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 +1,44 @@
 Changelog
 =========
 
-0.32.0 (2020-04-13)
+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]
 
 

README.rst

@@ -41,7 +41,8 @@ CLI Usage is as follows::
                   [-P] [-F] [--prefer-ssh] [-v]
                   [--keychain-name OSX_KEYCHAIN_ITEM_NAME]
                   [--keychain-account OSX_KEYCHAIN_ITEM_ACCOUNT]
-                  [--releases] [--assets]
+                  [--releases] [--assets] [--throttle-limit THROTTLE_LIMIT]
+                  [--throttle-pause THROTTLE_PAUSE]
                   USER
 
     Backup a github account
@@ -111,6 +112,13 @@ CLI Usage is as follows::
                             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).
@@ -145,10 +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)::
 
@@ -158,6 +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

github_backup/__init__.py

@@ -1 +1 @@
-__version__ = '0.32.0'
+__version__ = '0.36.0'

github_backup/github_backup.py

@@ -30,9 +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
@@ -331,6 +333,16 @@ 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()
 
 
@@ -353,7 +365,7 @@ def get_auth(args, encode=True, for_git_cli=False):
                 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')
@@ -409,13 +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, 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),
@@ -439,6 +457,14 @@ def retrieve_data_gen(args, template, query_args=None, single_request=False):
         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:
@@ -471,9 +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 = {}
@@ -877,18 +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_template,
-                                   query_args=query_args)
+            _pulls = retrieve_data_gen(
+                args,
+                _pulls_template,
+                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_template,
-                               query_args=query_args)
+        _pulls = retrieve_data_gen(
+            args,
+            _pulls_template,
+            query_args=query_args
+        )
         for pull in _pulls:
             if args.since and pull['updated_at'] < args.since:
                 break