh_response):
    return dict(
        [(rel[6:-1], url[url.index('<')+1:-1]) for url, rel in
            [link.split(';') for link in
                gh_response.headers['link'].split(',')]])

filename = '%s-issues.csv' % (GH_REPO.replace('/', '-'))

with open(filename, 'w', encoding='utf_8_sig') as csvfile:
    r = requests.get(GH_ISSUES_URL, headers=GH_HEADERS, params=GH_PARAMS)
    csvout = csv.writer(csvfile)
    csvout.writerow(('pipeline', 'id', 'title', 'body', 'created_at', 'updated_at', 'labels'))
    write_issues(r)

    pages = extract_paging(r)
    print(pages)

    #more pages? examine the 'link' header returned
    if 'link' in r.headers:
        while pages['last'] != pages['next']:
            r = requests.get(pages['next'], headers=GH_HEADERS)
            write_issues(r)
            pages = extract_paging(r)
            print(pages, flush=True)
        r = requests.get(pages['next'], headers=GH_HEADERS)
        write_issues(r)