python-github-backup/bin/github-backup at master · llpj/python-github-backup · GitHub

History

executable file

411 lines (318 loc) · 16.9 KB

Raw

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

130

131

132

133

134

135

136

137

138

139

140

141

142

143

144

145

146

147

148

149

150

151

152

153

154

155

156

157

158

159

160

161

162

163

164

165

166

167

168

169

170

171

172

173

174

175

176

177

178

179

180

181

182

183

184

185

186

187

188

189

190

191

192

193

194

195

196

197

198

199

200

201

202

203

204

205

206

207

208

209

210

211

212

213

214

215

216

217

218

219

220

221

222

223

224

225

226

227

228

229

230

231

232

233

234

235

236

237

238

239

240

241

242

243

244

245

246

247

248

249

250

251

252

253

254

255

256

257

258

259

260

261

262

263

264

265

266

267

268

269

270

271

272

273

274

275

276

277

278

279

280

281

282

283

284

285

286

287

288

289

290

291

292

293

294

295

296

297

298

299

300

301

302

303

304

305

306

307

308

309

310

311

312

313

314

315

316

317

318

319

320

321

322

323

324

325

326

327

328

329

330

331

332

333

334

335

336

337

338

339

340

341

342

343

344

345

346

347

348

349

350

351

352

353

354

355

356

357

358

359

360

361

362

363

364

365

366

367

368

369

370

371

372

373

374

375

376

377

378

379

380

381

382

383

384

385

386

387

388

389

390

391

392

393

394

395

396

397

398

399

400

401

402

403

404

405

406

407

408

409

410

411

#!/usr/bin/env python

from __future__ import print_function

import argparse

import base64

import calendar

import errno

import json

import logging

import os

import re

import select

import subprocess

import sys

import time

import urllib

import urllib2

from github_backup import __version__

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(u'{} returned {}:'.format(popenargs[0], rc), file=sys.stderr)

print('\t', u' '.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 parse_args():

parser = argparse.ArgumentParser(description='Backup a github users account', prog='Github Backup')

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')

parser.add_argument('-t', '--token', dest='token', help='personal access or OAuth token')

parser.add_argument('-o', '--output-directory', default='.', dest='output_directory', help='directory at which to backup the repositories')

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('--repositories', action='store_true', dest='include_repository', help='include repository clone in backup')

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 a query for an organization')

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__)

return parser.parse_args()

def get_auth(args):

auth = None

if args.token:

auth = base64.b64encode(args.token + ':' + 'x-oauth-basic')

elif args.username and args.password:

auth = base64.b64encode(args.username + ':' + args.password)

elif args.username and not args.password:

log_error('You must specify a password for basic auth when specifying a username')

elif args.password and not args.username:

log_error('You must specify a username for basic auth when specifying a password')

return auth

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_ssh_host(args):

if args.github_host:

host = args.github_host

else:

host = 'github.com'

return host

def retrieve_data(args, template, query_args=None, single_request=False):

auth = get_auth(args)

per_page = 100

page = 0

data = []

if not query_args:

query_args = {}

while True:

page = page + 1

querystring = urllib.urlencode(dict({

'per_page': per_page,

'page': page

}.items() + query_args.items()))

request = urllib2.Request(template + '?' + querystring)

if auth is not None:

request.add_header('Authorization', 'Basic ' + auth)

errors = []

# We'll make requests in a loop so we can delay and retry in the case of rate-limiting

while True:

try:

r = urllib2.urlopen(request)

except urllib2.HTTPError as exc:

# HTTPError behaves like a Response so we can check the status code and headers to see exactly

# what failed.

limit_remaining = int(exc.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(exc.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 = exc.headers.get('x-ratelimit-limit')

print('Exceeded rate limit of {} requests; waiting {} seconds to reset'.format(limit, delta),

file=sys.stderr)

ratelimit_error = 'No more requests remaining'

if auth is None:

ratelimit_error = ratelimit_error + '; authenticate to raise your GitHub rate limit'

errors.append(ratelimit_error)

time.sleep(delta)

continue

break

status_code = int(r.getcode())

if status_code != 200:

errors.append('API request returned HTTP {}: {}'.format(status_code, r.reason))

log_error(errors)

response = json.loads(r.read())

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 retrieve_repositories(args):

log_info('Retrieving repositories')

single_request = False

template = 'https://{0}/users/{1}/repos'.format(get_github_api_host(args), args.user)

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, repositories):

log_info('Filtering repositories')

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]

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))

issue_states = ['open', 'closed']

pull_states = ['open', 'closed']

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')

if args.prefer_ssh:

repo_url = repository['ssh_url']

else:

repo_url = repository['git_url']

if args.include_repository or args.include_everything:

fetch_repository(repository['name'], repo_url, repo_dir, skip_existing=args.skip_existing)

if repository['has_wiki'] and (args.include_wiki or args.include_everything):

fetch_repository(repository['name'],

repo_url.replace('.git', '.wiki.git'),

os.path.join(repo_cwd, 'wiki'),

skip_existing=args.skip_existing)

if args.include_issues or args.include_everything:

if args.skip_existing and os.path.isdir('{0}/issues/.git'.format(repo_cwd)):

continue

log_info('Retrieving {0} issues'.format(repository['full_name']))

issue_cwd = os.path.join(repo_cwd, 'issues')

mkdir_p(backup_cwd, repo_cwd, issue_cwd)

issues = {}

_issue_template = '{0}/{1}/issues'.format(repos_template, repository['full_name'])

for issue_state in issue_states:

query_args = {

'filter': 'all',

'state': issue_state

}

_issues = retrieve_data(args, _issue_template, query_args=query_args)

for issue in _issues:

issues[issue['number']] = issue

log_info('Saving {0} issues to disk'.format(len(issues.keys())))

for number, issue in issues.iteritems():

comments_template = _issue_template + '/{0}/comments'

events_template = _issue_template + '/{0}/events'

if args.include_issue_comments or args.include_everything:

issues[number]['comment_data'] = retrieve_data(args, comments_template.format(number))

if args.include_issue_events or args.include_everything:

issues[number]['event_data'] = retrieve_data(args, events_template.format(number))

with open('{0}/{1}.json'.format(issue_cwd, number), 'w') as issue_file:

json.dump(issue, issue_file, sort_keys=True, indent=4, separators=(',', ': '))

if args.include_pulls or args.include_everything:

if args.skip_existing and os.path.isdir('{0}/pulls/.git'.format(repo_cwd)):

continue

log_info('Retrieving {0} pull requests'.format(repository['full_name']))

pulls_cwd = os.path.join(repo_cwd, 'pulls')

mkdir_p(backup_cwd, repo_cwd, pulls_cwd)

pulls = {}

_pulls_template = '{0}/{1}/pulls'.format(repos_template, repository['full_name'])

for pull_state in pull_states:

query_args = {

'filter': 'all',

'state': pull_state

}

_pulls = retrieve_data(args, _pulls_template, query_args=query_args)

for pull in _pulls:

pulls[pull['number']] = pull

log_info('Saving {0} pull requests to disk'.format(len(pulls.keys())))

for number, pull in pulls.iteritems():

comments_template = _pulls_template + '/{0}/comments'

commits_template = _pulls_template + '/{0}/commits'

if args.include_pull_comments or args.include_everything:

pulls[number]['comment_data'] = retrieve_data(args, comments_template.format(number))

if args.include_pull_commits or args.include_everything:

pulls[number]['commit_data'] = retrieve_data(args, commits_template.format(number))

with open('{0}/{1}.json'.format(pulls_cwd, number), 'w') as pull_file:

json.dump(pull, pull_file, sort_keys=True, indent=4, separators=(',', ': '))

def fetch_repository(name, remote_url, local_dir, skip_existing=False):

clone_exists = os.path.exists(os.path.join(local_dir, '.git'))

if clone_exists and skip_existing:

return

if clone_exists:

log_info('Updating {} in {}'.format(name, local_dir))

git_command = ['git', 'fetch', '--all', '--tags', '--prune']

logging_subprocess(git_command, None, cwd=local_dir)

else:

log_info('Cloning {} repository from {} to {}'.format(name, remote_url, local_dir))

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:

if not args.skip_existing or not os.path.exists('{0}/starred.json'.format(account_cwd)):

log_info('Retrieving {0} starred repositories'.format(args.user))

mkdir_p(account_cwd)

starred_template = "https://{0}/users/{1}/starred"

starred = retrieve_data(args, starred_template.format(get_github_api_host(args), args.user))

log_info('Writing {0} starred repositories'.format(len(starred)))

with open('{0}/starred.json'.format(account_cwd), 'w') as starred_file:

json.dump(starred, starred_file, sort_keys=True, indent=4, separators=(',', ': '))

if args.include_watched or args.include_everything:

if not args.skip_existing or not os.path.exists('{0}/watched.json'.format(account_cwd)):

log_info('Retrieving {0} watched repositories'.format(args.user))

mkdir_p(account_cwd)

watched_template = "https://{0}/users/{1}/subscriptions"

watched = retrieve_data(args, watched_template.format(get_github_api_host(args), args.user))

log_info('Writing {0} watched repositories'.format(len(watched)))

with open('{0}/watched.json'.format(account_cwd), 'w') as watched_file:

json.dump(watched, watched_file, sort_keys=True, indent=4, separators=(',', ': '))

def main():

args = parse_args()

output_directory = os.path.realpath(args.output_directory)

if not os.path.isdir(output_directory):

log_error('Specified output directory is not a directory: {0}'.format(output_directory))

log_info('Backing up user {0} to {1}'.format(args.user, output_directory))

repositories = retrieve_repositories(args)

repositories = filter_repositories(args, repositories)

backup_repositories(args, output_directory, repositories)

backup_account(args, output_directory)

if __name__ == '__main__':

main()

python-github-backup/bin/github-backup at master · llpj/python-github-backup · GitHub

Expand file tree

Breadcrumbs

github-backup

Latest commit

History

Breadcrumbs

github-backup

File metadata and controls