Release version 0.52.0

Skip DMCA'd repos which return a 451 response

.github/workflows/automatic-release.yml

@@ -18,7 +18,7 @@ jobs:
         runs-on: ubuntu-24.04
         steps:
             - name: Checkout repository
-              uses: actions/checkout@v5
+              uses: actions/checkout@v6
               with:
                 fetch-depth: 0
                 ssh-key: ${{ secrets.DEPLOY_PRIVATE_KEY }}

.github/workflows/docker.yml

@@ -38,7 +38,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v5
+        uses: actions/checkout@v6
         with:
           persist-credentials: false
 

.github/workflows/lint.yml

@@ -21,7 +21,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v5
+        uses: actions/checkout@v6
         with:
           fetch-depth: 0
       - name: Setup Python

.github/workflows/test.yml

@@ -21,7 +21,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v5
+        uses: actions/checkout@v6
         with:
           fetch-depth: 0
       - name: Setup Python

CHANGES.rst

@@ -1,9 +1,97 @@
 Changelog
 =========
 
-0.51.2 (2025-11-16)
+0.52.0 (2025-11-28)
 -------------------
 ------------------------
+- Skip DMCA'd repos which return a 451 response. [Rodos]
+
+  Log a warning and the link to the DMCA notice. Continue backing up
+  other repositories instead of crashing.
+
+  Closes #163
+- Chore(deps): bump restructuredtext-lint in the python-packages group.
+  [dependabot[bot]]
+
+  Bumps the python-packages group with 1 update: [restructuredtext-lint](https://github.com/twolfson/restructuredtext-lint).
+
+
+  Updates `restructuredtext-lint` from 1.4.0 to 2.0.2
+  - [Changelog](https://github.com/twolfson/restructuredtext-lint/blob/master/CHANGELOG.rst)
+  - [Commits](https://github.com/twolfson/restructuredtext-lint/compare/1.4.0...2.0.2)
+
+  ---
+  updated-dependencies:
+  - dependency-name: restructuredtext-lint
+    dependency-version: 2.0.2
+    dependency-type: direct:production
+    update-type: version-update:semver-major
+    dependency-group: python-packages
+  ...
+- Chore(deps): bump actions/checkout from 5 to 6. [dependabot[bot]]
+
+  Bumps [actions/checkout](https://github.com/actions/checkout) from 5 to 6.
+  - [Release notes](https://github.com/actions/checkout/releases)
+  - [Changelog](https://github.com/actions/checkout/blob/main/CHANGELOG.md)
+  - [Commits](https://github.com/actions/checkout/compare/v5...v6)
+
+  ---
+  updated-dependencies:
+  - dependency-name: actions/checkout
+    dependency-version: '6'
+    dependency-type: direct:production
+    update-type: version-update:semver-major
+  ...
+- Chore(deps): bump the python-packages group with 3 updates.
+  [dependabot[bot]]
+
+  Bumps the python-packages group with 3 updates: [click](https://github.com/pallets/click), [pytest](https://github.com/pytest-dev/pytest) and [keyring](https://github.com/jaraco/keyring).
+
+
+  Updates `click` from 8.3.0 to 8.3.1
+  - [Release notes](https://github.com/pallets/click/releases)
+  - [Changelog](https://github.com/pallets/click/blob/main/CHANGES.rst)
+  - [Commits](https://github.com/pallets/click/compare/8.3.0...8.3.1)
+
+  Updates `pytest` from 8.3.3 to 9.0.1
+  - [Release notes](https://github.com/pytest-dev/pytest/releases)
+  - [Changelog](https://github.com/pytest-dev/pytest/blob/main/CHANGELOG.rst)
+  - [Commits](https://github.com/pytest-dev/pytest/compare/8.3.3...9.0.1)
+
+  Updates `keyring` from 25.6.0 to 25.7.0
+  - [Release notes](https://github.com/jaraco/keyring/releases)
+  - [Changelog](https://github.com/jaraco/keyring/blob/main/NEWS.rst)
+  - [Commits](https://github.com/jaraco/keyring/compare/v25.6.0...v25.7.0)
+
+  ---
+  updated-dependencies:
+  - dependency-name: click
+    dependency-version: 8.3.1
+    dependency-type: direct:production
+    update-type: version-update:semver-patch
+    dependency-group: python-packages
+  - dependency-name: pytest
+    dependency-version: 9.0.1
+    dependency-type: direct:production
+    update-type: version-update:semver-major
+    dependency-group: python-packages
+  - dependency-name: keyring
+    dependency-version: 25.7.0
+    dependency-type: direct:production
+    update-type: version-update:semver-minor
+    dependency-group: python-packages
+  ...
+
+
+0.51.3 (2025-11-18)
+-------------------
+- Test: Add pagination tests for cursor and page-based Link headers.
+  [Rodos]
+- Use cursor based pagination. [Helio Machado]
+
+
+0.51.2 (2025-11-16)
+-------------------
 
 Fix
 ~~~

github_backup/__init__.py

@@ -1 +1 @@
-__version__ = "0.51.2"
+__version__ = "0.52.0"

github_backup/github_backup.py

@@ -37,6 +37,15 @@ FNULL = open(os.devnull, "w")
 FILE_URI_PREFIX = "file://"
 logger = logging.getLogger(__name__)
 
+
+class RepositoryUnavailableError(Exception):
+    """Raised when a repository is unavailable due to legal reasons (e.g., DMCA takedown)."""
+
+    def __init__(self, message, dmca_url=None):
+        super().__init__(message)
+        self.dmca_url = dmca_url
+
+
 # Setup SSL context with fallback chain
 https_ctx = ssl.create_default_context()
 if https_ctx.get_ca_certs():
@@ -592,27 +601,39 @@ def retrieve_data_gen(args, template, query_args=None, single_request=False):
     auth = get_auth(args, encode=not args.as_app)
     query_args = get_query_args(query_args)
     per_page = 100
-    page = 0
+    next_url = None
 
     while True:
         if single_request:
-            request_page, request_per_page = None, None
+            request_per_page = None
         else:
-            page = page + 1
+            request_per_page = per_page
-            request_page, request_per_page = page, per_page
 
         request = _construct_request(
             request_per_page,
-            request_page,
             query_args,
-            template,
+            next_url or template,
             auth,
             as_app=args.as_app,
             fine=True if args.token_fine is not None else False,
         )  # noqa
-        r, errors = _get_response(request, auth, template)
+        r, errors = _get_response(request, auth, next_url or template)
 
         status_code = int(r.getcode())
+
+        # Handle DMCA takedown (HTTP 451) - raise exception to skip entire repository
+        if status_code == 451:
+            dmca_url = None
+            try:
+                response_data = json.loads(r.read().decode("utf-8"))
+                dmca_url = response_data.get("block", {}).get("html_url")
+            except Exception:
+                pass
+            raise RepositoryUnavailableError(
+                "Repository unavailable due to legal reasons (HTTP 451)",
+                dmca_url=dmca_url
+            )
+
         # Check if we got correct data
         try:
             response = json.loads(r.read().decode("utf-8"))
@@ -644,15 +665,14 @@ def retrieve_data_gen(args, template, query_args=None, single_request=False):
             retries += 1
             time.sleep(5)
             request = _construct_request(
-                per_page,
+                request_per_page,
-                page,
                 query_args,
-                template,
+                next_url or template,
                 auth,
                 as_app=args.as_app,
                 fine=True if args.token_fine is not None else False,
             )  # noqa
-            r, errors = _get_response(request, auth, template)
+            r, errors = _get_response(request, auth, next_url or template)
 
             status_code = int(r.getcode())
             try:
@@ -682,7 +702,16 @@ def retrieve_data_gen(args, template, query_args=None, single_request=False):
             if type(response) is list:
                 for resp in response:
                     yield resp
-                if len(response) < per_page:
+                # Parse Link header for next page URL (cursor-based pagination)
+                link_header = r.headers.get("Link", "")
+                next_url = None
+                if link_header:
+                    # 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(">")]
+                            break
+                if not next_url:
                     break
             elif type(response) is dict and single_request:
                 yield response
@@ -735,22 +764,27 @@ def _get_response(request, auth, template):
 
 
 def _construct_request(
-    per_page, page, query_args, template, auth, as_app=None, fine=False
+    per_page, query_args, template, auth, as_app=None, fine=False
 ):
-    all_query_args = {}
+    # If template is already a full URL with query params (from Link header), use it directly
-    if per_page:
+    if "?" in template and template.startswith("http"):
-        all_query_args["per_page"] = per_page
+        request_url = template
-    if page:
+        # Extract query string for logging
-        all_query_args["page"] = page
+        querystring = template.split("?", 1)[1]
-    if query_args:
-        all_query_args.update(query_args)
-
-    request_url = template
-    if all_query_args:
-        querystring = urlencode(all_query_args)
-        request_url = template + "?" + querystring
     else:
-        querystring = ""
+        # Build URL with query parameters
+        all_query_args = {}
+        if per_page:
+            all_query_args["per_page"] = per_page
+        if query_args:
+            all_query_args.update(query_args)
+
+        request_url = template
+        if all_query_args:
+            querystring = urlencode(all_query_args)
+            request_url = template + "?" + querystring
+        else:
+            querystring = ""
 
     request = Request(request_url)
     if auth is not None:
@@ -766,7 +800,7 @@ def _construct_request(
                 "Accept", "application/vnd.github.machine-man-preview+json"
             )
 
-    log_url = template
+    log_url = template if "?" not in template else template.split("?")[0]
     if querystring:
         log_url += "?" + querystring
     logger.info("Requesting {}".format(log_url))
@@ -843,8 +877,7 @@ def download_file(url, path, auth, as_app=False, fine=False):
         return
 
     request = _construct_request(
-        per_page=100,
+        per_page=None,
-        page=1,
         query_args={},
         template=url,
         auth=auth,
@@ -1657,40 +1690,47 @@ def backup_repositories(args, output_directory, repositories):
 
                 continue  # don't try to back anything else for a gist; it doesn't exist
 
-        download_wiki = args.include_wiki or args.include_everything
+        try:
-        if repository["has_wiki"] and download_wiki:
+            download_wiki = args.include_wiki or args.include_everything
-            fetch_repository(
+            if repository["has_wiki"] and download_wiki:
-                repository["name"],
+                fetch_repository(
-                repo_url.replace(".git", ".wiki.git"),
+                    repository["name"],
-                os.path.join(repo_cwd, "wiki"),
+                    repo_url.replace(".git", ".wiki.git"),
-                skip_existing=args.skip_existing,
+                    os.path.join(repo_cwd, "wiki"),
-                bare_clone=args.bare_clone,
+                    skip_existing=args.skip_existing,
-                lfs_clone=args.lfs_clone,
+                    bare_clone=args.bare_clone,
-                no_prune=args.no_prune,
+                    lfs_clone=args.lfs_clone,
-            )
+                    no_prune=args.no_prune,
-        if args.include_issues or args.include_everything:
+                )
-            backup_issues(args, repo_cwd, repository, repos_template)
+            if args.include_issues or args.include_everything:
+                backup_issues(args, repo_cwd, repository, repos_template)
 
-        if args.include_pulls or args.include_everything:
+            if args.include_pulls or args.include_everything:
-            backup_pulls(args, repo_cwd, repository, repos_template)
+                backup_pulls(args, repo_cwd, repository, repos_template)
 
-        if args.include_milestones or args.include_everything:
+            if args.include_milestones or args.include_everything:
-            backup_milestones(args, repo_cwd, repository, repos_template)
+                backup_milestones(args, repo_cwd, repository, repos_template)
 
-        if args.include_labels or args.include_everything:
+            if args.include_labels or args.include_everything:
-            backup_labels(args, repo_cwd, repository, repos_template)
+                backup_labels(args, repo_cwd, repository, repos_template)
 
-        if args.include_hooks or args.include_everything:
+            if args.include_hooks or args.include_everything:
-            backup_hooks(args, repo_cwd, repository, repos_template)
+                backup_hooks(args, repo_cwd, repository, repos_template)
 
-        if args.include_releases or args.include_everything:
+            if args.include_releases or args.include_everything:
-            backup_releases(
+                backup_releases(
-                args,
+                    args,
-                repo_cwd,
+                    repo_cwd,
-                repository,
+                    repository,
-                repos_template,
+                    repos_template,
-                include_assets=args.include_assets or args.include_everything,
+                    include_assets=args.include_assets or args.include_everything,
-            )
+                )
+        except RepositoryUnavailableError as e:
+            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']}")
+            continue
 
     if args.incremental:
         if last_update == "0000-00-00T00:00:00Z":

release-requirements.txt

@@ -3,16 +3,16 @@ black==25.11.0
 bleach==6.3.0
 certifi==2025.11.12
 charset-normalizer==3.4.4
-click==8.3.0
+click==8.3.1
 colorama==0.4.6
 docutils==0.22.3
 flake8==7.3.0
 gitchangelog==3.0.4
-pytest==8.3.3
+pytest==9.0.1
 idna==3.11
 importlib-metadata==8.7.0
 jaraco.classes==3.4.0
-keyring==25.6.0
+keyring==25.7.0
 markdown-it-py==4.0.0
 mccabe==0.7.0
 mdurl==0.1.2
@@ -28,7 +28,7 @@ Pygments==2.19.2
 readme-renderer==44.0
 requests==2.32.5
 requests-toolbelt==1.0.0
-restructuredtext-lint==1.4.0
+restructuredtext-lint==2.0.2
 rfc3986==2.0.0
 rich==14.2.0
 setuptools==80.9.0

tests/test_http_451.py

@@ -0,0 +1,143 @@
+"""Tests for HTTP 451 (DMCA takedown) handling."""
+
+import json
+from unittest.mock import Mock, patch
+
+import pytest
+
+from github_backup import github_backup
+
+
+class TestHTTP451Exception:
+    """Test suite for HTTP 451 DMCA takedown exception handling."""
+
+    def test_repository_unavailable_error_raised(self):
+        """HTTP 451 should raise RepositoryUnavailableError with DMCA URL."""
+        # Create mock args
+        args = Mock()
+        args.as_app = False
+        args.token_fine = None
+        args.token_classic = None
+        args.username = None
+        args.password = None
+        args.osx_keychain_item_name = None
+        args.osx_keychain_item_account = None
+        args.throttle_limit = None
+        args.throttle_pause = 0
+
+        # Mock HTTPError 451 response
+        mock_response = Mock()
+        mock_response.getcode.return_value = 451
+
+        dmca_data = {
+            "message": "Repository access blocked",
+            "block": {
+                "reason": "dmca",
+                "created_at": "2024-11-12T14:38:04Z",
+                "html_url": "https://github.com/github/dmca/blob/master/2024/11/2024-11-04-source-code.md"
+            }
+        }
+        mock_response.read.return_value = json.dumps(dmca_data).encode("utf-8")
+        mock_response.headers = {"x-ratelimit-remaining": "5000"}
+        mock_response.reason = "Unavailable For Legal Reasons"
+
+        def mock_get_response(request, auth, template):
+            return mock_response, []
+
+        with patch("github_backup.github_backup._get_response", side_effect=mock_get_response):
+            with pytest.raises(github_backup.RepositoryUnavailableError) as exc_info:
+                list(github_backup.retrieve_data_gen(args, "https://api.github.com/repos/test/dmca/issues"))
+
+            # Check exception has DMCA URL
+            assert exc_info.value.dmca_url == "https://github.com/github/dmca/blob/master/2024/11/2024-11-04-source-code.md"
+            assert "451" in str(exc_info.value)
+
+    def test_repository_unavailable_error_without_dmca_url(self):
+        """HTTP 451 without DMCA details should still raise exception."""
+        args = Mock()
+        args.as_app = False
+        args.token_fine = None
+        args.token_classic = None
+        args.username = None
+        args.password = None
+        args.osx_keychain_item_name = None
+        args.osx_keychain_item_account = None
+        args.throttle_limit = None
+        args.throttle_pause = 0
+
+        mock_response = Mock()
+        mock_response.getcode.return_value = 451
+        mock_response.read.return_value = b'{"message": "Blocked"}'
+        mock_response.headers = {"x-ratelimit-remaining": "5000"}
+        mock_response.reason = "Unavailable For Legal Reasons"
+
+        def mock_get_response(request, auth, template):
+            return mock_response, []
+
+        with patch("github_backup.github_backup._get_response", side_effect=mock_get_response):
+            with pytest.raises(github_backup.RepositoryUnavailableError) as exc_info:
+                list(github_backup.retrieve_data_gen(args, "https://api.github.com/repos/test/dmca/issues"))
+
+            # Exception raised even without DMCA URL
+            assert exc_info.value.dmca_url is None
+            assert "451" in str(exc_info.value)
+
+    def test_repository_unavailable_error_with_malformed_json(self):
+        """HTTP 451 with malformed JSON should still raise exception."""
+        args = Mock()
+        args.as_app = False
+        args.token_fine = None
+        args.token_classic = None
+        args.username = None
+        args.password = None
+        args.osx_keychain_item_name = None
+        args.osx_keychain_item_account = None
+        args.throttle_limit = None
+        args.throttle_pause = 0
+
+        mock_response = Mock()
+        mock_response.getcode.return_value = 451
+        mock_response.read.return_value = b"invalid json {"
+        mock_response.headers = {"x-ratelimit-remaining": "5000"}
+        mock_response.reason = "Unavailable For Legal Reasons"
+
+        def mock_get_response(request, auth, template):
+            return mock_response, []
+
+        with patch("github_backup.github_backup._get_response", side_effect=mock_get_response):
+            with pytest.raises(github_backup.RepositoryUnavailableError):
+                list(github_backup.retrieve_data_gen(args, "https://api.github.com/repos/test/dmca/issues"))
+
+    def test_other_http_errors_unchanged(self):
+        """Other HTTP errors should still raise generic Exception."""
+        args = Mock()
+        args.as_app = False
+        args.token_fine = None
+        args.token_classic = None
+        args.username = None
+        args.password = None
+        args.osx_keychain_item_name = None
+        args.osx_keychain_item_account = None
+        args.throttle_limit = None
+        args.throttle_pause = 0
+
+        mock_response = Mock()
+        mock_response.getcode.return_value = 404
+        mock_response.read.return_value = b'{"message": "Not Found"}'
+        mock_response.headers = {"x-ratelimit-remaining": "5000"}
+        mock_response.reason = "Not Found"
+
+        def mock_get_response(request, auth, template):
+            return mock_response, []
+
+        with patch("github_backup.github_backup._get_response", side_effect=mock_get_response):
+            # Should raise generic Exception, not RepositoryUnavailableError
+            with pytest.raises(Exception) as exc_info:
+                list(github_backup.retrieve_data_gen(args, "https://api.github.com/repos/test/notfound/issues"))
+
+            assert not isinstance(exc_info.value, github_backup.RepositoryUnavailableError)
+            assert "404" in str(exc_info.value)
+
+
+if __name__ == "__main__":
+    pytest.main([__file__, "-v"])

tests/test_pagination.py

@@ -0,0 +1,153 @@
+"""Tests for Link header pagination handling."""
+
+import json
+from unittest.mock import Mock, patch
+
+import pytest
+
+from github_backup import github_backup
+
+
+class MockHTTPResponse:
+    """Mock HTTP response for paginated API calls."""
+
+    def __init__(self, data, link_header=None):
+        self._content = json.dumps(data).encode("utf-8")
+        self._link_header = link_header
+        self._read = False
+        self.reason = "OK"
+
+    def getcode(self):
+        return 200
+
+    def read(self):
+        if self._read:
+            return b""
+        self._read = True
+        return self._content
+
+    def get_header(self, name, default=None):
+        """Mock method for headers.get()."""
+        return self.headers.get(name, default)
+
+    @property
+    def headers(self):
+        headers = {"x-ratelimit-remaining": "5000"}
+        if self._link_header:
+            headers["Link"] = self._link_header
+        return headers
+
+
+@pytest.fixture
+def mock_args():
+    """Mock args for retrieve_data_gen."""
+    args = Mock()
+    args.as_app = False
+    args.token_fine = None
+    args.token_classic = "fake_token"
+    args.username = None
+    args.password = None
+    args.osx_keychain_item_name = None
+    args.osx_keychain_item_account = None
+    args.throttle_limit = None
+    args.throttle_pause = 0
+    return args
+
+
+def test_cursor_based_pagination(mock_args):
+    """Link header with 'after' cursor parameter works correctly."""
+
+    # Simulate issues endpoint behavior: returns cursor in Link header
+    responses = [
+        # Issues endpoint returns 'after' cursor parameter (not 'page')
+        MockHTTPResponse(
+            data=[{"issue": i} for i in range(1, 101)],  # Page 1 contents
+            link_header='<https://api.github.com/repos/owner/repo/issues?per_page=100&after=ABC123&page=2>; rel="next"',
+        ),
+        MockHTTPResponse(
+            data=[{"issue": i} for i in range(101, 151)],  # Page 2 contents
+            link_header=None,  # No Link header - signals end of pagination
+        ),
+    ]
+    requests_made = []
+
+    def mock_urlopen(request, *args, **kwargs):
+        url = request.get_full_url()
+        requests_made.append(url)
+        return responses[len(requests_made) - 1]
+
+    with patch("github_backup.github_backup.urlopen", side_effect=mock_urlopen):
+        results = list(
+            github_backup.retrieve_data_gen(
+                mock_args, "https://api.github.com/repos/owner/repo/issues"
+            )
+        )
+
+    # Verify all items retrieved and cursor was used in second request
+    assert len(results) == 150
+    assert len(requests_made) == 2
+    assert "after=ABC123" in requests_made[1]
+
+
+def test_page_based_pagination(mock_args):
+    """Link header with 'page' parameter works correctly."""
+
+    # Simulate pulls/repos endpoint behavior: returns page numbers in Link header
+    responses = [
+        # Pulls endpoint uses traditional 'page' parameter (not cursor)
+        MockHTTPResponse(
+            data=[{"pull": i} for i in range(1, 101)],  # Page 1 contents
+            link_header='<https://api.github.com/repos/owner/repo/pulls?per_page=100&page=2>; rel="next"',
+        ),
+        MockHTTPResponse(
+            data=[{"pull": i} for i in range(101, 181)],  # Page 2 contents
+            link_header=None,  # No Link header - signals end of pagination
+        ),
+    ]
+    requests_made = []
+
+    def mock_urlopen(request, *args, **kwargs):
+        url = request.get_full_url()
+        requests_made.append(url)
+        return responses[len(requests_made) - 1]
+
+    with patch("github_backup.github_backup.urlopen", side_effect=mock_urlopen):
+        results = list(
+            github_backup.retrieve_data_gen(
+                mock_args, "https://api.github.com/repos/owner/repo/pulls"
+            )
+        )
+
+    # Verify all items retrieved and page parameter was used (not cursor)
+    assert len(results) == 180
+    assert len(requests_made) == 2
+    assert "page=2" in requests_made[1]
+    assert "after" not in requests_made[1]
+
+
+def test_no_link_header_stops_pagination(mock_args):
+    """Pagination stops when Link header is absent."""
+
+    # Simulate endpoint with results that fit in a single page
+    responses = [
+        MockHTTPResponse(
+            data=[{"label": i} for i in range(1, 51)],  # Page contents
+            link_header=None,  # No Link header - signals end of pagination
+        )
+    ]
+    requests_made = []
+
+    def mock_urlopen(request, *args, **kwargs):
+        requests_made.append(request.get_full_url())
+        return responses[len(requests_made) - 1]
+
+    with patch("github_backup.github_backup.urlopen", side_effect=mock_urlopen):
+        results = list(
+            github_backup.retrieve_data_gen(
+                mock_args, "https://api.github.com/repos/owner/repo/labels"
+            )
+        )
+
+    # Verify pagination stopped after first request
+    assert len(results) == 50
+    assert len(requests_made) == 1