github-backup 0.56.0__py3-none-any.whl → 0.57.0__py3-none-any.whl

github_backup/__init__.py

@@ -1 +1 @@
-__version__ = "0.56.0"
+__version__ = "0.57.0"

github_backup/github_backup.py

@@ -440,6 +440,12 @@ def parse_args(args=None):
         dest="include_assets",
         help="include assets alongside release information; only applies if including releases",
     )
+    parser.add_argument(
+        "--skip-assets-on",
+        dest="skip_assets_on",
+        nargs="*",
+        help="skip asset downloads for these repositories",
+    )
     parser.add_argument(
         "--attachments",
         action="store_true",
@@ -561,7 +567,7 @@ def get_github_host(args):
 
 
 def read_file_contents(file_uri):
-    return open(file_uri[len(FILE_URI_PREFIX):], "rt").readline().strip()
+    return open(file_uri[len(FILE_URI_PREFIX) :], "rt").readline().strip()
 
 
 def get_github_repo_url(args, repository):
@@ -631,7 +637,7 @@ def retrieve_data_gen(args, template, query_args=None, single_request=False):
                 pass
             raise RepositoryUnavailableError(
                 "Repository unavailable due to legal reasons (HTTP 451)",
-                dmca_url=dmca_url
+                dmca_url=dmca_url,
             )
 
         # Check if we got correct data
@@ -709,7 +715,7 @@ def retrieve_data_gen(args, template, query_args=None, single_request=False):
                     # Parse Link header: <https://api.github.com/...?per_page=100&after=cursor>; rel="next"
                     for link in link_header.split(","):
                         if 'rel="next"' in link:
-                            next_url = link[link.find("<") + 1:link.find(">")]
+                            next_url = link[link.find("<") + 1 : link.find(">")]
                             break
                 if not next_url:
                     break
@@ -763,9 +769,7 @@ def _get_response(request, auth, template):
     return r, errors
 
 
-def _construct_request(
-    per_page, query_args, template, auth, as_app=None, fine=False
-):
+def _construct_request(per_page, query_args, template, auth, as_app=None, fine=False):
     # If template is already a full URL with query params (from Link header), use it directly
     if "?" in template and template.startswith("http"):
         request_url = template
@@ -796,9 +800,6 @@ def _construct_request(
         else:
             auth = auth.encode("ascii")
             request.add_header("Authorization", "token ".encode("ascii") + auth)
-            request.add_header(
-                "Accept", "application/vnd.github.machine-man-preview+json"
-            )
 
     log_url = template if "?" not in template else template.split("?")[0]
     if querystring:
@@ -1480,9 +1481,11 @@ def download_attachments(
         manifest = {
             "issue_number": number,
             "issue_type": item_type,
-            "repository": f"{args.user}/{args.repository}"
-            if hasattr(args, "repository") and args.repository
-            else args.user,
+            "repository": (
+                f"{args.user}/{args.repository}"
+                if hasattr(args, "repository") and args.repository
+                else args.user
+            ),
             "manifest_updated_at": datetime.now(timezone.utc).isoformat(),
             "attachments": attachment_metadata_list,
         }
@@ -1538,9 +1541,7 @@ def retrieve_repositories(args, authenticated_user):
         else:
             repo_path = "{0}/{1}".format(args.user, args.repository)
         single_request = True
-        template = "https://{0}/repos/{1}".format(
-            get_github_api_host(args), repo_path
-        )
+        template = "https://{0}/repos/{1}".format(get_github_api_host(args), repo_path)
 
     repos = retrieve_data(args, template, single_request=single_request)
 
@@ -1565,7 +1566,10 @@ def retrieve_repositories(args, authenticated_user):
         repos.extend(gists)
 
     if args.include_starred_gists:
-        if not authenticated_user.get("login") or args.user.lower() != authenticated_user["login"].lower():
+        if (
+            not authenticated_user.get("login")
+            or args.user.lower() != authenticated_user["login"].lower()
+        ):
             logger.warning(
                 "Cannot retrieve starred gists for '%s'. GitHub only allows access to the authenticated user's starred gists.",
                 args.user,
@@ -1673,9 +1677,11 @@ def backup_repositories(args, output_directory, repositories):
 
         include_gists = args.include_gists or args.include_starred_gists
         include_starred = args.all_starred and repository.get("is_starred")
-        if (args.include_repository or args.include_everything) or (
-            include_gists and repository.get("is_gist")
-        ) or include_starred:
+        if (
+            (args.include_repository or args.include_everything)
+            or (include_gists and repository.get("is_gist"))
+            or include_starred
+        ):
             repo_name = (
                 repository.get("name")
                 if not repository.get("is_gist")
@@ -1735,7 +1741,9 @@ def backup_repositories(args, output_directory, repositories):
                     include_assets=args.include_assets or args.include_everything,
                 )
         except RepositoryUnavailableError as e:
-            logger.warning(f"Repository {repository['full_name']} is unavailable (HTTP 451)")
+            logger.warning(
+                f"Repository {repository['full_name']} is unavailable (HTTP 451)"
+            )
             if e.dmca_url:
                 logger.warning(f"DMCA notice: {e.dmca_url}")
             logger.info(f"Skipping remaining resources for {repository['full_name']}")
@@ -1795,7 +1803,11 @@ def backup_issues(args, repo_cwd, repository, repos_template):
             modified = os.path.getmtime(issue_file)
             modified = datetime.fromtimestamp(modified).strftime("%Y-%m-%dT%H:%M:%SZ")
             if modified > issue["updated_at"]:
-                logger.info("Skipping issue {0} because it wasn't modified since last backup".format(number))
+                logger.info(
+                    "Skipping issue {0} because it wasn't modified since last backup".format(
+                        number
+                    )
+                )
                 continue
 
         if args.include_issue_comments or args.include_everything:
@@ -1869,7 +1881,11 @@ def backup_pulls(args, repo_cwd, repository, repos_template):
             modified = os.path.getmtime(pull_file)
             modified = datetime.fromtimestamp(modified).strftime("%Y-%m-%dT%H:%M:%SZ")
             if modified > pull["updated_at"]:
-                logger.info("Skipping pull request {0} because it wasn't modified since last backup".format(number))
+                logger.info(
+                    "Skipping pull request {0} because it wasn't modified since last backup".format(
+                        number
+                    )
+                )
                 continue
         if args.include_pull_comments or args.include_everything:
             template = comments_regular_template.format(number)
@@ -1919,9 +1935,11 @@ def backup_milestones(args, repo_cwd, repository, repos_template):
     elif written_count == 0:
         logger.info("{0} milestones unchanged, skipped write".format(total))
     else:
-        logger.info("Saved {0} of {1} milestones to disk ({2} unchanged)".format(
-            written_count, total, total - written_count
-        ))
+        logger.info(
+            "Saved {0} of {1} milestones to disk ({2} unchanged)".format(
+                written_count, total, total - written_count
+            )
+        )
 
 
 def backup_labels(args, repo_cwd, repository, repos_template):
@@ -1975,6 +1993,20 @@ def backup_releases(args, repo_cwd, repository, repos_template, include_assets=F
         )
         releases = releases[: args.number_of_latest_releases]
 
+    # Check if this repo should skip asset downloads (case-insensitive)
+    skip_assets = False
+    if include_assets:
+        repo_name = repository.get("name", "").lower()
+        repo_full_name = repository.get("full_name", "").lower()
+        skip_repos = [r.lower() for r in (args.skip_assets_on or [])]
+        skip_assets = repo_name in skip_repos or repo_full_name in skip_repos
+        if skip_assets:
+            logger.info(
+                "Skipping assets for {0} ({1} releases) due to --skip-assets-on".format(
+                    repository.get("name"), len(releases)
+                )
+            )
+
     # for each release, store it
     written_count = 0
     for release in releases:
@@ -1986,7 +2018,7 @@ def backup_releases(args, repo_cwd, repository, repos_template, include_assets=F
         if json_dump_if_changed(release, output_filepath):
             written_count += 1
 
-        if include_assets:
+        if include_assets and not skip_assets:
             assets = retrieve_data(args, release["assets_url"])
             if len(assets) > 0:
                 # give release asset files somewhere to live & download them (not including source archives)
@@ -2008,9 +2040,11 @@ def backup_releases(args, repo_cwd, repository, repos_template, include_assets=F
     elif written_count == 0:
         logger.info("{0} releases unchanged, skipped write".format(total))
     else:
-        logger.info("Saved {0} of {1} releases to disk ({2} unchanged)".format(
-            written_count, total, total - written_count
-        ))
+        logger.info(
+            "Saved {0} of {1} releases to disk ({2} unchanged)".format(
+                written_count, total, total - written_count
+            )
+        )
 
 
 def fetch_repository(
@@ -2024,9 +2058,12 @@ def fetch_repository(
 ):
     if bare_clone:
         if os.path.exists(local_dir):
-            clone_exists = subprocess.check_output(
-                ["git", "rev-parse", "--is-bare-repository"], cwd=local_dir
-            ) == b"true\n"
+            clone_exists = (
+                subprocess.check_output(
+                    ["git", "rev-parse", "--is-bare-repository"], cwd=local_dir
+                )
+                == b"true\n"
+            )
         else:
             clone_exists = False
     else:
@@ -2047,7 +2084,9 @@ def fetch_repository(
             )
         else:
             logger.info(
-                "Skipping {0} (repository not accessible - may be empty, private, or credentials invalid)".format(name)
+                "Skipping {0} (repository not accessible - may be empty, private, or credentials invalid)".format(
+                    name
+                )
             )
         return
 

{github_backup-0.56.0.dist-info → github_backup-0.57.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: github-backup
-Version: 0.56.0
+Version: 0.57.0
 Summary: backup a github user or organization
 Home-page: http://github.com/josegonzalez/python-github-backup
 Author: Jose Diaz-Gonzalez
@@ -80,8 +80,8 @@ CLI Help output::
                   [--keychain-name OSX_KEYCHAIN_ITEM_NAME]
                   [--keychain-account OSX_KEYCHAIN_ITEM_ACCOUNT]
                   [--releases] [--latest-releases NUMBER_OF_LATEST_RELEASES]
-                  [--skip-prerelease] [--assets] [--attachments]
-                  [--exclude [REPOSITORY [REPOSITORY ...]]
+                  [--skip-prerelease] [--assets] [--skip-assets-on [REPO ...]]
+                  [--attachments] [--exclude [REPOSITORY [REPOSITORY ...]]
                   [--throttle-limit THROTTLE_LIMIT] [--throttle-pause THROTTLE_PAUSE]
                   USER
 
@@ -163,6 +163,9 @@ CLI Help output::
       --skip-prerelease     skip prerelease and draft versions; only applies if including releases
       --assets              include assets alongside release information; only
                             applies if including releases
+      --skip-assets-on [REPO ...]
+                            skip asset downloads for these repositories (e.g.
+                            --skip-assets-on repo1 owner/repo2)
       --attachments         download user-attachments from issues and pull requests
                             to issues/attachments/{issue_number}/ and
                             pulls/attachments/{pull_number}/ directories
@@ -204,6 +207,37 @@ Customise the permissions for your use case, but for a personal account full bac
 **Repository permissions**: Read access to contents, issues, metadata, pull requests, and webhooks.
 
 
+GitHub Apps
+~~~~~~~~~~~
+
+GitHub Apps are ideal for organization backups in CI/CD. Tokens are scoped to specific repositories and expire after 1 hour.
+
+**One-time setup:**
+
+1. Create a GitHub App at *Settings -> Developer Settings -> GitHub Apps -> New GitHub App*
+2. Set a name and homepage URL (can be any URL)
+3. Uncheck "Webhook > Active" (not needed for backups)
+4. Set permissions (same as fine-grained tokens above)
+5. Click "Create GitHub App", then note the **App ID** shown on the next page
+6. Under "Private keys", click "Generate a private key" and save the downloaded file
+7. Go to *Install App* in your app's settings
+8. Select the account/organization and which repositories to back up
+
+**CI/CD usage with GitHub Actions:**
+
+Store the App ID as a repository variable and the private key contents as a secret, then use ``actions/create-github-app-token``::
+
+    - uses: actions/create-github-app-token@v1
+      id: app-token
+      with:
+        app-id: ${{ vars.APP_ID }}
+        private-key: ${{ secrets.APP_PRIVATE_KEY }}
+
+    - run: github-backup myorg -t ${{ steps.app-token.outputs.token }} --as-app -o ./backup --all
+
+Note: Installation tokens expire after 1 hour. For long-running backups, use a fine-grained personal access token instead.
+
+
 Prefer SSH
 ~~~~~~~~~~
 
@@ -391,6 +425,9 @@ Debug an error/block or incomplete backup into a temporary directory. Omit "incr
 
     github-backup -f $FINE_ACCESS_TOKEN -o /tmp/github-backup/ -l debug -P --all-starred --starred --watched --followers --following --issues --issue-comments --issue-events --pulls --pull-comments --pull-commits --labels --milestones --repositories --wikis --releases --assets --pull-details --gists --starred-gists $GH_USER
 
+Pipe a token from stdin to avoid storing it in environment variables or command history (Unix-like systems only)::
+
+    my-secret-manager get github-token | github-backup user -t file:///dev/stdin -o /backup --repositories
 
 Restoring from Backup
 =====================

github_backup-0.57.0.dist-info/RECORD

@@ -0,0 +1,11 @@
+github_backup/__init__.py,sha256=jmnoPljZ40w5Zc7DEZpxkJSfC9yHbRjV50qzvnfEbdI,23
+github_backup/__main__.py,sha256=3yorCiC63maaxbjdtaeAs-G-yAAxKSO3mprhGfa1Fho,271
+github_backup/cli.py,sha256=zMUU0pTnh9KPqv8K--KNpUNf-yaA1qWeI6AdC1KVrn8,2361
+github_backup/github_backup.py,sha256=_P0WVPpZpyzs3PPkwtmIWDu2mkmeGXd2EePymeEtOV0,81890
+github_backup-0.57.0.dist-info/licenses/LICENSE.txt,sha256=ML-pLyn1qtAKo_DHMcQ8-p7k3f8cp-IR-mf5B49R2rk,1085
+github_backup-0.57.0.dist-info/METADATA,sha256=4Jni1TDR6oVFdIKCzjy6hacTh1TQrigaAeXVyidL-As,25921
+github_backup-0.57.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+github_backup-0.57.0.dist-info/entry_points.txt,sha256=cLPKK7MqC77QVb6HnT2mnyL_f-ciavJG_Y9vVHlCF68,57
+github_backup-0.57.0.dist-info/top_level.txt,sha256=Za6fKRAlxZ0b3ZBH_osPqklLe14LetdNAkvAQANT2AA,14
+github_backup-0.57.0.dist-info/zip-safe,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
+github_backup-0.57.0.dist-info/RECORD,,

github_backup-0.56.0.dist-info/RECORD

@@ -1,11 +0,0 @@
-github_backup/__init__.py,sha256=pLF99dIRilisWyZd9CliPPWqIlV81Xy8XtGEMuThTaM,23
-github_backup/__main__.py,sha256=3yorCiC63maaxbjdtaeAs-G-yAAxKSO3mprhGfa1Fho,271
-github_backup/cli.py,sha256=zMUU0pTnh9KPqv8K--KNpUNf-yaA1qWeI6AdC1KVrn8,2361
-github_backup/github_backup.py,sha256=wlVrA50q5iP8BbJ_6WIIMEP7MKl_B3cKm2zvEtNYMS4,80777
-github_backup-0.56.0.dist-info/licenses/LICENSE.txt,sha256=ML-pLyn1qtAKo_DHMcQ8-p7k3f8cp-IR-mf5B49R2rk,1085
-github_backup-0.56.0.dist-info/METADATA,sha256=0N-CqtE9r3amkSHGkrgR3YeG7wylthaM0Q2RDct5vbc,24230
-github_backup-0.56.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-github_backup-0.56.0.dist-info/entry_points.txt,sha256=cLPKK7MqC77QVb6HnT2mnyL_f-ciavJG_Y9vVHlCF68,57
-github_backup-0.56.0.dist-info/top_level.txt,sha256=Za6fKRAlxZ0b3ZBH_osPqklLe14LetdNAkvAQANT2AA,14
-github_backup-0.56.0.dist-info/zip-safe,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
-github_backup-0.56.0.dist-info/RECORD,,