Release version 0.36.0

Add circleci config

.circleci/config.yml

@@ -0,0 +1,23 @@
+version: 2.1
+
+orbs:
+  python: circleci/python@0.3.2
+
+jobs:
+  build-and-test:
+    executor: python/default
+    steps:
+      - checkout
+      - python/load-cache
+      - run:
+          command: pip install flake8
+          name: Install dependencies
+      - python/save-cache
+      - run:
+          command: flake8 --ignore=E501
+          name: Lint
+
+workflows:
+  main:
+    jobs:
+      - build-and-test

CHANGES.rst

@@ -1,9 +1,61 @@
 Changelog
 =========
 
-0.28.0 (2020-02-03)
+0.36.0 (2020-08-29)
 -------------------
 ------------------------
+- Add flake8 instructions to readme. [Albert Wang]
+- Fix regex string. [Albert Wang]
+- Fix whitespace issues. [Albert Wang]
+- Do not use bare excepts. [Albert Wang]
+- Add .circleci/config.yml. [Albert Wang]
+- Include --private flag in example. [wouter bolsterlee]
+
+  By default, private repositories are not included. This is surprising.
+  It took me a while to figure this out, and making that clear in the
+  example can help others to be aware of that.
+
+
+0.35.0 (2020-08-05)
+-------------------
+- Make API request throttling optional. [Samantha Baldwin]
+
+
+0.34.0 (2020-07-24)
+-------------------
+- Add logic for transforming gist repository urls to ssh. [Matt Fields]
+
+
+0.33.0 (2020-04-13)
+-------------------
+- Add basic API request throttling. [Enrico Tröger]
+
+  A simple approach to throttle API requests and so keep within the rate
+  limits of the API. Can be enabled with "--throttle-limit" to specify
+  when throttling should start.
+  "--throttle-pause" defines the time to sleep between further API
+  requests.
+
+
+0.32.0 (2020-04-13)
+-------------------
+- Add timestamp to log messages. [Enrico Tröger]
+
+
+0.31.0 (2020-02-25)
+-------------------
+- #123 update: changed --as-app 'help' description. [ethan]
+- #123: Support Authenticating As Github Application. [ethan]
+
+
+0.29.0 (2020-02-14)
+-------------------
+- #50 update: keep main() in bin. [ethan]
+- #50 - refactor for friendlier import. [ethan]
+
+
+0.28.0 (2020-02-03)
+-------------------
 - Remove deprecated (and removed) git lfs flags. [smiley]
 
   "--tags" and "--force" were removed at some point from "git lfs fetch". This broke our backup script.

README.rst

@@ -29,19 +29,20 @@ Usage
 
 CLI Usage is as follows::
 
-    github-backup [-h] [-u USERNAME] [-p PASSWORD] [-t TOKEN]
+    github-backup [-h] [-u USERNAME] [-p PASSWORD] [-t TOKEN] [--as-app]
                   [-o OUTPUT_DIRECTORY] [-i] [--starred] [--all-starred]
                   [--watched] [--followers] [--following] [--all]
                   [--issues] [--issue-comments] [--issue-events] [--pulls]
-                  [--pull-comments] [--pull-commits] [--labels] [--hooks]
+                  [--pull-comments] [--pull-commits] [--pull-details]
-                  [--milestones] [--repositories] [--releases] [--assets]
+                  [--labels] [--hooks] [--milestones] [--repositories]
                   [--bare] [--lfs] [--wikis] [--gists] [--starred-gists]
-                  [--skip-existing]
+                  [--skip-existing] [-L [LANGUAGES [LANGUAGES ...]]]
-                  [-L [LANGUAGES [LANGUAGES ...]]] [-N NAME_REGEX]
+                  [-N NAME_REGEX] [-H GITHUB_HOST] [-O] [-R REPOSITORY]
-                  [-H GITHUB_HOST] [-O] [-R REPOSITORY] [-P] [-F]
+                  [-P] [-F] [--prefer-ssh] [-v]
-                  [--prefer-ssh] [-v]
                   [--keychain-name OSX_KEYCHAIN_ITEM_NAME]
                   [--keychain-account OSX_KEYCHAIN_ITEM_ACCOUNT]
+                  [--releases] [--assets] [--throttle-limit THROTTLE_LIMIT]
+                  [--throttle-pause THROTTLE_PAUSE]
                   USER
 
     Backup a github account
@@ -57,36 +58,36 @@ CLI Usage is as follows::
                             password for basic auth. If a username is given but
                             not a password, the password will be prompted for.
       -t TOKEN, --token TOKEN
-                            personal access or OAuth token, or path to token
+                            personal access, OAuth, or JSON Web token, or path to
-                            (file://...)
+                            token (file://...)
+      --as-app              authenticate as github app instead of as a user.
       -o OUTPUT_DIRECTORY, --output-directory OUTPUT_DIRECTORY
                             directory at which to backup the repositories
       -i, --incremental     incremental backup
       --starred             include JSON output of starred repositories in backup
-      --all-starred         include starred repositories in backup
+      --all-starred         include starred repositories in backup [*]
-      --watched             include watched repositories in backup
+      --watched             include JSON output of watched repositories in backup
       --followers           include JSON output of followers in backup
       --following           include JSON output of following users in backup
-      --all                 include everything in backup
+      --all                 include everything in backup (not including [*])
       --issues              include issues in backup
       --issue-comments      include issue comments in backup
       --issue-events        include issue events in backup
       --pulls               include pull requests in backup
       --pull-comments       include pull request review comments in backup
       --pull-commits        include pull request commits in backup
+      --pull-details        include more pull request details in backup [*]
       --labels              include labels in backup
       --hooks               include hooks in backup (works only when
                             authenticated)
       --milestones          include milestones in backup
       --repositories        include repository clone in backup
-      --releases            include repository releases' information without assets or binaries
-      --assets              include assets alongside release information; only applies if including releases
       --bare                clone bare repositories
       --lfs                 clone LFS repositories (requires Git LFS to be
-                            installed, https://git-lfs.github.com)
+                            installed, https://git-lfs.github.com) [*]
       --wikis               include wiki clone in backup
-      --gists               include gists in backup
+      --gists               include gists in backup [*]
-      --starred-gists       include starred gists in backup
+      --starred-gists       include starred gists in backup [*]
       --skip-existing       skip project if a backup directory exists
       -L [LANGUAGES [LANGUAGES ...]], --languages [LANGUAGES [LANGUAGES ...]]
                             only allow these languages
@@ -97,8 +98,8 @@ CLI Usage is as follows::
       -O, --organization    whether or not this is an organization user
       -R REPOSITORY, --repository REPOSITORY
                             name of repository to limit backup to
-      -P, --private         include private repositories
+      -P, --private         include private repositories [*]
-      -F, --fork            include forked repositories
+      -F, --fork            include forked repositories [*]
       --prefer-ssh          Clone repositories using SSH instead of HTTPS
       -v, --version         show program's version number and exit
       --keychain-name OSX_KEYCHAIN_ITEM_NAME
@@ -107,6 +108,17 @@ CLI Usage is as follows::
       --keychain-account OSX_KEYCHAIN_ITEM_ACCOUNT
                             OSX ONLY: account field of password item in OSX
                             keychain that holds the personal access or OAuth token
+      --releases            include release information, not including assets or
+                            binaries
+      --assets              include assets alongside release information; only
+                            applies if including releases
+      --throttle-limit THROTTLE_LIMIT
+                            start throttling of GitHub API requests after this
+                            amount of API requests remain
+      --throttle-pause THROTTLE_PAUSE
+                            wait this amount of seconds when API request
+                            throttling is active (default: 30.0, requires
+                            --throttle-limit to be set)
 
 
 The package can be used to backup an *entire* organization or repository, including issues and wikis in the most appropriate format (clones for wikis, json files for issues).
@@ -141,10 +153,10 @@ Instructions on how to do this can be found on https://git-lfs.github.com.
 Examples
 ========
 
-Backup all repositories::
+Backup all repositories, including private ones::
 
     export ACCESS_TOKEN=SOME-GITHUB-TOKEN
-    github-backup WhiteHouse --token $ACCESS_TOKEN --organization --output-directory /tmp/white-house --repositories
+    github-backup WhiteHouse --token $ACCESS_TOKEN --organization --output-directory /tmp/white-house --repositories --private
 
 Backup a single organization repository with everything else (wiki, pull requests, comments, issues etc)::
 
@@ -154,6 +166,15 @@ Backup a single organization repository with everything else (wiki, pull request
     # e.g. git@github.com:docker/cli.git
     github-backup $ORGANIZATION -P -t $ACCESS_TOKEN -o . --all -O -R $REPO
 
+Testing
+=======
+
+This project currently contains no unit tests.  To run linting::
+
+    pip install flake8
+    flake8 --ignore=E501
+
+
 .. |PyPI| image:: https://img.shields.io/pypi/v/github-backup.svg
    :target: https://pypi.python.org/pypi/github-backup/
 .. |Python Versions| image:: https://img.shields.io/pypi/pyversions/github-backup.svg

bin/github-backup

@@ -26,9 +26,12 @@ def main():
     if args.lfs_clone:
         check_git_lfs_install()
 
+    if not args.as_app:
         log_info('Backing up user {0} to {1}'.format(args.user, output_directory))
-
         authenticated_user = get_authenticated_user(args)
+    else:
+        authenticated_user = {'login': None}
+
     repositories = retrieve_repositories(args, authenticated_user)
     repositories = filter_repositories(args, repositories)
     backup_repositories(args, output_directory, repositories)

github_backup/__init__.py

@@ -1 +1 @@
-__version__ = '0.29.0'
+__version__ = '0.36.0'

github_backup/github_backup.py

@@ -7,6 +7,7 @@ import argparse
 import base64
 import calendar
 import codecs
+import datetime
 import errno
 import getpass
 import json
@@ -29,9 +30,11 @@ try:
     from urllib.request import Request
     from urllib.request import HTTPRedirectHandler
     from urllib.request import build_opener
+    from subprocess import SubprocessError
 except ImportError:
     # python 2
     PY2 = True
+    from subprocess import CalledProcessError as SubprocessError
     from urlparse import urlparse
     from urllib import quote as urlquote
     from urllib import urlencode
@@ -50,6 +53,10 @@ except ImportError:
 FNULL = open(os.devnull, 'w')
 
 
+def _get_log_date():
+    return datetime.datetime.isoformat(datetime.datetime.now())
+
+
 def log_error(message):
     """
     Log message (str) or messages (List[str]) to stderr and exit with status 1
@@ -66,7 +73,7 @@ def log_info(message):
         message = [message]
 
     for msg in message:
-        sys.stdout.write("{0}\n".format(msg))
+        sys.stdout.write("{0}: {1}\n".format(_get_log_date(), msg))
 
 
 def log_warning(message):
@@ -77,7 +84,7 @@ def log_warning(message):
         message = [message]
 
     for msg in message:
-        sys.stderr.write("{0}\n".format(msg))
+        sys.stderr.write("{0}: {1}\n".format(_get_log_date(), msg))
 
 
 def logging_subprocess(popenargs,
@@ -168,7 +175,11 @@ def parse_args():
     parser.add_argument('-t',
                         '--token',
                         dest='token',
-                        help='personal access or OAuth token, or path to token (file://...)')  # noqa
+                        help='personal access, OAuth, or JSON Web token, or path to token (file://...)')  # noqa
+    parser.add_argument('--as-app',
+                        action='store_true',
+                        dest='as_app',
+                        help='authenticate as github app instead of as a user.')
     parser.add_argument('-o',
                         '--output-directory',
                         default='.',
@@ -322,10 +333,20 @@ def parse_args():
                         action='store_true',
                         dest='include_assets',
                         help='include assets alongside release information; only applies if including releases')
+    parser.add_argument('--throttle-limit',
+                        dest='throttle_limit',
+                        type=int,
+                        default=0,
+                        help='start throttling of GitHub API requests after this amount of API requests remain')
+    parser.add_argument('--throttle-pause',
+                        dest='throttle_pause',
+                        type=float,
+                        default=30.0,
+                        help='wait this amount of seconds when API request throttling is active (default: 30.0, requires --throttle-limit to be set)')
     return parser.parse_args()
 
 
-def get_auth(args, encode=True):
+def get_auth(args, encode=True, for_git_cli=False):
     auth = None
 
     if args.osx_keychain_item_name:
@@ -344,7 +365,7 @@ def get_auth(args, encode=True):
                 if not PY2:
                     token = token.decode('utf-8')
                 auth = token + ':' + 'x-oauth-basic'
-            except:
+            except SubprocessError:
                 log_error('No password item matching the provided name and account could be found in the osx keychain.')
     elif args.osx_keychain_item_account:
         log_error('You must specify both name and account fields for osx keychain password items')
@@ -353,7 +374,13 @@ def get_auth(args, encode=True):
         if args.token.startswith(_path_specifier):
             args.token = open(args.token[len(_path_specifier):],
                               'rt').readline().strip()
+        if not args.as_app:
             auth = args.token + ':' + 'x-oauth-basic'
+        else:
+            if not for_git_cli:
+                auth = args.token
+            else:
+                auth = 'x-access-token:' + args.token
     elif args.username:
         if not args.password:
             args.password = getpass.getpass()
@@ -394,13 +421,19 @@ def get_github_host(args):
 
 def get_github_repo_url(args, repository):
     if repository.get('is_gist'):
-        return repository['git_pull_url']
+        if args.prefer_ssh:
+            # The git_pull_url value is always https for gists, so we need to transform it to ssh form
+            repo_url = re.sub(r'^https?:\/\/(.+)\/(.+)\.git$', r'git@\1:\2.git', repository['git_pull_url'])
+            repo_url = re.sub(r'^git@gist\.', 'git@', repo_url)  # strip gist subdomain for better hostkey compatibility
+        else:
+            repo_url = repository['git_pull_url']
+        return repo_url
 
     if args.prefer_ssh:
         return repository['ssh_url']
 
-    auth = get_auth(args, False)
+    auth = get_auth(args, encode=False, for_git_cli=True)
-    if auth and repository['private'] == True:
+    if auth and repository['private'] is True:
         repo_url = 'https://{0}@{1}/{2}/{3}.git'.format(
             auth,
             get_github_host(args),
@@ -413,24 +446,32 @@ def get_github_repo_url(args, repository):
 
 
 def retrieve_data_gen(args, template, query_args=None, single_request=False):
-    auth = get_auth(args)
+    auth = get_auth(args, encode=not args.as_app)
     query_args = get_query_args(query_args)
     per_page = 100
     page = 0
 
     while True:
         page = page + 1
-        request = _construct_request(per_page, page, query_args, template, auth)  # noqa
+        request = _construct_request(per_page, page, query_args, template, auth, as_app=args.as_app)  # noqa
         r, errors = _get_response(request, auth, template)
 
         status_code = int(r.getcode())
+        # be gentle with API request limit and throttle requests if remaining requests getting low
+        limit_remaining = int(r.headers.get('x-ratelimit-remaining', 0))
+        if args.throttle_limit and limit_remaining <= args.throttle_limit:
+            log_info(
+                'API request limit hit: {} requests left, pausing further requests for {}s'.format(
+                    limit_remaining,
+                    args.throttle_pause))
+            time.sleep(args.throttle_pause)
 
         retries = 0
         while retries < 3 and status_code == 502:
-            print('API request returned HTTP 502: Bad Gateway. Retrying in 5 seconds')
+            log_warning('API request returned HTTP 502: Bad Gateway. Retrying in 5 seconds')
             retries += 1
             time.sleep(5)
-            request = _construct_request(per_page, page, query_args, template, auth)  # noqa
+            request = _construct_request(per_page, page, query_args, template, auth, as_app=args.as_app)  # noqa
             r, errors = _get_response(request, auth, template)
 
             status_code = int(r.getcode())
@@ -456,9 +497,11 @@ def retrieve_data_gen(args, template, query_args=None, single_request=False):
         if single_request:
             break
 
+
 def retrieve_data(args, template, query_args=None, single_request=False):
     return list(retrieve_data_gen(args, template, query_args, single_request))
 
+
 def get_query_args(query_args=None):
     if not query_args:
         query_args = {}
@@ -495,7 +538,7 @@ def _get_response(request, auth, template):
     return r, errors
 
 
-def _construct_request(per_page, page, query_args, template, auth):
+def _construct_request(per_page, page, query_args, template, auth, as_app=None):
     querystring = urlencode(dict(list({
         'per_page': per_page,
         'page': page
@@ -503,7 +546,13 @@ def _construct_request(per_page, page, query_args, template, auth):
 
     request = Request(template + '?' + querystring)
     if auth is not None:
+        if not as_app:
             request.add_header('Authorization', 'Basic '.encode('ascii') + auth)
+        else:
+            if not PY2:
+                auth = auth.encode('ascii')
+            request.add_header('Authorization', 'token '.encode('ascii') + auth)
+            request.add_header('Accept', 'application/vnd.github.machine-man-preview+json')
     log_info('Requesting {}?{}'.format(template, querystring))
     return request
 
@@ -528,12 +577,10 @@ def _request_http_error(exc, auth, errors):
         delta = max(10, reset - gm_now)
 
         limit = headers.get('x-ratelimit-limit')
-        print('Exceeded rate limit of {} requests; waiting {} seconds to reset'.format(limit, delta),  # noqa
+        log_warning('Exceeded rate limit of {} requests; waiting {} seconds to reset'.format(limit, delta))  # noqa
-              file=sys.stderr)
 
         if auth is None:
-            print('Hint: Authenticate to raise your GitHub rate limit',
+            log_info('Hint: Authenticate to raise your GitHub rate limit')
-                  file=sys.stderr)
 
         time.sleep(delta)
         should_continue = True
@@ -858,18 +905,22 @@ def backup_pulls(args, repo_cwd, repository, repos_template):
         pull_states = ['open', 'closed']
         for pull_state in pull_states:
             query_args['state'] = pull_state
-            _pulls = retrieve_data_gen(args,
+            _pulls = retrieve_data_gen(
+                args,
                 _pulls_template,
-                                   query_args=query_args)
+                query_args=query_args
+            )
             for pull in _pulls:
                 if args.since and pull['updated_at'] < args.since:
                     break
                 if not args.since or pull['updated_at'] >= args.since:
                     pulls[pull['number']] = pull
     else:
-        _pulls = retrieve_data_gen(args,
+        _pulls = retrieve_data_gen(
+            args,
             _pulls_template,
-                               query_args=query_args)
+            query_args=query_args
+        )
         for pull in _pulls:
             if args.since and pull['updated_at'] < args.since:
                 break