-g GLOB, --glob=GLOB

.gitignore

@@ -0,0 +1,3 @@
+__pycache__/
+/dist/
+/*.egg*

.pre-commit-config.yaml

@@ -1,38 +1,30 @@
 repos:
--   repo: https://github.com/bemeurer/beautysh
-    rev: 'v6.2.1'
-    hooks:
-    - id: beautysh
--   repo: https://github.com/jumanjihouse/pre-commit-hooks
-    rev: '3.0.0'
-    hooks:
-    - id: shellcheck
--   repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.5.0
-    hooks:
-    - id: check-added-large-files
-    - id: check-case-conflict
-    - id: check-executables-have-shebangs
-    - id: check-json
-    - id: check-yaml
-    - id: check-xml
-    - id: check-symlinks
-    - id: check-vcs-permalinks
-    - id: trailing-whitespace
-    - id: detect-private-key
-    - id: end-of-file-fixer
-    - id: mixed-line-ending
--   repo: https://github.com/pycqa/flake8
-    rev: '6.1.0'  # pick a git hash / tag to point to
-    hooks:
-    - id: flake8
-      args: ["--ignore=E501,W503,E722"]
--   repo: https://github.com/psf/black-pre-commit-mirror
-    rev: 23.10.1
-    hooks:
-    - id: black
-      language_version: python3.11
--   repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.5.0
-    hooks:
-    - id: check-added-large-files
+- repo: https://github.com/lovesegfault/beautysh
+  rev: v6.2.1
+  hooks: [{id: beautysh}]
+- repo: https://github.com/jumanjihouse/pre-commit-hooks
+  rev: '3.0.0'
+  hooks: [{id: shellcheck}]
+- repo: https://github.com/pre-commit/pre-commit-hooks
+  rev: v4.6.0
+  hooks:
+  - id: check-added-large-files
+  - id: check-case-conflict
+  - id: check-executables-have-shebangs
+  - id: check-json
+  - id: check-yaml
+  - id: check-xml
+  - id: check-symlinks
+  - id: check-vcs-permalinks
+  - id: trailing-whitespace
+  - id: detect-private-key
+  - id: end-of-file-fixer
+  - id: mixed-line-ending
+- repo: https://github.com/pycqa/flake8
+  rev: '7.0.0'  # pick a git hash / tag to point to
+  hooks:
+  - id: flake8
+    args: ["--ignore=E203,E501,W503,E722"]
+- repo: https://github.com/psf/black
+  rev: '24.3.0'
+  hooks: [{id: black}]

README.md

@@ -64,6 +64,8 @@ Special parameters:
 - ``-m`` : generate md5sums.txt for verification. Beware, if `md5sums.txt` is
   present in the dataset, it will overwrite this generated file. Verification example:
   `md5sum -c md5sums.txt`
+- ``-g GLOB`` : A [glob](https://docs.python.org/3/library/fnmatch.html) expression to
+   select a subset of record files.
 - ``-w FILE`` : instead of downloading the record files, it will
    generate a FILE which contains direct links to the Zenodo site. These links
    could be downloaded with any download manager, e.g. with wget:
@@ -77,7 +79,7 @@ Special parameters:
 - ``-n`` : do not continue. The default behaviour is to download only the files
    which are not yet download or where the checksum does not match with the file.
    This flag disables this feature, and it will force download existing files,
-   and assigining a new name to the files (e.g. file(1).ext )
+   and assigning a new name to the files (e.g. file(1).ext )
 
 
 Remark for batch processing: the program always exits with non-zero exit code, if any error has happened,

appveyor.yml

@@ -16,7 +16,7 @@ matrix:
 
 platform:
     -x64
-    
+
 install:
     - "SET PATH=C:\\Python38-x64;%PATH%"
     - "python -m pip install -r requirements.txt"

setup.cfg

@@ -1,3 +1,2 @@
 [metadata]
 description-file = README.md
-

tests/test.sh

@@ -2,7 +2,7 @@
 set -e
 
 CMD="python3 -m coverage run -a --source zenodo_get -m zenodo_get"
-$CMD 
+$CMD
 $CMD  -h
 $CMD  --cite
 

tests/win-test.bat

@@ -5,4 +5,3 @@ python -m zenodo_get -d 10.5281/zenodo.1215979 -w urls.txt -n
 python -m zenodo_get  -r 1215979 -w -
 python -m zenodo_get  1215979 -R 3 -p 2 -n
 python -m zenodo_get 1215979
-

zenodo_get/zget.py

@@ -1,15 +1,16 @@
 #!/usr/bin/env python3
-import zenodo_get as zget
-import requests
 import hashlib
-import sys
 import os
-from optparse import OptionParser
-import wget
-import time
+import requests
 import signal
-from pathlib import Path
+import sys
+import time
+import wget
+import zenodo_get as zget
 from contextlib import contextmanager
+from fnmatch import fnmatch
+from optparse import OptionParser
+from pathlib import Path
 from urllib.parse import unquote
 
 
@@ -221,6 +222,16 @@ def zenodo_get(argv=None):
         help="Optional access token for the requests query.",
     )
 
+    parser.add_option(
+        "-g",
+        "--glob",
+        action="store",
+        type=str,
+        dest="glob",
+        default="*",
+        help="Optional glob expression for files.",
+    )
+
     (options, args) = parser.parse_args(argv)
 
     if options.cite:
@@ -306,7 +317,14 @@ def zenodo_get(argv=None):
 
         if r.ok:
             js = r.json()
-            files = js["files"]
+            files = [
+                f
+                for f in js["files"]
+                if fnmatch(f.get("filename") or f["key"], options.glob)
+            ]
+            if not files:
+                eprint("Files {} not found in metadata".format(options.glob))
+
             total_size = sum((f.get("filesize") or f["size"]) for f in files)
 
             if options.md5 is not None: