Export Issues from Github repo to CSV (API v3)

github_issues_to_csv.py

"""
Exports issues from a list of repositories to individual csv files.
Uses basic authentication (Github username + password) to retrieve issues
from a repository that username has access to. Supports Github API v3.
Forked from: unbracketed/export_repo_issues_to_csv.py
"""
import argparse
import csv
from getpass import getpass
import requests

# encoding=utf8
import sys
reload(sys)
sys.setdefaultencoding('utf8')

auth = None
state = 'open'


def write_issues(r, csvout):
    """Parses JSON response and writes to CSV."""
    if r.status_code != 200:
        raise Exception(r.status_code)
    for issue in r.json():
        if 'pull_request' not in issue:
            labels = ', '.join([l['name'] for l in issue['labels']])
            date = issue['created_at'].split('T')[0]
            # Change the following line to write out additional fields
            csvout.writerow([labels, issue['number'], issue['title'], issue['state'], date,
                             issue['html_url']])


def get_issues(name):
    """Requests issues from GitHub API and writes to CSV file."""
    url = 'https://api.github.com/repos/{}/issues?state={}'.format(name, state)
    r = requests.get(url, auth=auth)

    csvfilename = '{}-issues.csv'.format(name.replace('/', '-'))
    with open(csvfilename, 'w') as csvfile:
        csvout = csv.writer(csvfile)
        csvout.writerow(['Labels', 'Number', 'Title', 'State', 'Date', 'URL'])
        write_issues(r, csvout)

        # Multiple requests are required if response is paged
        if 'link' in r.headers:
            pages = {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 = {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, csvout)
                if pages['next'] == pages['last']:
                    break


parser = argparse.ArgumentParser(description="Write GitHub repository issues "
                                             "to CSV file.")
parser.add_argument('repositories', nargs='+', help="Repository names, "
                    "formatted as 'username/repo'")
parser.add_argument('--all', action='store_true', help="Returns both open "
                    "and closed issues.")
args = parser.parse_args()

if args.all:
    state = 'all'

username = input("Username for 'https://github.com': ")
password = getpass("Password for 'https://{}@github.com': ".format(username))
auth = (username, password)
for repository in args.repositories:
    get_issues(repository)

Traceback (most recent call last):
File "export repository.py", line 72, in
get_issues(repository)
File "export repository.py", line 38, in get_issues
write_issues(r, csvout)
File "export repository.py", line 19, in write_issues
raise Exception(r.status_code)
Exception: 401

Getting this error

@manu4387 - what are the steps to reproduce? On OSX you may need to try different versions of python - try running the command using python3 instead of python

OK let me try that.

…

On Thu, 24 Oct 2019 at 17:10, Andy Dempster ***@***.***> wrote: @manu4387 <https://github.com/manu4387> - what are the steps to reproduce? On OSX you may need to try different versions of python - try running the command using python3 instead of python — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <https://gist.github.com/87780652b4ec37794dc6992935556062?email_source=notifications&email_token=ANOUZL2N637ZI7DR6E474ODQQGCSXA5CNFSM4JECCHOKYY3PNVWWK3TUL52HS4DFVNDWS43UINXW23LFNZ2KUY3PNVWWK3TUL5UWJTQAF3BQY#gistcomment-3064588>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/ANOUZL6GJZ7QV5N4H5KRLN3QQGCSXANCNFSM4JECCHOA> .

-- Manu Agarwal Senior Implementation Consultant, Siren A Unit 3, GTC, Mervue Business Park, Galway, H91 CR20, Ireland P +353 (0)91 704 885 <+353+(0)91+704+885> M +91-7620037800 <+91-7620037800> E [email protected] <[email protected]> W www.siren.io <http://www.siren.io?utm_source=WiseStamp&utm_medium=email&utm_term=&utm_content=&utm_campaign=signature> <https://twitter.com/sirensearch?utm_source=WiseStamp&utm_medium=email&utm_term=&utm_content=&utm_campaign=signature> <https://www.youtube.com/channel/UCKGsC-vD28r7hW6T9QspKPA?utm_source=WiseStamp&utm_medium=email&utm_term=&utm_content=&utm_campaign=signature> <https://vimeo.com/sirenio?utm_source=WiseStamp&utm_medium=email&utm_term=&utm_content=&utm_campaign=signature> <https://www.facebook.com/sirensearch?utm_source=WiseStamp&utm_medium=email&utm_term=&utm_content=&utm_campaign=signature> <https://www.linkedin.com/company/11117365?utm_source=WiseStamp&utm_medium=email&utm_term=&utm_content=&utm_campaign=signature>

I am getting this error with the above code:
Traceback (most recent call last):
File "C:\Data\GISData\PythonCode\githubExtract\test3.py", line 14, in
reload(sys)
NameError: name 'reload' is not defined

@froberts

Scripts python github_issues_to_csv.py
usage: github_issues_to_csv.py [-h] [--all] repositories [repositories ...]
github_issues_to_csv.py: error: too few arguments
➜  Scripts python3 github_issues_to_csv.py
Traceback (most recent call last):
  File "github_issues_to_csv.py", line 14, in <module>
    reload(sys)
NameError: name 'reload' is not defined
➜  Scripts

@froberts

Looking at the 2to3 automated updater
reload
Converts reload() to importlib.reload().

So if you're running v3 try that - otherwise run in Python 2