Merge pull request #5 from micafer/osf_revert

Osf revert

datahugger/services.py

@@ -326,7 +326,7 @@ class OSFDataset(DatasetDownloader):
  API_URL = "https://api.osf.io/v2/nodes/"
 
  # the files and metadata about the dataset
- API_URL_META = "{api_url}{record_id}/files/"
+ API_URL_META = "{api_url}{record_id}/files/osfstorage/?format=jsonapi"
  META_FILES_JSONPATH = "data[*]"
 
  PAGINATION_JSONPATH = "links.next"
@@ -342,25 +342,6 @@ class OSFDataset(DatasetDownloader):
  ATTR_HASH_JSONPATH = "attributes.extra.hashes.sha256"
  ATTR_HASH_TYPE_VALUE = "sha256"
 
- def _get_node_providers(self):
- """Get the providers of a node."""
- record_id = self._params["record_id"]
- res = requests.get(f"{self.API_URL}/{record_id}/files/")
- return set([prov["attributes"]["provider"] for prov in res.json()["data"]])
-
- def _get_files_recursive(self, url, folder_name=None, base_url=None):
- files = []
- # In case of the top-level folder, we need to get first the providers
- if folder_name is None:
- for provider in self._get_node_providers():
- # and then the files of each provider
- files.extend(
- super()._get_files_recursive(f"{url}{provider}/", None, base_url)
- )
- else:
- files = super()._get_files_recursive(url, folder_name, base_url)
- return files
-
 
 class ZenodoDataset(DatasetDownloader):
  """Downloader for Zenodo repository.

tests/test_repositories.toml

@@ -47,8 +47,8 @@ location = "https://figshare.com/articles/dataset/Long-term_behavioral_repeatabi
 files = "cross_year_data2.csv"
 
 [[figshare]]
-location = "https://doi.org/10.15131/shef.data.22010159.v2"
-files = "ScHARR QUIT evaluation statistical and health economic analysis plan.pdf"
+location = "https://doi.org/10.15131/shef.data.26977237.v1"
+files = "README.txt"
 
 [[djehuty]]
 location = "https://doi.org/10.4121/21989216.v1"
@@ -62,10 +62,6 @@ files = "ReadmeFile.txt"
 location = "https://doi.org/10.5061/dryad.31zcrjdm5"
 files = "ReadmeFile.txt"
 
-[[osf]]
-location = "https://osf.io/ews27/"
-files = "Cross-comparison/amarlt1"
-
 [[osf]]
 location = "https://osf.io/kq573/"
 files = "nest_area_data.xlsx"