├── ghrr ├── __init__.py ├── version.py └── main.py ├── influencers dashboard.png ├── .vscode ├── settings.json ├── tasks.json └── launch.json ├── requirements.txt ├── .devcontainer └── devcontainer.json ├── setup.py ├── README.md └── LICENSE /ghrr/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /ghrr/version.py: -------------------------------------------------------------------------------- 1 | version = '0.0.1' 2 | -------------------------------------------------------------------------------- /influencers dashboard.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/schosterbarak/ghrr/HEAD/influencers dashboard.png -------------------------------------------------------------------------------- /.vscode/settings.json: -------------------------------------------------------------------------------- 1 | { 2 | "files.exclude": { 3 | "**/.git": true, 4 | "**/.svn": true, 5 | "**/.hg": true, 6 | "**/CVS": true, 7 | "**/.DS_Store": true, 8 | "**/*.pyc": true, 9 | "**/__pycache__": true 10 | }, 11 | "python.pythonPath": ".venv" 12 | } -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | certifi==2022.9.24 2 | cffi==1.15.1 3 | charset-normalizer==2.1.1 4 | cryptography==38.0.3 5 | github3.py==3.2.0 6 | idna==3.4 7 | lxml==4.9.1 8 | pycparser==2.21 9 | PyJWT==2.6.0 10 | python-dateutil==2.8.2 11 | requests==2.28.1 12 | six==1.16.0 13 | tqdm==4.64.1 14 | uritemplate==4.1.1 15 | urllib3==1.26.12 16 | -------------------------------------------------------------------------------- /.vscode/tasks.json: -------------------------------------------------------------------------------- 1 | { 2 | "version": "2.0.0", 3 | "tasks": [ 4 | { 5 | "label": "pipInstall", 6 | "type": "shell", 7 | "osx": { 8 | "command": "${config:python.pythonPath}/bin/python -m pip install -r requirements.txt" 9 | }, 10 | "windows": { 11 | "command": "${config:python.pythonPath} -m pip install -r requirements.txt" 12 | }, 13 | "linux": { 14 | "command": "${config:python.pythonPath}/bin/python -m pip install -r requirements.txt" 15 | }, 16 | "problemMatcher": [], 17 | } 18 | ] 19 | } -------------------------------------------------------------------------------- /.vscode/launch.json: -------------------------------------------------------------------------------- 1 | { 2 | // Use IntelliSense to learn about possible attributes. 3 | // Hover to view descriptions of existing attributes. 4 | // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387 5 | "version": "0.2.0", 6 | "configurations": [ 7 | { 8 | "name": "Python: Current File", 9 | "type": "python", 10 | "request": "launch", 11 | "program": "${file}", 12 | "console": "integratedTerminal", 13 | "justMyCode": true, 14 | "preLaunchTask": "pipInstall", 15 | 16 | } 17 | ] 18 | } -------------------------------------------------------------------------------- /.devcontainer/devcontainer.json: -------------------------------------------------------------------------------- 1 | { 2 | "name": "Python 3", 3 | "image": "mcr.microsoft.com/devcontainers/python:3.10-bullseye", 4 | "features": { 5 | "ghcr.io/devcontainers/features/node:1": { 6 | "version": "none" 7 | }, 8 | "ghcr.io/devcontainers/features/github-cli:1": {} 9 | } 10 | 11 | // Use 'forwardPorts' to make a list of ports inside the container available locally. 12 | // "forwardPorts": [], 13 | 14 | // Use 'postCreateCommand' to run commands after the container is created. 15 | // "postCreateCommand": "pip3 install --user -r requirements.txt", 16 | 17 | // Configure tool-specific properties. 18 | // "customizations": {}, 19 | 20 | // Uncomment to connect as root instead. More info: https://aka.ms/dev-containers-non-root. 21 | // "remoteUser": "root" 22 | } 23 | -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | import logging 3 | import os 4 | from importlib import util 5 | from os import path 6 | 7 | import setuptools 8 | from setuptools import setup 9 | 10 | # read the contents of your README file 11 | this_directory = path.abspath(path.dirname(__file__)) 12 | with open(path.join(this_directory, "README.md"), encoding="utf-8") as f: 13 | long_description = f.read() 14 | 15 | logger = logging.getLogger(__name__) 16 | spec = util.spec_from_file_location( 17 | "ghrr.version", os.path.join("ghrr", "version.py") 18 | ) 19 | # noinspection PyUnresolvedReferences 20 | mod = util.module_from_spec(spec) 21 | spec.loader.exec_module(mod) # type: ignore 22 | version = mod.version # type: ignore 23 | 24 | setup( 25 | extras_require={ 26 | "dev": [ 27 | "github3.py==2.3.0" 28 | ] 29 | }, 30 | install_requires=[ 31 | "github3.py==2.3.0" 32 | ], 33 | license="Apache License 2.0", 34 | name="ghrr", 35 | version=version, 36 | description="GitHub Research Runner", 37 | author="schoster barak", 38 | author_email="schosterbarak@gmail.com", 39 | url="https://github.com/schosterbarak/ghrr", 40 | packages=setuptools.find_packages(exclude=["tests*","integration_tests*"]), 41 | long_description=long_description, 42 | long_description_content_type="text/markdown", 43 | classifiers=[ 44 | 'Environment :: Console', 45 | 'Intended Audience :: Developers', 46 | 'Intended Audience :: System Administrators', 47 | 'Programming Language :: Python :: 3.6', 48 | 'Programming Language :: Python :: 3.7', 49 | ] 50 | ) 51 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # GitHub Research Runner (ghrr) 2 | A utility to collect data from github stargazers, subscribers and contributors of a selected project. 3 | 4 | Usecases are detailed at the following blog: https://www.battery.com/blog/fantastic-developer-community-heroes-and-where-to-find-them/ 5 | 6 | ## installing 7 | 8 | ```bash 9 | 10 | git clone https://github.com/schosterbarak/ghrr.git 11 | cd ghrr 12 | python setup.py install 13 | 14 | ``` 15 | 16 | ## Using 17 | 1. Create github personal access token using the following guide: 18 | https://docs.github.com/en/github/authenticating-to-github/creating-a-personal-access-token 19 | 20 | 2. Run: 21 | ```bash 22 | export GITHUB_USER=XXX 23 | export GITHUB_TOKEN=YYY 24 | 25 | #an example command 26 | ghrr --org bridgecrewio --repo checkov 27 | 28 | ``` 29 | 30 | ## Result 31 | will be created at the following format under the working directory: 32 | `ghusers_{ORG}_{REPO}_{DATE}.csv` 33 | 34 | example: 35 | `ghusers_bridgecrewio_checkov_2020-09-21.csv` 36 | ` 37 | | username | company | organizations | email | location | followers_count | public_repos_count | user_iteraction | 38 | | -------- | ------- | ------------- | ------- | -------- | --------------- | ------------------ | --------------- | 39 | | Jon. | ACME. | ACME. | jon@acme.com | US | 3 | 200 | stargazer | 40 | | Jane | ACME. | ACME. | jane@acme.com | IL | 3 | 200 | collaborator | 41 | 42 | ` 43 | 44 | When loading to a BI tool: 45 | ![GitHub Influencers Dashboard](/influencers%20dashboard.png "GitHub Influencers Dashboard"). 46 | 47 | -------------------------------------------------------------------------------- /ghrr/main.py: -------------------------------------------------------------------------------- 1 | import argparse 2 | import csv 3 | import os, sys 4 | from datetime import date, datetime 5 | from collections import namedtuple 6 | from time import sleep 7 | from github3 import login 8 | from github3.exceptions import ForbiddenError 9 | from tqdm import tqdm 10 | 11 | 12 | RATE_LIMIT_BACKOFF= 10 13 | gh_user = os.getenv('GITHUB_USER') 14 | gh_token = os.getenv('GITHUB_TOKEN') 15 | 16 | parser = argparse.ArgumentParser(description='stargazers crawler') 17 | parser.add_argument('-o', '--organization', action='store', 18 | help='github organization', required=True) 19 | parser.add_argument('-r', '--repository', action='store', 20 | help='github repository', required=True) 21 | parser.add_argument('-f', '--file', action='store', 22 | help='output file path', required=False) 23 | 24 | warn = lambda msg: print(f'\033[93mError: {msg}\033[0m', file=sys.stderr) 25 | die = lambda msg: warn(msg) or exit(1) 26 | 27 | User = namedtuple('User', ['email', 'location','username','company','followers','repos','organizations']) 28 | 29 | def get_user_data(gh, u): 30 | username = u.login 31 | gh_user = gh.user(username) 32 | company = gh_user.company 33 | followers = gh_user.followers_count 34 | repos = gh_user.public_repos_count 35 | if company: 36 | company = company.replace("@", "") 37 | organizationsIterator = gh_user.organizations() 38 | organizations = [] 39 | for org in organizationsIterator: 40 | organizations.append(org.login) 41 | return User(gh_user.email, gh_user.location, username, company, followers, repos, organizations) 42 | 43 | def validate_params(args): 44 | if not gh_user: 45 | die("Please add GITHUB_USER environment variable") 46 | if not gh_token: 47 | die("Please add GITHUB_TOKEN environment variable") 48 | if not args.repository and not args.organization: 49 | die("No argument given. Try ` --help` for further information") 50 | 51 | 52 | class DummyUpdater(object): 53 | 54 | def update(self, c): 55 | pass 56 | 57 | class DummyProgress(object): 58 | def __init__(self, *args, **kwargs): 59 | pass 60 | def __enter__(self): 61 | return DummyUpdater() 62 | def __exit__(self, type, value, traceback): 63 | pass 64 | 65 | 66 | def wait_rate_limit(e: ForbiddenError): 67 | if not e.message.startswith('API rate limit exceeded'): 68 | raise e 69 | reset_time = e.response.headers.get('X-RateLimit-Reset') 70 | sleep_until = datetime.fromtimestamp(int(reset_time)) 71 | # add 3 seconds to compensate for clocks being clocks 72 | seconds_to_sleep = int((sleep_until - datetime.now()).total_seconds()) + 3 73 | sleep_until_pretty = sleep_until.strftime('%m/%d/%Y, %H:%M:%S') 74 | warn(f'Rate limited. sleeping until "{sleep_until_pretty}" due to rate limit...') 75 | sleep(seconds_to_sleep) 76 | 77 | 78 | def iterate_users(gh, users_iterator, users_count, user_writer,user_interaction, progress=True): 79 | total = users_count if users_count > 0 else None 80 | progress = tqdm(total=total, desc=f'Fetching {user_interaction} data', unit='users') if progress else DummyProgress() 81 | with progress as progress_bar: 82 | for u in users_iterator: 83 | data_received = False 84 | while not data_received: 85 | try: 86 | user = get_user_data(gh, u) 87 | user_writer.writerow([ 88 | user.username, 89 | user.company, 90 | user.organizations, 91 | user.email, 92 | user.location, 93 | user.followers, 94 | user.repos, 95 | user_interaction 96 | ]) 97 | data_received = True 98 | progress_bar.update(1) 99 | except ForbiddenError as e: 100 | wait_rate_limit(e) 101 | continue 102 | except Exception as ae: 103 | warn(f'got an unexpected error: {ae}, will wait a bit and try again') 104 | sleep(RATE_LIMIT_BACKOFF) 105 | 106 | 107 | if __name__ == '__main__': 108 | args = parser.parse_args() 109 | validate_params(args) 110 | repository = args.repository 111 | org = args.organization 112 | gh = login(gh_user, token=gh_token) 113 | repo_succeeded = False 114 | output = None 115 | progress = True 116 | while not repo_succeeded: 117 | try: 118 | gh_repository = gh.repository(org, repository) 119 | stargazers = gh_repository.stargazers() 120 | stargazers_count = gh_repository.stargazers_count 121 | contributors = gh_repository.contributors() 122 | subscribers = gh_repository.subscribers() 123 | subscribers_count = gh_repository.subscribers_count 124 | if not args.file: 125 | today = date.today() 126 | formated_today = today.strftime("%Y-%m-%d") # YY-MM-DD 127 | file_name = 'ghusers_{}_{}_{}.csv'.format(org, repository, formated_today) 128 | output = open(file_name, mode='w') 129 | elif args.file == '-': 130 | output = sys.stdout 131 | progress = False 132 | else: 133 | output = open(args.file, mode='w') 134 | repo_succeeded = True 135 | except ForbiddenError as e: 136 | wait_rate_limit(e) 137 | continue 138 | except Exception as ae: 139 | warn(f'got an unexpected error: {ae}, will wait a bit and try again') 140 | sleep(RATE_LIMIT_BACKOFF) 141 | 142 | with output as out: 143 | user_writer = csv.writer(out) 144 | user_writer.writerow(["username", "company", "organizations", "email", "location","followers_count","public_repos_count", "user_interaction"]) 145 | iterate_users(gh, stargazers, stargazers_count, user_writer,"stargazer", progress=progress) 146 | iterate_users (gh, subscribers, subscribers_count, user_writer,"subscriber", progress=progress) 147 | iterate_users (gh, contributors, -1, user_writer,"contributor", progress=progress) 148 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | --------------------------------------------------------------------------------