Export Issues from Github repo to CSV (API v3)

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
import icu #to install CFLAGS=-I/usr/local/opt/icu4c/include LDFLAGS=-L/usr/local/opt/icu4c/lib pip install pyicu


GITHUB_USER = ''
GITHUB_PASSWORD = ''
REPO = ''  # format is username/repo
ISSUES_FOR_REPO_URL = 'https://api.github.com/repos/%s/issues' % REPO
LABELS_FOR_REPO_URL = 'https://api.github.com/repos/%s/labels' % REPO
MILESTONE_FOR_REPO_URL = 'https://api.github.com/repos/%s/milestones' % REPO
AUTH = (GITHUB_USER, GITHUB_PASSWORD)

def write_issues(response, labels):
    "output a list of issues to csv"
    if not r.status_code == 200:
        raise Exception(r.status_code)
    for issue in r.json():
        issueLabels = issue['labels']
        issueLabelsStatus = []
        for label in labels:
            s = "No"
            for il in issueLabels:
                if il['name'] == label:
                    s = "Yes"
                    break
            issueLabelsStatus.append(s)

        if not 'pull_request' in issue:
            row = [issue['number'],
                '' if issue['assignee'] == None else issue['assignee']['login'],
                issue['title'].encode('utf-8'), 
                issue['body'].encode('utf-8'),
                '' if issue['milestone'] == None else issue['milestone']['title'],
                issue['url'],
                issue['created_at'], 
                issue['updated_at']]

            csvout.writerow(row + issueLabelsStatus)

def get_labels(response):
    "get labels"
    labels = []
    if not response.status_code == 200:
        raise Exception(r.status_code)
    for label in response.json():
        labels.append(label['name'])
    return sorted(labels)

def write_milestones(response):
    "output a list of milestones to csv"

    if not r.status_code == 200:
            raise Exception(r.status_code)

    for milestone in r.json():

        row = [milestone[u'title'].encode('utf-8'),
            milestone[u'state'].encode('utf-8'),
            '' if milestone['due_on'] == None else milestone['due_on'],
            milestone[u'description'].encode('utf-8'),
            milestone[u'url'].encode('utf-8')]

        csvout.writerow(row)

labels = requests.get(LABELS_FOR_REPO_URL, auth=AUTH)
labels = get_labels(labels)

r = requests.get(ISSUES_FOR_REPO_URL, auth=AUTH)
csvfile = '%s-issues.csv' % (REPO.replace('/', '-'))
csvout = csv.writer(open(csvfile, 'wb'))
headers = ['ID', 'Asignee', 'Title', 'Body', 'Milestone', 'Url', 'Created At', 'Updated At']
csvout.writerow(headers + labels)
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:
        r = requests.get(pages['next'], auth=AUTH)
        write_issues(r, labels)
        if pages['next'] == pages['last']:
            break

r = requests.get(MILESTONE_FOR_REPO_URL, auth=AUTH)
csvfile = '%s-milestones.csv' % (REPO.replace('/', '-'))
csvout = csv.writer(open(csvfile, 'wb'))
headers = ['Title', 'State', 'Due On', 'Description', 'Url']
csvout.writerow(headers)
write_milestones(r)