Release version 0.43.0

Add --log-level command line argument

.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

.gitchangelog.rc

@@ -0,0 +1,117 @@
+#
+# Format
+#
+#   ACTION: [AUDIENCE:] COMMIT_MSG [@TAG ...]
+#
+# Description
+#
+#   ACTION is one of 'chg', 'fix', 'new'
+#
+#       Is WHAT the change is about.
+#
+#       'chg' is for refactor, small improvement, cosmetic changes...
+#       'fix' is for bug fixes
+#       'new' is for new features, big improvement
+#
+#   SUBJECT is optional and one of 'dev', 'usr', 'pkg', 'test', 'doc'
+#
+#       Is WHO is concerned by the change.
+#
+#       'dev'  is for developpers (API changes, refactors...)
+#       'usr'  is for final users (UI changes)
+#       'pkg'  is for packagers   (packaging changes)
+#       'test' is for testers     (test only related changes)
+#       'doc'  is for doc guys    (doc only changes)
+#
+#   COMMIT_MSG is ... well ... the commit message itself.
+#
+#   TAGs are additionnal adjective as 'refactor' 'minor' 'cosmetic'
+#
+#       'refactor' is obviously for refactoring code only
+#       'minor' is for a very meaningless change (a typo, adding a comment)
+#       'cosmetic' is for cosmetic driven change (re-indentation, 80-col...)
+#
+# Example:
+#
+#   new: usr: support of bazaar implemented
+#   chg: re-indentend some lines @cosmetic
+#   new: dev: updated code to be compatible with last version of killer lib.
+#   fix: pkg: updated year of licence coverage.
+#   new: test: added a bunch of test around user usability of feature X.
+#   fix: typo in spelling my name in comment. @minor
+#
+#   Please note that multi-line commit message are supported, and only the
+#   first line will be considered as the "summary" of the commit message. So
+#   tags, and other rules only applies to the summary.  The body of the commit
+#   message will be displayed in the changelog with minor reformating.
+
+#
+# ``ignore_regexps`` is a line of regexps
+#
+# Any commit having its full commit message matching any regexp listed here
+# will be ignored and won't be reported in the changelog.
+#
+ignore_regexps = [
+    r'(?i)^(Merge pull request|Merge branch|Release|Update)',
+]
+
+
+#
+# ``replace_regexps`` is a dict associating a regexp pattern and its replacement
+#
+# It will be applied to get the summary line from the full commit message.
+#
+# Note that you can provide multiple replacement patterns, they will be all
+# tried. If None matches, the summary line will be the full commit message.
+#
+replace_regexps = {
+    # current format (ie: 'chg: dev: my commit msg @tag1 @tag2')
+
+    r'^([cC]hg|[fF]ix|[nN]ew)\s*:\s*((dev|use?r|pkg|test|doc)\s*:\s*)?([^\n@]*)(@[a-z]+\s+)*$':
+    r'\4',
+}
+
+
+# ``section_regexps`` is a list of 2-tuples associating a string label and a
+# list of regexp
+#
+# Commit messages will be classified in sections thanks to this. Section
+# titles are the label, and a commit is classified under this section if any
+# of the regexps associated is matching.
+#
+section_regexps = [
+    ('New', [
+        r'^[nN]ew\s*:\s*((dev|use?r|pkg|test|doc)\s*:\s*)?([^\n]*)$',
+    ]),
+    ('Changes', [
+        r'^[cC]hg\s*:\s*((dev|use?r|pkg|test|doc)\s*:\s*)?([^\n]*)$',
+    ]),
+    ('Fix', [
+        r'^[fF]ix\s*:\s*((dev|use?r|pkg|test|doc)\s*:\s*)?([^\n]*)$',
+    ]),
+    ('Other', None  # Match all lines
+     ),
+
+]
+
+# ``body_split_regexp`` is a regexp
+#
+# Commit message body (not the summary) if existing will be split
+# (new line) on this regexp
+#
+body_split_regexp = r'[\n-]'
+
+
+# ``tag_filter_regexp`` is a regexp
+#
+# Tags that will be used for the changelog must match this regexp.
+#
+# tag_filter_regexp = r'^[0-9]+$'
+tag_filter_regexp = r'^(?:[vV])?[0-9\.]+$'
+
+
+# ``unreleased_version_label`` is a string
+#
+# This label will be used as the changelog Title of the last set of changes
+# between last valid tag and HEAD if any.
+unreleased_version_label = "%%version%% (unreleased)"

.github/workflows/tagged-release.yml

@@ -0,0 +1,19 @@
+---
+name: "tagged-release"
+
+# yamllint disable-line rule:truthy
+on:
+  push:
+    tags:
+      - '*'
+
+jobs:
+  tagged-release:
+    name: tagged-release
+    runs-on: ubuntu-20.04
+
+    steps:
+      - uses: "marvinpinto/action-automatic-releases@v1.2.1"
+        with:
+          repo_token: "${{ secrets.GITHUB_TOKEN }}"
+          prerelease: false

.gitignore

@@ -25,3 +25,13 @@ doc/_build
 
 # Generated man page
 doc/aws_hostname.1
+
+# Annoying macOS files
+.DS_Store
+._*
+
+# IDE configuration files
+.vscode
+.atom
+
+README

CHANGES.rst

@@ -1,19 +1,408 @@
 Changelog
 =========
 
-0.13.2 (2017-05-06)
+0.43.0 (2023-05-29)
+-------------------
+------------------------
+
+Fix
+~~~
+- Do not update readme. [Jose Diaz-Gonzalez]
+- Adjust for black. [Jose Diaz-Gonzalez]
+- Adjust for black. [Jose Diaz-Gonzalez]
+- Adjust for black. [Jose Diaz-Gonzalez]
+
+Other
+~~~~~
+- Feat: commit gitchangelog.rc to repo so anyone can generate a
+  changelog. [Jose Diaz-Gonzalez]
+- Feat: add release tagging. [Jose Diaz-Gonzalez]
+- Chore: formatting. [Jose Diaz-Gonzalez]
+- Chore: run black. [Jose Diaz-Gonzalez]
+- Add --log-level command line argument. [Enrico Tröger]
+
+  Support changing the log level to the desired value easily.
+  For example, this is useful to suppress progress messages but
+  keep logging warnings and errors.
+- Check both updated_at and pushed_at properties. [Ken Bailey]
+
+  Check both updated_at and pushed_at dates to get the last_update to reduce data retrieved on incremental api calls using since.
+
+
+0.42.0 (2022-11-28)
+-------------------
+- Add option to exclude repositories. [npounder]
+- Backup regular pull request comments as well. [Oneric]
+
+  Before, only review comments were backed up;
+  regular comments need to be fetched via issue API.
+- Fix bug forever retry when request url error. [kornpisey]
+- Added --no-prune option to disable prune option when doing git fetch.
+  [kornpisey]
+
+
+0.41.0 (2022-03-02)
+-------------------
+- Git lfs clone doe snot respect --mirror. [Louis Parisot]
+
+
+0.40.2 (2021-12-29)
+-------------------
+- Fix lint issues raised by Flake8. [atinary-afoulon]
+
+  According to job:
+  [ https://app.circleci.com/pipelines/github/josegonzalez/python-github-backup/30/workflows/74eb93f2-2505-435d-b728-03b3cc04c14a/jobs/23 ]
+
+  Failed on the following checks:
+  ./github_backup/github_backup.py:20:1: F811 redefinition of unused 'logging' from line 14
+  ./github_backup/github_backup.py:45:1: E302 expected 2 blank lines, found 1
+  ./github_backup/github_backup.py:136:20: E251 unexpected spaces around keyword / parameter equals
+
+
+0.40.1 (2021-09-22)
+-------------------
+- Revert to fetch. [Harrison Wright]
+
+
+0.40.0 (2021-07-12)
+-------------------
+- Add retry on certain network errors. [Jacek Nykis]
+
+  This change includes certain network level errors in the retry logic.
+  It partially address #110 but I think more comprehensive fix would be useful.
+- Pull changes from remote. [Jonas]
+
+  use `git pull` to pull actual files from the remote instead of using `fetch` for only the metadata
+
+
+0.39.0 (2021-03-19)
 -------------------
 
+Fix
+~~~
+- Fix missing INFO logs. [Gallo Feliz]
+
+Other
+~~~~~
+- Try to make compatible code with direct Python call ; reduce the hard
+  link of the code with the cli. [Gallo Feliz]
+- Fixed release_name with slash bug. [Álvaro Torres Cogollo]
+
+
+0.38.0 (2021-02-13)
+-------------------
+
+Fix
+~~~
+- Always clone with OAuth token when provided. [Samantha Baldwin]
+
+  Github Enterprise servers with 'Anonymous Git read access' disabled
+  cause `git ls-remote` to fail (128) for a repo's `clone_url`. Using the
+  OAuth token when provided allows cloning private AND public repos when
+  Anonymous Git read access is disabled.
+
+Other
+~~~~~
+- Change broken link to a fork to a working link to upstream. [Rick van
+  Schijndel]
+
+
+0.37.2 (2021-01-02)
+-------------------
+
+Fix
+~~~
+- Use distutils.core on error. [Jose Diaz-Gonzalez]
+
+
+0.37.1 (2021-01-02)
+-------------------
+
+Fix
+~~~
+- Use twine for releases. [Jose Diaz-Gonzalez]
+
+  The old method of releasing to pypi broke for whatever reason and switching to a supported toolchain is easier than debugging the old one.
+
+  Additionally:
+
+  - Update gitchangelog
+  - Fix license entry
+  - Set long description type
+  - Gitignore the temporary readme file
+
+
+0.37.0 (2021-01-02)
+-------------------
+- Add support for python 3.7 and 3.8 in package classifiers. [Albert
+  Wang]
+- Remove support for python 2.7 in package classifiers. [Albert Wang]
+- Remove python 2 specific import logic. [Albert Wang]
+- Remove python 2 specific logic. [Albert Wang]
+- Add ability to skip archived repositories. [Gary Moon]
+
+
+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.
+
+
+0.27.0 (2020-01-22)
+-------------------
+- Fixed script fails if not installed from pip. [Ben Baron]
+
+  At the top of the script, the line from github_backup import __version__ gets the script's version number to use if the script is called with the -v or --version flags. The problem is that if the script hasn't been installed via pip (for example I cloned the repo directly to my backup server), the script will fail due to an import exception.
+
+  Also presumably it will always use the version number from pip even if running a modified version from git or a fork or something, though this does not fix that as I have no idea how to check if it's running the pip installed version or not. But at least the script will now work fine if cloned from git or just copied to another machine.
+
+  closes https://github.com/josegonzalez/python-github-backup/issues/141
+- Fixed macOS keychain access when using Python 3. [Ben Baron]
+
+  Python 3 is returning bytes rather than a string, so the string concatenation to create the auth variable was throwing an exception which the script was interpreting to mean it couldn't find the password. Adding a conversion to string first fixed the issue.
+- Public repos no longer include the auth token. [Ben Baron]
+
+  When backing up repositories using an auth token and https, the GitHub personal auth token is leaked in each backed up repository. It is included in the URL of each repository's git remote url.
+
+  This is not needed as they are public and can be accessed without the token and can cause issues in the future if the token is ever changed, so I think it makes more sense not to have the token stored in each repo backup. I think the token should only be "leaked" like this out of necessity, e.g. it's a private repository and the --prefer-ssh option was not chosen so https with auth token was required to perform the clone.
+- Fixed comment typo. [Ben Baron]
+- Switched log_info to log_warning in download_file. [Ben Baron]
+- Crash when an release asset doesn't exist. [Ben Baron]
+
+  Currently, the script crashes whenever a release asset is unable to download (for example a 404 response). This change instead logs the failure and allows the script to continue. No retry logic is enabled, but at least it prevents the crash and allows the backup to complete. Retry logic can be implemented later if wanted.
+
+  closes https://github.com/josegonzalez/python-github-backup/issues/129
+- Moved asset downloading loop inside the if block. [Ben Baron]
+- Separate release assets and skip re-downloading. [Ben Baron]
+
+  Currently the script puts all release assets into the same folder called `releases`. So any time 2 release files have the same name, only the last one downloaded is actually saved. A particularly bad example of this is MacDownApp/macdown where all of their releases are named `MacDown.app.zip`. So even though they have 36 releases and all 36 are downloaded, only the last one is actually saved.
+
+  With this change, each releases' assets are now stored in a fubfolder inside `releases` named after the release name. There could still be edge cases if two releases have the same name, but this is still much safer tha the previous behavior.
+
+  This change also now checks if the asset file already exists on disk and skips downloading it. This drastically speeds up addiotnal syncs as it no longer downloads every single release every single time. It will now only download new releases which I believe is the expected behavior.
+
+  closes https://github.com/josegonzalez/python-github-backup/issues/126
+- Added newline to end of file. [Ben Baron]
+- Improved gitignore, macOS files and IDE configs. [Ben Baron]
+
+  Ignores the annoying hidden macOS files .DS_Store and ._* as well as the IDE configuration folders for contributors using the popular Visual Studio Code and Atom IDEs (more can be added later as needed).
+
+
+0.26.0 (2019-09-23)
+-------------------
+- Workaround gist clone in `--prefer-ssh` mode. [Vladislav Yarmak]
+- Create PULL_REQUEST.md. [Jose Diaz-Gonzalez]
+- Create ISSUE_TEMPLATE.md. [Jose Diaz-Gonzalez]
+
+
+0.25.0 (2019-07-03)
+-------------------
+- Issue 119: Change retrieve_data to be a generator. [2a]
+
+  See issue #119.
+
+
+0.24.0 (2019-06-27)
+-------------------
+- QKT-45: include assets - update readme. [Ethan Timm]
+
+  update readme with flag information for including assets alongside their respective releases
+- Make assets it's own flag. [Harrison Wright]
+- Fix super call for python2. [Harrison Wright]
+- Fix redirect to s3. [Harrison Wright]
+- WIP: download assets. [Harrison Wright]
+- QKT-42: releases - add readme info. [ethan]
+- QKT-42 update: shorter command flag. [ethan]
+- QKT-42: support saving release information. [ethan]
+- Fix pull details. [Harrison Wright]
+
+
+0.23.0 (2019-06-04)
+-------------------
+- Avoid to crash in case of HTTP 502 error. [Gael de Chalendar]
+
+  Survive also on socket.error connections like on HTTPError or URLError.
+
+  This should solve issue #110.
+
+
+0.22.2 (2019-02-21)
+-------------------
+
+Fix
+~~~
+- Warn instead of error. [Jose Diaz-Gonzalez]
+
+  Refs #106
+
+
+0.22.1 (2019-02-21)
+-------------------
+- Log URL error https://github.com/josegonzalez/python-github-
+  backup/issues/105. [JOHN STETIC]
+
+
+0.22.0 (2019-02-01)
+-------------------
+- Remove unnecessary sys.exit call. [W. Harrison Wright]
+- Add org check to avoid incorrect log output. [W. Harrison Wright]
+- Fix accidental system exit with better logging strategy. [W. Harrison
+  Wright]
+
+
+0.21.1 (2018-12-25)
+-------------------
+- Mark options which are not included in --all. [Bernd]
+
+  As discussed in Issue #100
+
+
+0.21.0 (2018-11-28)
+-------------------
+- Correctly download repos when user arg != authenticated user. [W.
+  Harrison Wright]
+
+
+0.20.1 (2018-09-29)
+-------------------
+- Clone the specified user's gists, not the authenticated user. [W.
+  Harrison Wright]
+- Clone the specified user's starred repos, not the authenticated user.
+  [W. Harrison Wright]
+
+
+0.20.0 (2018-03-24)
+-------------------
+- Chore: drop Python 2.6. [Jose Diaz-Gonzalez]
+- Feat: simplify release script. [Jose Diaz-Gonzalez]
+
+
+0.19.2 (2018-03-24)
+-------------------
+
+Fix
+~~~
+- Cleanup pep8 violations. [Jose Diaz-Gonzalez]
+
+
+0.19.0 (2018-03-24)
+-------------------
+- Add additional output for the current request. [Robin Gloster]
+
+  This is useful to have some progress indication for huge repositories.
+- Add option to backup additional PR details. [Robin Gloster]
+
+  Some payload is only included when requesting a single pull request
+- Mark string as binary in comparison for skip_existing. [Johannes
+  Bornhold]
+
+  Found out that the flag "--skip-existing" did not work out as expected on Python
+  3.6. Tracked it down to the comparison which has to be against a string of bytes
+  in Python3.
+
+
+0.18.0 (2018-02-22)
+-------------------
+- Add option to fetch followers/following JSON data. [Stephen Greene]
+
+
+0.17.0 (2018-02-20)
+-------------------
+- Short circuit gists backup process. [W. Harrison Wright]
+- Formatting. [W. Harrison Wright]
+- Add ability to backup gists. [W. Harrison Wright]
+
+
+0.16.0 (2018-01-22)
+-------------------
+- Change option to --all-starred. [W. Harrison Wright]
+- JK don't update documentation. [W. Harrison Wright]
+- Put starred clone repoistories under a new option. [W. Harrison
+  Wright]
+- Add comment. [W. Harrison Wright]
+- Add ability to clone starred repos. [W. Harrison Wright]
+
+
+0.14.1 (2017-10-11)
+-------------------
+- Fix arg not defined error. [Edward Pfremmer]
+
+
+0.14.0 (2017-10-11)
+-------------------
+- Added a check to see if git-lfs is installed when doing an LFS clone.
+  [pieterclaerhout]
+- Added support for LFS clones. [pieterclaerhout]
+- Add pypi info to readme. [Albert Wang]
+- Explicitly support python 3 in package description. [Albert Wang]
+- Add couple examples to help new users. [Yusuf Tran]
+
+
+0.13.2 (2017-05-06)
+-------------------
 - Fix remotes while updating repository. [Dima Gerasimov]
 
+
 0.13.1 (2017-04-11)
 -------------------
-
 - Fix error when repository has no updated_at value. [Nicolai Ehemann]
 
+
 0.13.0 (2017-04-05)
 -------------------
-
 - Add OS check for OSX specific keychain args. [Martin O'Reilly]
 
   Keychain arguments are only supported on Mac OSX.
@@ -22,8 +411,6 @@ Changelog
   error message rather than a "No password item matching the
   provided name and account could be found in the osx keychain"
   error message
-
-
 - Add support for storing PAT in OSX keychain. [Martin O'Reilly]
 
   Added additional optional arguments and README guidance for storing
@@ -33,62 +420,48 @@ Changelog
 
 0.12.1 (2017-03-27)
 -------------------
-
 - Avoid remote branch name churn. [Chris Adams]
 
   This avoids the backup output having lots of "[new branch]" messages
   because removing the old remote name removed all of the existing branch
   references.
-
-
 - Fix detection of bare git directories. [Andrzej Maczuga]
 
+
 0.12.0 (2016-11-22)
 -------------------
 
 Fix
 ~~~
-
 - Properly import version from github_backup package. [Jose Diaz-
   Gonzalez]
-
 - Support alternate git status output. [Jose Diaz-Gonzalez]
 
 Other
 ~~~~~
-
 - Pep8: E501 line too long (83 > 79 characters) [Jose Diaz-Gonzalez]
-
 - Pep8: E128 continuation line under-indented for visual indent. [Jose
   Diaz-Gonzalez]
-
 - Support archivization using bare git clones. [Andrzej Maczuga]
-
 - Fix typo, 3x. [Terrell Russell]
 
+
 0.11.0 (2016-10-26)
 -------------------
-
 - Support --token file:///home/user/token.txt (fixes gh-51) [Björn
   Dahlgren]
-
 - Fix some linting. [Albert Wang]
-
 - Fix byte/string conversion for python 3. [Albert Wang]
-
 - Support python 3. [Albert Wang]
-
 - Encode special characters in password. [Remi Rampin]
-
 - Don't pretend program name is "Github Backup" [Remi Rampin]
-
 - Don't install over insecure connection. [Remi Rampin]
 
   The git:// protocol is unauthenticated and unencrypted, and no longer advertised by GitHub. Using HTTPS shouldn't impact performance.
 
+
 0.10.3 (2016-08-21)
 -------------------
-
 - Fixes #29. [Jonas Michel]
 
   Reporting an error when the user's rate limit is exceeded causes
@@ -96,8 +469,6 @@ Other
   sleep. Instead of generating an explicit error we just want to
   inform the user that the script is going to sleep until their rate
   limit count resets.
-
-
 - Fixes #29. [Jonas Michel]
 
   The errors list was not being cleared out after resuming a backup
@@ -108,14 +479,13 @@ Other
 
 0.10.2 (2016-08-21)
 -------------------
-
 - Add a note regarding git version requirement. [Jose Diaz-Gonzalez]
 
   Closes #37
 
+
 0.10.0 (2016-08-18)
 -------------------
-
 - Implement incremental updates. [Robert Bradshaw]
 
   Guarded with an --incremental flag.
@@ -128,12 +498,11 @@ Other
 
 0.9.0 (2016-03-29)
 ------------------
-
 - Fix cloning private repos with basic auth or token. [Kazuki Suda]
 
+
 0.8.0 (2016-02-14)
 ------------------
-
 - Don't store issues which are actually pull requests. [Enrico Tröger]
 
   This prevents storing pull requests twice since the Github API returns
@@ -144,43 +513,31 @@ Other
 
 0.7.0 (2016-02-02)
 ------------------
-
 - Softly fail if not able to read hooks. [Albert Wang]
-
 - Add note about 2-factor auth. [Albert Wang]
-
 - Make user repository search go through endpoint capable of reading
   private repositories. [Albert Wang]
-
 - Prompt for password if only username given. [Alex Hall]
 
+
 0.6.0 (2015-11-10)
 ------------------
-
 - Force proper remote url. [Jose Diaz-Gonzalez]
-
 - Improve error handling in case of HTTP errors. [Enrico Tröger]
 
   In case of a HTTP status code 404, the returned 'r' was never assigned.
   In case of URL errors which are not timeouts, we probably should bail
   out.
-
-
 - Add --hooks to also include web hooks into the backup. [Enrico Tröger]
-
 - Create the user specified output directory if it does not exist.
   [Enrico Tröger]
 
   Fixes #17.
-
-
 - Add missing auth argument to _get_response() [Enrico Tröger]
 
   When running unauthenticated and Github starts rate-limiting the client,
   github-backup crashes because the used auth variable in _get_response()
   was not available. This change should fix it.
-
-
 - Add repository URL to error message for non-existing repositories.
   [Enrico Tröger]
 
@@ -191,40 +548,28 @@ Other
 
 0.5.0 (2015-10-10)
 ------------------
-
 - Add release script. [Jose Diaz-Gonzalez]
-
 - Refactor to both simplify codepath as well as follow PEP8 standards.
   [Jose Diaz-Gonzalez]
-
 - Retry 3 times when the connection times out. [Mathijs Jonker]
-
 - Made unicode output defalut. [Kirill Grushetsky]
-
 - Import alphabetised. [Kirill Grushetsky]
-
 - Preserve Unicode characters in the output file. [Kirill Grushetsky]
 
   Added option to preserve Unicode characters in the output file
-
 - Josegonzales/python-github-backup#12 Added backup of labels and
   milestones. [aensley]
-
 - Fixed indent. [Mathijs Jonker]
-
 - Skip unitialized repo's. [mjonker-embed]
 
   These gave me errors which caused mails from crontab.
-
 - Added prefer-ssh. [mjonker-embed]
 
   Was needed for my back-up setup, code includes this but readme wasn't updated
-
 - Retry API requests which failed due to rate-limiting. [Chris Adams]
 
   This allows operation to continue, albeit at a slower pace,
   if you have enough data to trigger the API rate limits
-
 - Logging_subprocess: always log when a command fails. [Chris Adams]
 
   Previously git clones could fail without any indication
@@ -234,21 +579,15 @@ Other
   Now a non-zero return code will always output a message to
   stderr and will display the executed command so it can be
   rerun for troubleshooting.
-
-
 - Switch to using ssh_url. [Chris Adams]
 
   The previous commit used the wrong URL for a private repo. This was
   masked by the lack of error loging in logging_subprocess (which will be
   in a separate branch)
-
-
 - Add an option to prefer checkouts over SSH. [Chris Adams]
 
   This is really useful with private repos to avoid being nagged
   for credentials for every repository
-
-
 - Add pull request support. [Kevin Laude]
 
   Back up reporitory pull requests by passing the --include-pulls
@@ -260,8 +599,6 @@ Other
 
   Pull requests are automatically backed up when the --all argument is
   uesd.
-
-
 - Add GitHub Enterprise support. [Kevin Laude]
 
   Pass the -H or --github-host argument with a GitHub Enterprise hostname
@@ -271,35 +608,21 @@ Other
 
 0.2.0 (2014-09-22)
 ------------------
-
 - Add support for retrieving repositories. Closes #1. [Jose Diaz-
   Gonzalez]
-
 - Fix PEP8 violations. [Jose Diaz-Gonzalez]
-
 - Add authorization to header only if specified by user. [Ioannis
   Filippidis]
-
 - Fill out readme more. [Jose Diaz-Gonzalez]
-
 - Fix import. [Jose Diaz-Gonzalez]
-
 - Properly name readme. [Jose Diaz-Gonzalez]
-
 - Create MANIFEST.in. [Jose Diaz-Gonzalez]
-
 - Create .gitignore. [Jose Diaz-Gonzalez]
-
 - Create setup.py. [Jose Diaz-Gonzalez]
-
 - Create requirements.txt. [Jose Diaz-Gonzalez]
-
 - Create __init__.py. [Jose Diaz-Gonzalez]
-
 - Create LICENSE.txt. [Jose Diaz-Gonzalez]
-
 - Create README.md. [Jose Diaz-Gonzalez]
-
 - Create github-backup. [Jose Diaz-Gonzalez]
 
 

ISSUE_TEMPLATE.md

@@ -0,0 +1,13 @@
+# Important notice regarding filed issues
+
+This project already fills my needs, and as such I have no real reason to continue it's development. This project is otherwise provided as is, and no support is given.
+
+If pull requests implementing bug fixes or enhancements are pushed, I am happy to review and merge them (time permitting).
+
+If you wish to have a bug fixed, you have a few options:
+
+- Fix it yourself and file a pull request.
+- File a bug and hope someone else fixes it for you.
+- Pay me to fix it (my rate is $200 an hour, minimum 1 hour, contact me via my [github email address](https://github.com/josegonzalez) if you want to go this route).
+
+In all cases, feel free to file an issue, they may be of help to others in the future.

PULL_REQUEST.md

@@ -0,0 +1,7 @@
+# Important notice regarding filed pull requests
+
+This project already fills my needs, and as such I have no real reason to continue it's development. This project is otherwise provided as is, and no support is given.
+
+I will attempt to review pull requests at _my_ earliest convenience. If I am unable to get to your pull request in a timely fashion, it is what it is. This repository does not pay any bills, and I am not required to merge any pull request from any individual.
+
+If you wish to jump my personal priority queue, you may pay me for my time to review. My rate is $200 an hour - minimum 1 hour - feel free contact me via my github email address if you want to go this route.

README.rst

@@ -2,6 +2,10 @@
 github-backup
 =============
 
+|PyPI| |Python Versions|
+
+    This project is considered feature complete for the primary maintainer. If you would like a bugfix or enhancement and cannot sponsor the work, pull requests are welcome. Feel free to contact the maintainer for consulting estimates if desired.
+
 backup a github user or organization
 
 Requirements
@@ -25,17 +29,20 @@ Usage
 
 CLI Usage is as follows::
 
-    github-backup [-h] [-u USERNAME] [-p PASSWORD] [-t TOKEN]
-                  [-o OUTPUT_DIRECTORY] [-i] [--starred] [--watched]
+    github-backup [-h] [-u USERNAME] [-p PASSWORD] [-t TOKEN] [--as-app]
+                  [-o OUTPUT_DIRECTORY] [-l LOG_LEVEL] [-i] [--starred]
+                  [--all-starred] [--watched] [--followers] [--following]
                   [--all] [--issues] [--issue-comments] [--issue-events]
-                  [--pulls] [--pull-comments] [--pull-commits] [--labels]
-                  [--hooks] [--milestones] [--repositories] [--bare]
-                  [--wikis] [--skip-existing]
-                  [-L [LANGUAGES [LANGUAGES ...]]] [-N NAME_REGEX]
-                  [-H GITHUB_HOST] [-O] [-R REPOSITORY] [-P] [-F]
-                  [--prefer-ssh] [-v]
+                  [--pulls] [--pull-comments] [--pull-commits]
+                  [--pull-details] [--labels] [--hooks] [--milestones]
+                  [--repositories] [--bare] [--lfs] [--wikis] [--gists]
+                  [--starred-gists] [--skip-archived] [--skip-existing]
+                  [-L [LANGUAGES ...]] [-N NAME_REGEX] [-H GITHUB_HOST]
+                  [-O] [-R REPOSITORY] [-P] [-F] [--prefer-ssh] [-v]
                   [--keychain-name OSX_KEYCHAIN_ITEM_NAME]
                   [--keychain-account OSX_KEYCHAIN_ITEM_ACCOUNT]
+                  [--releases] [--assets] [--exclude [REPOSITORY [REPOSITORY ...]]
+                  [--throttle-limit THROTTLE_LIMIT] [--throttle-pause THROTTLE_PAUSE]
                   USER
 
     Backup a github account
@@ -51,26 +58,39 @@ 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
+                            personal access, OAuth, or JSON Web token, or path to
+                            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
+      -l LOG_LEVEL, --log-level LOG_LEVEL
+                            log level to use (default: info, possible levels:
+                            debug, info, warning, error, critical)
       -i, --incremental     incremental backup
-      --starred             include starred repositories in backup
-      --watched             include watched repositories in backup
-      --all                 include everything in backup
+      --starred             include JSON output of starred repositories in backup
+      --all-starred         include starred 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 (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
       --bare                clone bare repositories
+      --lfs                 clone LFS repositories (requires Git LFS to be
+                            installed, https://git-lfs.github.com) [*]
       --wikis               include wiki clone in backup
+      --gists               include 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
@@ -81,8 +101,8 @@ 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
-      -F, --fork            include forked repositories
+      -P, --private         include private 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
@@ -91,6 +111,19 @@ 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
+      --exclude [REPOSITORY [REPOSITORY ...]]
+                            names of repositories to exclude from backup.
+      --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).
@@ -114,3 +147,40 @@ Note:  When you run github-backup, you will be asked whether you want to allow "
 
 1. **Allow:** In this case you will need to click "Allow" each time you run `github-backup`
 2. **Always Allow:** In this case, you will not be asked for permission when you run `github-backup` in future. This is less secure, but is required if you want to schedule `github-backup` to run automatically
+
+About Git LFS
+=============
+
+When you use the "--lfs" option, you will need to make sure you have Git LFS installed.
+
+Instructions on how to do this can be found on https://git-lfs.github.com.
+
+Examples
+========
+
+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 --private
+
+Backup a single organization repository with everything else (wiki, pull requests, comments, issues etc)::
+
+    export ACCESS_TOKEN=SOME-GITHUB-TOKEN
+    ORGANIZATION=docker
+    REPO=cli
+    # 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
+   :target: https://github.com/josegonzalez/python-github-backup

bin/github-backup

@@ -1,843 +1,25 @@
 #!/usr/bin/env python
 
-from __future__ import print_function
-
-import argparse
-import base64
-import calendar
-import codecs
-import errno
-import getpass
-import json
-import logging
-import os
-import re
-import select
-import subprocess
-import sys
-import time
-import platform
-try:
-    # python 3
-    from urllib.parse import urlparse
-    from urllib.parse import quote as urlquote
-    from urllib.parse import urlencode
-    from urllib.error import HTTPError, URLError
-    from urllib.request import urlopen
-    from urllib.request import Request
-except ImportError:
-    # python 2
-    from urlparse import urlparse
-    from urllib import quote as urlquote
-    from urllib import urlencode
-    from urllib2 import HTTPError, URLError
-    from urllib2 import urlopen
-    from urllib2 import Request
-
-from github_backup import __version__
-
-FNULL = open(os.devnull, 'w')
-
-
-def log_error(message):
-    if type(message) == str:
-        message = [message]
-
-    for msg in message:
-        sys.stderr.write("{0}\n".format(msg))
-
-    sys.exit(1)
-
-
-def log_info(message):
-    if type(message) == str:
-        message = [message]
-
-    for msg in message:
-        sys.stdout.write("{0}\n".format(msg))
-
-
-def logging_subprocess(popenargs,
-                       logger,
-                       stdout_log_level=logging.DEBUG,
-                       stderr_log_level=logging.ERROR,
-                       **kwargs):
-    """
-    Variant of subprocess.call that accepts a logger instead of stdout/stderr,
-    and logs stdout messages via logger.debug and stderr messages via
-    logger.error.
-    """
-    child = subprocess.Popen(popenargs, stdout=subprocess.PIPE,
-                             stderr=subprocess.PIPE, **kwargs)
-
-    log_level = {child.stdout: stdout_log_level,
-                 child.stderr: stderr_log_level}
-
-    def check_io():
-        ready_to_read = select.select([child.stdout, child.stderr],
-                                      [],
-                                      [],
-                                      1000)[0]
-        for io in ready_to_read:
-            line = io.readline()
-            if not logger:
-                continue
-            if not (io == child.stderr and not line):
-                logger.log(log_level[io], line[:-1])
-
-    # keep checking stdout/stderr until the child exits
-    while child.poll() is None:
-        check_io()
-
-    check_io()  # check again to catch anything after the process exits
-
-    rc = child.wait()
-
-    if rc != 0:
-        print('{} returned {}:'.format(popenargs[0], rc), file=sys.stderr)
-        print('\t', ' '.join(popenargs), file=sys.stderr)
-
-    return rc
-
-
-def mkdir_p(*args):
-    for path in args:
-        try:
-            os.makedirs(path)
-        except OSError as exc:  # Python >2.5
-            if exc.errno == errno.EEXIST and os.path.isdir(path):
-                pass
-            else:
-                raise
-
-
-def mask_password(url, secret='*****'):
-    parsed = urlparse(url)
-
-    if not parsed.password:
-        return url
-    elif parsed.password == 'x-oauth-basic':
-        return url.replace(parsed.username, secret)
-
-    return url.replace(parsed.password, secret)
-
-
-def parse_args():
-    parser = argparse.ArgumentParser(description='Backup a github account')
-    parser.add_argument('user',
-                        metavar='USER',
-                        type=str,
-                        help='github username')
-    parser.add_argument('-u',
-                        '--username',
-                        dest='username',
-                        help='username for basic auth')
-    parser.add_argument('-p',
-                        '--password',
-                        dest='password',
-                        help='password for basic auth. '
-                             'If a username is given but not a password, the '
-                             'password will be prompted for.')
-    parser.add_argument('-t',
-                        '--token',
-                        dest='token',
-                        help='personal access or OAuth token, or path to token (file://...)')  # noqa
-    parser.add_argument('-o',
-                        '--output-directory',
-                        default='.',
-                        dest='output_directory',
-                        help='directory at which to backup the repositories')
-    parser.add_argument('-i',
-                        '--incremental',
-                        action='store_true',
-                        dest='incremental',
-                        help='incremental backup')
-    parser.add_argument('--starred',
-                        action='store_true',
-                        dest='include_starred',
-                        help='include starred repositories in backup')
-    parser.add_argument('--watched',
-                        action='store_true',
-                        dest='include_watched',
-                        help='include watched repositories in backup')
-    parser.add_argument('--all',
-                        action='store_true',
-                        dest='include_everything',
-                        help='include everything in backup')
-    parser.add_argument('--issues',
-                        action='store_true',
-                        dest='include_issues',
-                        help='include issues in backup')
-    parser.add_argument('--issue-comments',
-                        action='store_true',
-                        dest='include_issue_comments',
-                        help='include issue comments in backup')
-    parser.add_argument('--issue-events',
-                        action='store_true',
-                        dest='include_issue_events',
-                        help='include issue events in backup')
-    parser.add_argument('--pulls',
-                        action='store_true',
-                        dest='include_pulls',
-                        help='include pull requests in backup')
-    parser.add_argument('--pull-comments',
-                        action='store_true',
-                        dest='include_pull_comments',
-                        help='include pull request review comments in backup')
-    parser.add_argument('--pull-commits',
-                        action='store_true',
-                        dest='include_pull_commits',
-                        help='include pull request commits in backup')
-    parser.add_argument('--labels',
-                        action='store_true',
-                        dest='include_labels',
-                        help='include labels in backup')
-    parser.add_argument('--hooks',
-                        action='store_true',
-                        dest='include_hooks',
-                        help='include hooks in backup (works only when authenticated)')  # noqa
-    parser.add_argument('--milestones',
-                        action='store_true',
-                        dest='include_milestones',
-                        help='include milestones in backup')
-    parser.add_argument('--repositories',
-                        action='store_true',
-                        dest='include_repository',
-                        help='include repository clone in backup')
-    parser.add_argument('--bare',
-                        action='store_true',
-                        dest='bare_clone',
-                        help='clone bare repositories')
-    parser.add_argument('--wikis',
-                        action='store_true',
-                        dest='include_wiki',
-                        help='include wiki clone in backup')
-    parser.add_argument('--skip-existing',
-                        action='store_true',
-                        dest='skip_existing',
-                        help='skip project if a backup directory exists')
-    parser.add_argument('-L',
-                        '--languages',
-                        dest='languages',
-                        help='only allow these languages',
-                        nargs='*')
-    parser.add_argument('-N',
-                        '--name-regex',
-                        dest='name_regex',
-                        help='python regex to match names against')
-    parser.add_argument('-H',
-                        '--github-host',
-                        dest='github_host',
-                        help='GitHub Enterprise hostname')
-    parser.add_argument('-O',
-                        '--organization',
-                        action='store_true',
-                        dest='organization',
-                        help='whether or not this is an organization user')
-    parser.add_argument('-R',
-                        '--repository',
-                        dest='repository',
-                        help='name of repository to limit backup to')
-    parser.add_argument('-P', '--private',
-                        action='store_true',
-                        dest='private',
-                        help='include private repositories')
-    parser.add_argument('-F', '--fork',
-                        action='store_true',
-                        dest='fork',
-                        help='include forked repositories')
-    parser.add_argument('--prefer-ssh',
-                        action='store_true',
-                        help='Clone repositories using SSH instead of HTTPS')
-    parser.add_argument('-v', '--version',
-                        action='version',
-                        version='%(prog)s ' + __version__)
-    parser.add_argument('--keychain-name',
-                        dest='osx_keychain_item_name',
-                        help='OSX ONLY: name field of password item in OSX keychain that holds the personal access or OAuth token')
-    parser.add_argument('--keychain-account',
-                        dest='osx_keychain_item_account',
-                        help='OSX ONLY: account field of password item in OSX keychain that holds the personal access or OAuth token')
-    return parser.parse_args()
-
-
-def get_auth(args, encode=True):
-    auth = None
-
-    if args.osx_keychain_item_name:
-        if not args.osx_keychain_item_account:
-            log_error('You must specify both name and account fields for osx keychain password items')
-        else:
-            if platform.system() != 'Darwin':
-                log_error("Keychain arguments are only supported on Mac OSX")
-            try:
-                with open(os.devnull,'w') as devnull:
-                    token = (subprocess.check_output([
-                        'security','find-generic-password',
-                        '-s',args.osx_keychain_item_name,
-                        '-a',args.osx_keychain_item_account,
-                        '-w' ], stderr=devnull).strip())
-                auth = token + ':' + 'x-oauth-basic'
-            except:
-                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')
-    elif args.token:
-        _path_specifier = 'file://'
-        if args.token.startswith(_path_specifier):
-            args.token = open(args.token[len(_path_specifier):],
-                              'rt').readline().strip()
-        auth = args.token + ':' + 'x-oauth-basic'
-    elif args.username:
-        if not args.password:
-            args.password = getpass.getpass()
-        if encode:
-            password = args.password
-        else:
-            password = urlquote(args.password)
-        auth = args.username + ':' + password
-    elif args.password:
-        log_error('You must specify a username for basic auth')
-
-    if not auth:
-        return None
-
-    if not encode:
-        return auth
-
-    return base64.b64encode(auth.encode('ascii'))
-
-
-def get_github_api_host(args):
-    if args.github_host:
-        host = args.github_host + '/api/v3'
-    else:
-        host = 'api.github.com'
-
-    return host
-
-
-def get_github_host(args):
-    if args.github_host:
-        host = args.github_host
-    else:
-        host = 'github.com'
-
-    return host
-
-
-def get_github_repo_url(args, repository):
-    if args.prefer_ssh:
-        return repository['ssh_url']
-
-    auth = get_auth(args, False)
-    if auth:
-        repo_url = 'https://{0}@{1}/{2}/{3}.git'.format(
-            auth,
-            get_github_host(args),
-            args.user,
-            repository['name'])
-    else:
-        repo_url = repository['clone_url']
-
-    return repo_url
-
-
-def retrieve_data(args, template, query_args=None, single_request=False):
-    auth = get_auth(args)
-    query_args = get_query_args(query_args)
-    per_page = 100
-    page = 0
-    data = []
-
-    while True:
-        page = page + 1
-        request = _construct_request(per_page, page, query_args, template, auth)  # noqa
-        r, errors = _get_response(request, auth, template)
-
-        status_code = int(r.getcode())
-
-        if status_code != 200:
-            template = 'API request returned HTTP {0}: {1}'
-            errors.append(template.format(status_code, r.reason))
-            log_error(errors)
-
-        response = json.loads(r.read().decode('utf-8'))
-        if len(errors) == 0:
-            if type(response) == list:
-                data.extend(response)
-                if len(response) < per_page:
-                    break
-            elif type(response) == dict and single_request:
-                data.append(response)
-
-        if len(errors) > 0:
-            log_error(errors)
-
-        if single_request:
-            break
-
-    return data
-
-
-def get_query_args(query_args=None):
-    if not query_args:
-        query_args = {}
-    return query_args
-
-
-def _get_response(request, auth, template):
-    retry_timeout = 3
-    errors = []
-    # We'll make requests in a loop so we can
-    # delay and retry in the case of rate-limiting
-    while True:
-        should_continue = False
-        try:
-            r = urlopen(request)
-        except HTTPError as exc:
-            errors, should_continue = _request_http_error(exc, auth, errors)  # noqa
-            r = exc
-        except URLError:
-            should_continue = _request_url_error(template, retry_timeout)
-            if not should_continue:
-                raise
-
-        if should_continue:
-            continue
-
-        break
-    return r, errors
-
-
-def _construct_request(per_page, page, query_args, template, auth):
-    querystring = urlencode(dict(list({
-        'per_page': per_page,
-        'page': page
-    }.items()) + list(query_args.items())))
-
-    request = Request(template + '?' + querystring)
-    if auth is not None:
-        request.add_header('Authorization', 'Basic '.encode('ascii') + auth)
-    return request
-
-
-def _request_http_error(exc, auth, errors):
-    # HTTPError behaves like a Response so we can
-    # check the status code and headers to see exactly
-    # what failed.
-
-    should_continue = False
-    headers = exc.headers
-    limit_remaining = int(headers.get('x-ratelimit-remaining', 0))
-
-    if exc.code == 403 and limit_remaining < 1:
-        # The X-RateLimit-Reset header includes a
-        # timestamp telling us when the limit will reset
-        # so we can calculate how long to wait rather
-        # than inefficiently polling:
-        gm_now = calendar.timegm(time.gmtime())
-        reset = int(headers.get('x-ratelimit-reset', 0)) or gm_now
-        # We'll never sleep for less than 10 seconds:
-        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
-              file=sys.stderr)
-
-        if auth is None:
-            print('Hint: Authenticate to raise your GitHub rate limit',
-                  file=sys.stderr)
-
-        time.sleep(delta)
-        should_continue = True
-    return errors, should_continue
-
-
-def _request_url_error(template, retry_timeout):
-    # Incase of a connection timing out, we can retry a few time
-    # But we won't crash and not back-up the rest now
-    log_info('{} timed out'.format(template))
-    retry_timeout -= 1
-
-    if retry_timeout >= 0:
-        return True
-
-    log_error('{} timed out to much, skipping!')
-    return False
-
-
-def retrieve_repositories(args):
-    log_info('Retrieving repositories')
-    single_request = False
-    template = 'https://{0}/user/repos'.format(
-        get_github_api_host(args))
-    if args.organization:
-        template = 'https://{0}/orgs/{1}/repos'.format(
-            get_github_api_host(args),
-            args.user)
-
-    if args.repository:
-        single_request = True
-        template = 'https://{0}/repos/{1}/{2}'.format(
-            get_github_api_host(args),
-            args.user,
-            args.repository)
-
-    return retrieve_data(args, template, single_request=single_request)
-
-
-def filter_repositories(args, unfiltered_repositories):
-    log_info('Filtering repositories')
-
-    repositories = []
-    for r in unfiltered_repositories:
-        if r['owner']['login'] == args.user:
-            repositories.append(r)
-
-    name_regex = None
-    if args.name_regex:
-        name_regex = re.compile(args.name_regex)
-
-    languages = None
-    if args.languages:
-        languages = [x.lower() for x in args.languages]
-
-    if not args.fork:
-        repositories = [r for r in repositories if not r['fork']]
-    if not args.private:
-        repositories = [r for r in repositories if not r['private']]
-    if languages:
-        repositories = [r for r in repositories if r['language'] and r['language'].lower() in languages]  # noqa
-    if name_regex:
-        repositories = [r for r in repositories if name_regex.match(r['name'])]
-
-    return repositories
-
-
-def backup_repositories(args, output_directory, repositories):
-    log_info('Backing up repositories')
-    repos_template = 'https://{0}/repos'.format(get_github_api_host(args))
-
-    if args.incremental:
-        last_update = max(list(repository['updated_at'] for repository in repositories) or [time.strftime('%Y-%m-%dT%H:%M:%SZ', time.localtime())])  # noqa
-        last_update_path = os.path.join(output_directory, 'last_update')
-        if os.path.exists(last_update_path):
-            args.since = open(last_update_path).read().strip()
-        else:
-            args.since = None
-    else:
-        args.since = None
-
-    for repository in repositories:
-        backup_cwd = os.path.join(output_directory, 'repositories')
-        repo_cwd = os.path.join(backup_cwd, repository['name'])
-        repo_dir = os.path.join(repo_cwd, 'repository')
-        repo_url = get_github_repo_url(args, repository)
-
-        if args.include_repository or args.include_everything:
-            fetch_repository(repository['name'],
-                             repo_url,
-                             repo_dir,
-                             skip_existing=args.skip_existing,
-                             bare_clone=args.bare_clone)
-
-        download_wiki = (args.include_wiki or args.include_everything)
-        if repository['has_wiki'] and download_wiki:
-            fetch_repository(repository['name'],
-                             repo_url.replace('.git', '.wiki.git'),
-                             os.path.join(repo_cwd, 'wiki'),
-                             skip_existing=args.skip_existing,
-                             bare_clone=args.bare_clone)
-
-        if args.include_issues or args.include_everything:
-            backup_issues(args, repo_cwd, repository, repos_template)
-
-        if args.include_pulls or args.include_everything:
-            backup_pulls(args, repo_cwd, repository, repos_template)
-
-        if args.include_milestones or args.include_everything:
-            backup_milestones(args, repo_cwd, repository, repos_template)
-
-        if args.include_labels or args.include_everything:
-            backup_labels(args, repo_cwd, repository, repos_template)
-
-        if args.include_hooks or args.include_everything:
-            backup_hooks(args, repo_cwd, repository, repos_template)
-
-    if args.incremental:
-        open(last_update_path, 'w').write(last_update)
-
-
-def backup_issues(args, repo_cwd, repository, repos_template):
-    has_issues_dir = os.path.isdir('{0}/issues/.git'.format(repo_cwd))
-    if args.skip_existing and has_issues_dir:
-        return
-
-    log_info('Retrieving {0} issues'.format(repository['full_name']))
-    issue_cwd = os.path.join(repo_cwd, 'issues')
-    mkdir_p(repo_cwd, issue_cwd)
-
-    issues = {}
-    issues_skipped = 0
-    issues_skipped_message = ''
-    _issue_template = '{0}/{1}/issues'.format(repos_template,
-                                              repository['full_name'])
-
-    should_include_pulls = args.include_pulls or args.include_everything
-    issue_states = ['open', 'closed']
-    for issue_state in issue_states:
-        query_args = {
-            'filter': 'all',
-            'state': issue_state
-        }
-        if args.since:
-            query_args['since'] = args.since
-
-        _issues = retrieve_data(args,
-                                _issue_template,
-                                query_args=query_args)
-        for issue in _issues:
-            # skip pull requests which are also returned as issues
-            # if retrieving pull requests is requested as well
-            if 'pull_request' in issue and should_include_pulls:
-                issues_skipped += 1
-                continue
-
-            issues[issue['number']] = issue
-
-    if issues_skipped:
-        issues_skipped_message = ' (skipped {0} pull requests)'.format(
-            issues_skipped)
-
-    log_info('Saving {0} issues to disk{1}'.format(
-        len(list(issues.keys())), issues_skipped_message))
-    comments_template = _issue_template + '/{0}/comments'
-    events_template = _issue_template + '/{0}/events'
-    for number, issue in list(issues.items()):
-        if args.include_issue_comments or args.include_everything:
-            template = comments_template.format(number)
-            issues[number]['comment_data'] = retrieve_data(args, template)
-        if args.include_issue_events or args.include_everything:
-            template = events_template.format(number)
-            issues[number]['event_data'] = retrieve_data(args, template)
-
-        issue_file = '{0}/{1}.json'.format(issue_cwd, number)
-        with codecs.open(issue_file, 'w', encoding='utf-8') as f:
-            json_dump(issue, f)
-
-
-def backup_pulls(args, repo_cwd, repository, repos_template):
-    has_pulls_dir = os.path.isdir('{0}/pulls/.git'.format(repo_cwd))
-    if args.skip_existing and has_pulls_dir:
-        return
-
-    log_info('Retrieving {0} pull requests'.format(repository['full_name']))  # noqa
-    pulls_cwd = os.path.join(repo_cwd, 'pulls')
-    mkdir_p(repo_cwd, pulls_cwd)
-
-    pulls = {}
-    _pulls_template = '{0}/{1}/pulls'.format(repos_template,
-                                             repository['full_name'])
-
-    pull_states = ['open', 'closed']
-    for pull_state in pull_states:
-        query_args = {
-            'filter': 'all',
-            'state': pull_state,
-            'sort': 'updated',
-            'direction': 'desc',
-        }
-
-        # It'd be nice to be able to apply the args.since filter here...
-        _pulls = retrieve_data(args,
-                               _pulls_template,
-                               query_args=query_args)
-        for pull in _pulls:
-            if not args.since or pull['updated_at'] >= args.since:
-                pulls[pull['number']] = pull
-
-    log_info('Saving {0} pull requests to disk'.format(
-        len(list(pulls.keys()))))
-    comments_template = _pulls_template + '/{0}/comments'
-    commits_template = _pulls_template + '/{0}/commits'
-    for number, pull in list(pulls.items()):
-        if args.include_pull_comments or args.include_everything:
-            template = comments_template.format(number)
-            pulls[number]['comment_data'] = retrieve_data(args, template)
-        if args.include_pull_commits or args.include_everything:
-            template = commits_template.format(number)
-            pulls[number]['commit_data'] = retrieve_data(args, template)
-
-        pull_file = '{0}/{1}.json'.format(pulls_cwd, number)
-        with codecs.open(pull_file, 'w', encoding='utf-8') as f:
-            json_dump(pull, f)
-
-
-def backup_milestones(args, repo_cwd, repository, repos_template):
-    milestone_cwd = os.path.join(repo_cwd, 'milestones')
-    if args.skip_existing and os.path.isdir(milestone_cwd):
-        return
-
-    log_info('Retrieving {0} milestones'.format(repository['full_name']))
-    mkdir_p(repo_cwd, milestone_cwd)
-
-    template = '{0}/{1}/milestones'.format(repos_template,
-                                           repository['full_name'])
-
-    query_args = {
-        'state': 'all'
-    }
-
-    _milestones = retrieve_data(args, template, query_args=query_args)
-
-    milestones = {}
-    for milestone in _milestones:
-        milestones[milestone['number']] = milestone
-
-    log_info('Saving {0} milestones to disk'.format(
-        len(list(milestones.keys()))))
-    for number, milestone in list(milestones.items()):
-        milestone_file = '{0}/{1}.json'.format(milestone_cwd, number)
-        with codecs.open(milestone_file, 'w', encoding='utf-8') as f:
-            json_dump(milestone, f)
-
-
-def backup_labels(args, repo_cwd, repository, repos_template):
-    label_cwd = os.path.join(repo_cwd, 'labels')
-    output_file = '{0}/labels.json'.format(label_cwd)
-    template = '{0}/{1}/labels'.format(repos_template,
-                                       repository['full_name'])
-    _backup_data(args,
-                 'labels',
-                 template,
-                 output_file,
-                 label_cwd)
-
-
-def backup_hooks(args, repo_cwd, repository, repos_template):
-    auth = get_auth(args)
-    if not auth:
-        log_info("Skipping hooks since no authentication provided")
-        return
-    hook_cwd = os.path.join(repo_cwd, 'hooks')
-    output_file = '{0}/hooks.json'.format(hook_cwd)
-    template = '{0}/{1}/hooks'.format(repos_template,
-                                      repository['full_name'])
-    try:
-        _backup_data(args,
-                     'hooks',
-                     template,
-                     output_file,
-                     hook_cwd)
-    except SystemExit:
-        log_info("Unable to read hooks, skipping")
-
-
-def fetch_repository(name,
-                     remote_url,
-                     local_dir,
-                     skip_existing=False,
-                     bare_clone=False):
-    if bare_clone:
-        if os.path.exists(local_dir):
-            clone_exists = subprocess.check_output(['git',
-                                                    'rev-parse',
-                                                    '--is-bare-repository'],
-                                                   cwd=local_dir) == "true\n"
-        else:
-            clone_exists = False
-    else:
-        clone_exists = os.path.exists(os.path.join(local_dir, '.git'))
-
-    if clone_exists and skip_existing:
-        return
-
-    masked_remote_url = mask_password(remote_url)
-
-    initialized = subprocess.call('git ls-remote ' + remote_url,
-                                  stdout=FNULL,
-                                  stderr=FNULL,
-                                  shell=True)
-    if initialized == 128:
-        log_info("Skipping {0} ({1}) since it's not initialized".format(
-            name, masked_remote_url))
-        return
-
-    if clone_exists:
-        log_info('Updating {0} in {1}'.format(name, local_dir))
-
-        remotes = subprocess.check_output(['git', 'remote', 'show'],
-                                          cwd=local_dir)
-        remotes = [i.strip() for i in remotes.decode('utf-8').splitlines()]
-
-        if 'origin' not in remotes:
-            git_command = ['git', 'remote', 'rm', 'origin']
-            logging_subprocess(git_command, None, cwd=local_dir)
-            git_command = ['git', 'remote', 'add', 'origin', remote_url]
-            logging_subprocess(git_command, None, cwd=local_dir)
-        else:
-            git_command = ['git', 'remote', 'set-url', 'origin', remote_url]
-            logging_subprocess(git_command, None, cwd=local_dir)
-
-        git_command = ['git', 'fetch', '--all', '--force', '--tags', '--prune']
-        logging_subprocess(git_command, None, cwd=local_dir)
-    else:
-        log_info('Cloning {0} repository from {1} to {2}'.format(
-            name,
-            masked_remote_url,
-            local_dir))
-        if bare_clone:
-            git_command = ['git', 'clone', '--mirror', remote_url, local_dir]
-        else:
-            git_command = ['git', 'clone', remote_url, local_dir]
-        logging_subprocess(git_command, None)
-
-
-def backup_account(args, output_directory):
-    account_cwd = os.path.join(output_directory, 'account')
-
-    if args.include_starred or args.include_everything:
-        output_file = '{0}/starred.json'.format(account_cwd)
-        template = "https://{0}/users/{1}/starred"
-        template = template.format(get_github_api_host(args), args.user)
-        _backup_data(args,
-                     'starred repositories',
-                     template,
-                     output_file,
-                     account_cwd)
-
-    if args.include_watched or args.include_everything:
-        output_file = '{0}/watched.json'.format(account_cwd)
-        template = "https://{0}/users/{1}/subscriptions"
-        template = template.format(get_github_api_host(args), args.user)
-        _backup_data(args,
-                     'watched repositories',
-                     template,
-                     output_file,
-                     account_cwd)
-
-
-def _backup_data(args, name, template, output_file, output_directory):
-    skip_existing = args.skip_existing
-    if not skip_existing or not os.path.exists(output_file):
-        log_info('Retrieving {0} {1}'.format(args.user, name))
-        mkdir_p(output_directory)
-        data = retrieve_data(args, template)
-
-        log_info('Writing {0} {1} to disk'.format(len(data), name))
-        with codecs.open(output_file, 'w', encoding='utf-8') as f:
-            json_dump(data, f)
-
-
-def json_dump(data, output_file):
-    json.dump(data,
-              output_file,
-              ensure_ascii=False,
-              sort_keys=True,
-              indent=4,
-              separators=(',', ': '))
-
+import os, sys, logging
+
+from github_backup.github_backup import (
+    backup_account,
+    backup_repositories,
+    check_git_lfs_install,
+    filter_repositories,
+    get_authenticated_user,
+    log_info,
+    log_warning,
+    mkdir_p,
+    parse_args,
+    retrieve_repositories,
+)
+
+logging.basicConfig(
+    format='%(asctime)s.%(msecs)03d: %(message)s',
+    datefmt='%Y-%m-%dT%H:%M:%S',
+    level=logging.INFO
+)
 
 def main():
     args = parse_args()
@@ -847,13 +29,29 @@ def main():
         log_info('Create output directory {0}'.format(output_directory))
         mkdir_p(output_directory)
 
-    log_info('Backing up user {0} to {1}'.format(args.user, output_directory))
+    if args.lfs_clone:
+        check_git_lfs_install()
 
-    repositories = retrieve_repositories(args)
+    if args.log_level:
+        log_level = logging.getLevelName(args.log_level.upper())
+        if isinstance(log_level, int):
+            logging.root.setLevel(log_level)
+
+    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)
     backup_account(args, output_directory)
 
 
 if __name__ == '__main__':
+    try:
         main()
+    except Exception as e:
+        log_warning(str(e))
+        sys.exit(1)

github_backup/__init__.py

@@ -1 +1 @@
-__version__ = '0.13.2'
+__version__ = "0.43.0"

release

@@ -1,8 +1,13 @@
 #!/usr/bin/env bash
 set -eo pipefail; [[ $RELEASE_TRACE ]] && set -x
 
-PACKAGE_NAME='github-backup'
-INIT_PACKAGE_NAME='github_backup'
+if [[ ! -f setup.py ]]; then
+  echo -e "${RED}WARNING: Missing setup.py${COLOR_OFF}\n"
+  exit 1
+fi
+
+PACKAGE_NAME="$(cat setup.py | grep 'name="' | head | cut -d '"' -f2)"
+INIT_PACKAGE_NAME="$(echo "${PACKAGE_NAME//-/_}")"
 PUBLIC="true"
 
 # Colors
@@ -17,7 +22,7 @@ CYAN="\033[0;36m"     # cyan
 pip install wheel > /dev/null
 
 command -v gitchangelog >/dev/null 2>&1 || {
-    echo -e "${RED}WARNING: Missing gitchangelog binary, please run: pip install gitchangelog==2.2.0${COLOR_OFF}\n"
+    echo -e "${RED}WARNING: Missing gitchangelog binary, please run: pip install gitchangelog==3.0.4${COLOR_OFF}\n"
     exit 1
 }
 
@@ -26,6 +31,11 @@ command -v rst-lint > /dev/null || {
     exit 1
 }
 
+command -v twine > /dev/null || {
+    echo -e "${RED}WARNING: Missing twine binary, please run: pip install twine==3.2.0${COLOR_OFF}\n"
+    exit 1
+}
+
 if [[ "$@" != "major" ]] && [[ "$@" != "minor" ]] && [[ "$@" != "patch" ]]; then
     echo -e "${RED}WARNING: Invalid release type, must specify 'major', 'minor', or 'patch'${COLOR_OFF}\n"
     exit 1
@@ -76,18 +86,12 @@ TMPFILE=$(mktemp /tmp/${tempfoo}.XXXXXX) || {
     exit 1
 }
 
-find_this="__version__ = '$current_version'"
-replace_with="__version__ = '$next_version'"
+find_this="__version__ = \"$current_version\""
+replace_with="__version__ = \"$next_version\""
 
 echo -e "${YELLOW}--->${COLOR_OFF} Updating ${INIT_PACKAGE_NAME}/__init__.py"
 sed "s/$find_this/$replace_with/" ${INIT_PACKAGE_NAME}/__init__.py > $TMPFILE && mv $TMPFILE ${INIT_PACKAGE_NAME}/__init__.py
 
-find_this="${PACKAGE_NAME}.git@$current_version"
-replace_with="${PACKAGE_NAME}.git@$next_version"
-
-echo -e "${YELLOW}--->${COLOR_OFF} Updating README.rst"
-sed "s/$find_this/$replace_with/" README.rst > $TMPFILE && mv $TMPFILE README.rst
-
 if [ -f docs/conf.py ]; then
     echo -e "${YELLOW}--->${COLOR_OFF} Updating docs"
     find_this="version = '${current_version}'"
@@ -120,7 +124,8 @@ git push -q origin master && git push -q --tags
 if [[ "$PUBLIC" == "true" ]]; then
     echo -e "${YELLOW}--->${COLOR_OFF} Creating python release"
     cp README.rst README
-    python setup.py sdist bdist_wheel upload > /dev/null
+    python setup.py sdist bdist_wheel > /dev/null
+    twine upload dist/*
     rm README
 fi
 

setup.py

@@ -5,6 +5,7 @@ from github_backup import __version__
 
 try:
     from setuptools import setup
+
     setup  # workaround for pyflakes issue #13
 except ImportError:
     from distutils.core import setup
@@ -15,6 +16,7 @@ except ImportError:
 # http://www.eby-sarna.com/pipermail/peak/2010-May/003357.html)
 try:
     import multiprocessing
+
     multiprocessing
 except ImportError:
     pass
@@ -25,23 +27,26 @@ def open_file(fname):
 
 
 setup(
-    name='github-backup',
+    name="github-backup",
     version=__version__,
-    author='Jose Diaz-Gonzalez',
-    author_email='github-backup@josediazgonzalez.com',
-    packages=['github_backup'],
-    scripts=['bin/github-backup'],
-    url='http://github.com/josegonzalez/python-github-backup',
-    license=open('LICENSE.txt').read(),
+    author="Jose Diaz-Gonzalez",
+    author_email="github-backup@josediazgonzalez.com",
+    packages=["github_backup"],
+    scripts=["bin/github-backup"],
+    url="http://github.com/josegonzalez/python-github-backup",
+    license="MIT",
     classifiers=[
-        'Development Status :: 5 - Production/Stable',
-        'Topic :: System :: Archiving :: Backup',
-        'License :: OSI Approved :: MIT License',
-        'Programming Language :: Python :: 2.6',
-        'Programming Language :: Python :: 2.7',
+        "Development Status :: 5 - Production/Stable",
+        "Topic :: System :: Archiving :: Backup",
+        "License :: OSI Approved :: MIT License",
+        "Programming Language :: Python :: 3.5",
+        "Programming Language :: Python :: 3.6",
+        "Programming Language :: Python :: 3.7",
+        "Programming Language :: Python :: 3.8",
     ],
-    description='backup a github user or organization',
-    long_description=open_file('README.rst').read(),
-    install_requires=open_file('requirements.txt').readlines(),
+    description="backup a github user or organization",
+    long_description=open_file("README.rst").read(),
+    long_description_content_type="text/x-rst",
+    install_requires=open_file("requirements.txt").readlines(),
     zip_safe=True,
 )