| Name | repo2data JSON |
| Version |
2.9.7
JSON |
| download |
| home_page | None |
| Summary | A Python package to automate the fetching and extraction of data from remote sources like Amazon S3, Zeonodo, Datalad, Google Drive, OSF, or any public download URL. |
| upload_time | 2024-11-20 20:06:56 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | >=3.7 |
| license | MIT License Copyright (c) 2019 SIMEXP Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions: The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software. THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. |
| keywords |
neurolibre
open-data
reproducible
osf
zenodo
datalad
conp
gdown
aws
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
awscli
patool
datalad
pytest
osfclient
gdown
zenodo-get
requests
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
[](https://circleci.com/gh/SIMEXP/Repo2Data) &color=white) [](https://www.python.org/downloads/release/python-360/) 
# Repo2Data
Repo2Data is a **python3** package that automatically fetches data from a remote server, and decompresses it if needed. Supported web data sources are [amazon s3](https://docs.aws.amazon.com/AmazonS3/latest/dev/Welcome.html), [datalad](https://www.datalad.org/), [osf](https://osf.io/), [Google drive](https://www.google.com/intl/en_ca/drive/), raw http(s) or specific python lib datasets (`sklearn.datasets.load`, `nilearn.datasets.fetch` etc...).
## Input
A `data_requirement.json` configuration file explaining what should be read, where should you store the data, and a project name (name of the folder where file will be downloaded).
```
{ "src": "https://github.com/SIMEXP/Repo2Data/archive/master.zip",
"dst": "./data",
"projectName": "repo2data_out"}
```
`src` is where you configure the upstream location for your data.
`dst` specifies where (which folder) the data should be downloaded.
`projectName` is the name of the directory where the data will be saved, such that you can access it at `{dst}/{projectName}`
## Output
The content of the server inside the specified folder.
## Execution
The tool can be executed through `bash` or imported as a python API.
#### Bash
If `data_requirement.json` is inside current directory, you can call the following on the command line:
```
repo2data
```
#### Python API
After defining the `data_requirement.json` and importing the module, first instanciate the `Repo2Data` object with:
```
from repo2data.repo2data import Repo2Data
# define data requirement path
data_req_path = os.path.join("data_requirement.json")
# download data
repo2data = Repo2Data(data_req_path)
```
You can then fetch the data with the `install` method, which returns a list to the output directory(ies) where the data was downloaded:
```
data_path = repo2data.install()
```
## Examples of data_requirement.json
###### archive file
Repo2Data will use `wget` if it detects a http link.
If this file is an archive, it will be automatically be decompressed using [patool](https://github.com/wummel/patool). Please unsure that you download the right package to unarchive the data (ex: `/usr/bin/tar` for `.tar.gz`).
```
{ "src": "https://github.com/SIMEXP/Repo2Data/archive/master.tar.gz",
"dst": "./data",
"projectName": "repo2data_wget"}
```
###### Google Drive
It can also download a file from [Google Drive](https://www.google.com/intl/en_ca/drive/) using [gdown](https://github.com/wkentaro/gdown).
You will need to make sure that your file is available **publically**, and get the project ID (a chain of 33 characters that you can find on the url).
Then you can construct the url with this ID:
`https://drive.google.com/uc?id=${PROJECT_ID}`
For example:
```
{ "src": "https://drive.google.com/uc?id=1_zeJqQP8umrTk-evSAt3wCLxAkTKo0lC",
"dst": "./data",
"projectName": "repo2data_gdrive"}
```
###### library data-package
You will need to put the script to import and download the data in the `src` field, the lib should be installed on the host machine.
Any lib function to fetch data needs a parameter so it know where is the output directory. To avoid dupplication of the destination parameter, please replace the parameter for the output dir in the function by `_dst`.
For example write `tf.keras.datasets.mnist.load_data(path=_dst)` instead of `tf.keras.datasets.mnist.load_data(path=/path/to/your/data)`.
Repo2Data will then automatically replace `_dst` by the one provided in the `dst` field.
```
{ "src": "import tensroflow as tf; tf.keras.datasets.mnist.load_data(path=_dst)",
"dst": "./data",
"projectName": "repo2data_lib"}
```
###### datalad
The `src` should be point to a `.git` link if using `datalad`, `Repo2Data` will then just call `datalad get`.
```
{ "src": "https://github.com/OpenNeuroDatasets/ds000005.git",
"dst": "./data",
"projectName": "repo2data_datalad"}
```
###### s3
To download an amazon s3 link, `Repo2Data` uses `aws s3 sync --no-sign-request` command. So you should provide the `s3://` bucket link of the data:
```
{ "src": "s3://openneuro.org/ds000005",
"dst": "./data",
"projectName": "repo2data_s3"}
```
###### osf
`Repo2Data` uses [osfclient](https://github.com/osfclient/osfclient) `osf -p PROJECT_ID clone` command. You will need to give the link to the **public** project containing your data `https://osf.io/.../`:
```
{ "src": "https://osf.io/fuqsk/",
"dst": "./data",
"projectName": "repo2data_osf"}
```
If you need to download a single file, or a list of files, you can do this using the `remote_filepath` field wich runs `osf -p PROJECT_ID fetch -f file`. For example to download two files (https://osf.io/aevrb/ and https://osf.io/bvuh6/), use a relative path to the root of the project:
```
{ "src": "https://osf.io/fuqsk/",
"remote_filepath": ["hello.txt", "test-subfolder/hello-from-subfolder.txt"],
"dst": "./data",
"projectName": "repo2data_osf_multiple"}
```
###### zenodo
The public data repository [zenodo](https://zenodo.org/) is also supported using [zenodo_get](https://gitlab.com/dvolgyes/zenodo_get). Make sure your project is public and it has a DOI with the form `10.5281/zenodo.XXXXXXX`:
```
{ "src": "10.5281/zenodo.6482995",
"dst": "./data",
"projectName": "repo2data_zenodo"}
```
###### multiple data
If you need to download many data at once, you can create a list of json. For example, to download different files from a repo :
```
{
"authors": {
"src": "https://github.com/tensorflow/tensorflow/blob/master/AUTHORS",
"dst": "./data",
"projectName": "repo2data_multiple1"
},
"license": {
"src": "https://github.com/tensorflow/tensorflow/blob/master/LICENSE",
"dst": "./data",
"projectName": "repo2data_multiple2"
}
}
```
## Install
### Docker (recommended)
This is the recommended way of using `Repo2Data`, because it encapsulate all the dependencies inside the container. It also features `scikit-learn` and `nilearn` to pull data from.
Clone this repo and build the docker image yourself :
```
git clone https://github.com/SIMEXP/Repo2Data
sudo docker build --tag repo2data ./Repo2Data/
```
### pip
To install `Datalad` you will need the latest version of [git-annex](https://git-annex.branchable.com/install/), please use the [package from neuro-debian](https://git-annex.branchable.com/install/) :
```
wget -O- http://neuro.debian.net/lists/stretch.us-nh.full | sudo tee /etc/apt/sources.list.d/neurodebian.sources.list
sudo apt-key adv --recv-keys --keyserver hkp://ipv4.pool.sks-keyservers.net:80 0xA5D32F012649A5A9
```
If you have troubles to download the key, please look at this [issue](https://github.com/jacobalberty/unifi-docker/issues/64).
You can now install with `pip`:
```
python3 -m pip install repo2data
```
## Usage
After creating the `data_requirement.json`, just use `repo2data` without any option:
```
repo2data
```
### requirement in another directory
If the `data_requirement.json` is in another directory, use the `-r` option:
```
repo2data -r /PATH/TO/data_requirement.json
```
### github repo url as input
Given a valid https github repository with a `data_requirement.json` at `HEAD` branch (under a `binder` directory or at its root), you can do:
```
repo2data -r GITHUB_REPO
```
An example of a valid `GITHUB_REPO` is: https://github.com/ltetrel/repo2data-caching-s3
### Trigger re-fetch
When you re-run Repo2Data with the same destination, it will automatically look for an existing `data_requirement.json` file in the downloaded folder.
If the configured `data_requirement.json` is the same (i.e. the [JSON dict](https://www.w3schools.com/python/python_json.asp) has the same fields) then it will not re-download.
To force the re-fetch (update existing files, add new files but keep the old files), you can add a new field or update an existing one in the `data_requirement.json`.
For example replace:
```
{ "src": "https://github.com/SIMEXP/Repo2Data/archive/master.zip",
"dst": "./data",
"projectName": "repo2data_out"}
```
by
```
{ "src": "https://github.com/SIMEXP/Repo2Data/archive/master.zip",
"dst": "./data",
"projectName": "repo2data_out",
"version": "1.1"}
```
This is especially usefull when the provenance link always stay the same (osf, google drive...).
### make `dst` field optionnal
##### using `dataLayout` field
In the case you have a fixed known layout for the data folder within a github repository, the `dst` field is not needed anymore.
To define what kind of layout you want, you can use the `dataLayout` field.
For now we just support the [neurolibre layout](https://docs.neurolibre.org/en/latest/SUBMISSION_STRUCTURE.html#preprint-repository-structure):
```
{ "src": "https://github.com/SIMEXP/Repo2Data/archive/master.zip",
"dataLayout": "neurolibre"}
```
If you need another data layout (like [YODA](https://f1000research.com/posters/7-1965) or [cookiecutter-data-science](https://drivendata.github.io/cookiecutter-data-science/)) you can create a feature request.
##### for administrator
You can disable the field `dst` by using the option
`repo2data --server`
In this case `Repo2Data` will put the data inside the folder `./data` from where it is run. This is usefull if you want to have full control over the destination (you are a server admin and don't want your users to control the destination).
### Docker
You will need to create a folder on your machine (containing a `data_requirement.json`) that the Docker container will access so `Repo2Data` can pull the data inside it, after you can use:
```
sudo docker run -v /PATH/TO/FOLDER:/data repo2data
```
(the container will run with `--server` enabled, so all the data in the container will be at `/data`)
A requirement from a github repo is also supported (so you don't need any `data_requirement.json` inside your host folder):
```
sudo docker run -v /PATH/TO/FOLDER:/data repo2data -r GITHUB_REPO
```
`Docker` mounts the host (your machine) folder into the container folder as `-v host_folder:container_folder`, so don't override `:/data`.
Raw data
{
"_id": null,
"home_page": null,
"name": "repo2data",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.7",
"maintainer_email": null,
"keywords": "neurolibre, open-data, reproducible, osf, zenodo, datalad, conp, gdown, aws",
"author": null,
"author_email": "ltetrel <roboneurolibre@gmail.com>, agahkarakuzu <agahkarakuzu@gmail.com>",
"download_url": "https://files.pythonhosted.org/packages/b9/8a/9654da3d59ce6a2d07a18129e1d76de0f2181f08c8cd5bb3d77f0b252218/repo2data-2.9.7.tar.gz",
"platform": null,
"description": "[](https://circleci.com/gh/SIMEXP/Repo2Data) &color=white) [](https://www.python.org/downloads/release/python-360/) \n# Repo2Data\nRepo2Data is a **python3** package that automatically fetches data from a remote server, and decompresses it if needed. Supported web data sources are [amazon s3](https://docs.aws.amazon.com/AmazonS3/latest/dev/Welcome.html), [datalad](https://www.datalad.org/), [osf](https://osf.io/), [Google drive](https://www.google.com/intl/en_ca/drive/), raw http(s) or specific python lib datasets (`sklearn.datasets.load`, `nilearn.datasets.fetch` etc...).\n \n## Input\n \nA `data_requirement.json` configuration file explaining what should be read, where should you store the data, and a project name (name of the folder where file will be downloaded).\n\n```\n{ \"src\": \"https://github.com/SIMEXP/Repo2Data/archive/master.zip\",\n \"dst\": \"./data\",\n \"projectName\": \"repo2data_out\"}\n```\n`src` is where you configure the upstream location for your data.\n\n`dst` specifies where (which folder) the data should be downloaded.\n\n`projectName` is the name of the directory where the data will be saved, such that you can access it at `{dst}/{projectName}`\n\n## Output\n\nThe content of the server inside the specified folder.\n\n## Execution\n\nThe tool can be executed through `bash` or imported as a python API.\n\n#### Bash\n\nIf `data_requirement.json` is inside current directory, you can call the following on the command line:\n\n```\nrepo2data\n```\n\n#### Python API\n\nAfter defining the `data_requirement.json` and importing the module, first instanciate the `Repo2Data` object with:\n\n```\nfrom repo2data.repo2data import Repo2Data\n\n# define data requirement path\ndata_req_path = os.path.join(\"data_requirement.json\")\n# download data\nrepo2data = Repo2Data(data_req_path)\n```\n\nYou can then fetch the data with the `install` method, which returns a list to the output directory(ies) where the data was downloaded:\n```\ndata_path = repo2data.install()\n```\n\n## Examples of data_requirement.json\n\n###### archive file\n\nRepo2Data will use `wget` if it detects a http link.\nIf this file is an archive, it will be automatically be decompressed using [patool](https://github.com/wummel/patool). Please unsure that you download the right package to unarchive the data (ex: `/usr/bin/tar` for `.tar.gz`).\n\n```\n{ \"src\": \"https://github.com/SIMEXP/Repo2Data/archive/master.tar.gz\",\n \"dst\": \"./data\",\n \"projectName\": \"repo2data_wget\"}\n```\n\n###### Google Drive\n\nIt can also download a file from [Google Drive](https://www.google.com/intl/en_ca/drive/) using [gdown](https://github.com/wkentaro/gdown).\nYou will need to make sure that your file is available **publically**, and get the project ID (a chain of 33 characters that you can find on the url).\nThen you can construct the url with this ID:\n`https://drive.google.com/uc?id=${PROJECT_ID}`\n\nFor example:\n```\n{ \"src\": \"https://drive.google.com/uc?id=1_zeJqQP8umrTk-evSAt3wCLxAkTKo0lC\",\n \"dst\": \"./data\",\n \"projectName\": \"repo2data_gdrive\"}\n```\n\n###### library data-package\n\nYou will need to put the script to import and download the data in the `src` field, the lib should be installed on the host machine.\n\nAny lib function to fetch data needs a parameter so it know where is the output directory. To avoid dupplication of the destination parameter, please replace the parameter for the output dir in the function by `_dst`.\n\nFor example write `tf.keras.datasets.mnist.load_data(path=_dst)` instead of `tf.keras.datasets.mnist.load_data(path=/path/to/your/data)`.\nRepo2Data will then automatically replace `_dst` by the one provided in the `dst` field.\n\n```\n{ \"src\": \"import tensroflow as tf; tf.keras.datasets.mnist.load_data(path=_dst)\",\n \"dst\": \"./data\",\n \"projectName\": \"repo2data_lib\"}\n```\n\n###### datalad\n\nThe `src` should be point to a `.git` link if using `datalad`, `Repo2Data` will then just call `datalad get`.\n\n```\n{ \"src\": \"https://github.com/OpenNeuroDatasets/ds000005.git\",\n \"dst\": \"./data\",\n \"projectName\": \"repo2data_datalad\"}\n```\n\n###### s3\n\nTo download an amazon s3 link, `Repo2Data` uses `aws s3 sync --no-sign-request` command. So you should provide the `s3://` bucket link of the data:\n\n```\n{ \"src\": \"s3://openneuro.org/ds000005\",\n \"dst\": \"./data\",\n \"projectName\": \"repo2data_s3\"}\n```\n\n###### osf\n\n`Repo2Data` uses [osfclient](https://github.com/osfclient/osfclient) `osf -p PROJECT_ID clone` command. You will need to give the link to the **public** project containing your data `https://osf.io/.../`:\n\n```\n{ \"src\": \"https://osf.io/fuqsk/\",\n \"dst\": \"./data\",\n \"projectName\": \"repo2data_osf\"}\n```\n\nIf you need to download a single file, or a list of files, you can do this using the `remote_filepath` field wich runs `osf -p PROJECT_ID fetch -f file`. For example to download two files (https://osf.io/aevrb/ and https://osf.io/bvuh6/), use a relative path to the root of the project:\n\n```\n{ \"src\": \"https://osf.io/fuqsk/\",\n \"remote_filepath\": [\"hello.txt\", \"test-subfolder/hello-from-subfolder.txt\"],\n \"dst\": \"./data\",\n \"projectName\": \"repo2data_osf_multiple\"}\n```\n\n###### zenodo\n\nThe public data repository [zenodo](https://zenodo.org/) is also supported using [zenodo_get](https://gitlab.com/dvolgyes/zenodo_get). Make sure your project is public and it has a DOI with the form `10.5281/zenodo.XXXXXXX`:\n\n```\n{ \"src\": \"10.5281/zenodo.6482995\",\n \"dst\": \"./data\",\n \"projectName\": \"repo2data_zenodo\"}\n```\n\n###### multiple data\n\nIf you need to download many data at once, you can create a list of json. For example, to download different files from a repo :\n\n```\n{\n \"authors\": {\n \"src\": \"https://github.com/tensorflow/tensorflow/blob/master/AUTHORS\",\n \"dst\": \"./data\",\n \"projectName\": \"repo2data_multiple1\"\n },\n \"license\": {\n \"src\": \"https://github.com/tensorflow/tensorflow/blob/master/LICENSE\",\n \"dst\": \"./data\",\n \"projectName\": \"repo2data_multiple2\"\n }\n}\n```\n## Install\n\n### Docker (recommended)\n\nThis is the recommended way of using `Repo2Data`, because it encapsulate all the dependencies inside the container. It also features `scikit-learn` and `nilearn` to pull data from.\n\nClone this repo and build the docker image yourself :\n```\ngit clone https://github.com/SIMEXP/Repo2Data\nsudo docker build --tag repo2data ./Repo2Data/\n```\n\n### pip\n\nTo install `Datalad` you will need the latest version of [git-annex](https://git-annex.branchable.com/install/), please use the [package from neuro-debian](https://git-annex.branchable.com/install/) :\n```\nwget -O- http://neuro.debian.net/lists/stretch.us-nh.full | sudo tee /etc/apt/sources.list.d/neurodebian.sources.list\nsudo apt-key adv --recv-keys --keyserver hkp://ipv4.pool.sks-keyservers.net:80 0xA5D32F012649A5A9\n```\nIf you have troubles to download the key, please look at this [issue](https://github.com/jacobalberty/unifi-docker/issues/64).\n\nYou can now install with `pip`:\n```\npython3 -m pip install repo2data\n```\n\n## Usage\n\nAfter creating the `data_requirement.json`, just use `repo2data` without any option:\n```\nrepo2data\n```\n\n### requirement in another directory\n\nIf the `data_requirement.json` is in another directory, use the `-r` option:\n```\nrepo2data -r /PATH/TO/data_requirement.json\n```\n\n### github repo url as input\n\nGiven a valid https github repository with a `data_requirement.json` at `HEAD` branch (under a `binder` directory or at its root), you can do:\n```\nrepo2data -r GITHUB_REPO\n```\n\nAn example of a valid `GITHUB_REPO` is: https://github.com/ltetrel/repo2data-caching-s3\n\n### Trigger re-fetch\n\nWhen you re-run Repo2Data with the same destination, it will automatically look for an existing `data_requirement.json` file in the downloaded folder.\nIf the configured `data_requirement.json` is the same (i.e. the [JSON dict](https://www.w3schools.com/python/python_json.asp) has the same fields) then it will not re-download.\n\nTo force the re-fetch (update existing files, add new files but keep the old files), you can add a new field or update an existing one in the `data_requirement.json`.\nFor example replace:\n```\n{ \"src\": \"https://github.com/SIMEXP/Repo2Data/archive/master.zip\",\n \"dst\": \"./data\",\n \"projectName\": \"repo2data_out\"}\n```\nby \n```\n{ \"src\": \"https://github.com/SIMEXP/Repo2Data/archive/master.zip\",\n \"dst\": \"./data\",\n \"projectName\": \"repo2data_out\",\n \"version\": \"1.1\"}\n```\nThis is especially usefull when the provenance link always stay the same (osf, google drive...).\n\n### make `dst` field optionnal\n\n##### using `dataLayout` field\nIn the case you have a fixed known layout for the data folder within a github repository, the `dst` field is not needed anymore.\nTo define what kind of layout you want, you can use the `dataLayout` field.\nFor now we just support the [neurolibre layout](https://docs.neurolibre.org/en/latest/SUBMISSION_STRUCTURE.html#preprint-repository-structure):\n```\n{ \"src\": \"https://github.com/SIMEXP/Repo2Data/archive/master.zip\",\n \"dataLayout\": \"neurolibre\"}\n```\nIf you need another data layout (like [YODA](https://f1000research.com/posters/7-1965) or [cookiecutter-data-science](https://drivendata.github.io/cookiecutter-data-science/)) you can create a feature request.\n\n##### for administrator\nYou can disable the field `dst` by using the option\n`repo2data --server`\n\nIn this case `Repo2Data` will put the data inside the folder `./data` from where it is run. This is usefull if you want to have full control over the destination (you are a server admin and don't want your users to control the destination).\n\n### Docker\n\nYou will need to create a folder on your machine (containing a `data_requirement.json`) that the Docker container will access so `Repo2Data` can pull the data inside it, after you can use:\n```\nsudo docker run -v /PATH/TO/FOLDER:/data repo2data\n```\n\n(the container will run with `--server` enabled, so all the data in the container will be at `/data`)\n\nA requirement from a github repo is also supported (so you don't need any `data_requirement.json` inside your host folder):\n```\nsudo docker run -v /PATH/TO/FOLDER:/data repo2data -r GITHUB_REPO\n```\n\n`Docker` mounts the host (your machine) folder into the container folder as `-v host_folder:container_folder`, so don't override `:/data`.\n\n",
"bugtrack_url": null,
"license": "MIT License Copyright (c) 2019 SIMEXP Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the \"Software\"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions: The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software. THE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. ",
"summary": "A Python package to automate the fetching and extraction of data from remote sources like Amazon S3, Zeonodo, Datalad, Google Drive, OSF, or any public download URL.",
"version": "2.9.7",
"project_urls": {
"Homepage": "https://github.com/SIMEXP/Repo2Data"
},
"split_keywords": [
"neurolibre",
" open-data",
" reproducible",
" osf",
" zenodo",
" datalad",
" conp",
" gdown",
" aws"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "eceedd10f2b48549378c9488a9bcb758fd1b428a4528ca84be0f13c5dc0de384",
"md5": "f865e292a7a509936214ac4d61a78031",
"sha256": "8f9b6790a12b0220553bf89e37df69da54855ebea36cad656651804b54ce37f9"
},
"downloads": -1,
"filename": "repo2data-2.9.7-py3-none-any.whl",
"has_sig": false,
"md5_digest": "f865e292a7a509936214ac4d61a78031",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.7",
"size": 11639,
"upload_time": "2024-11-20T20:06:54",
"upload_time_iso_8601": "2024-11-20T20:06:54.556325Z",
"url": "https://files.pythonhosted.org/packages/ec/ee/dd10f2b48549378c9488a9bcb758fd1b428a4528ca84be0f13c5dc0de384/repo2data-2.9.7-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "b98a9654da3d59ce6a2d07a18129e1d76de0f2181f08c8cd5bb3d77f0b252218",
"md5": "e1c6d399e3eb9627eab1278150c79dc9",
"sha256": "2d26a33894d6dcd394cb3c318e8c41d41b57b717c613cbb3f971977425a348e9"
},
"downloads": -1,
"filename": "repo2data-2.9.7.tar.gz",
"has_sig": false,
"md5_digest": "e1c6d399e3eb9627eab1278150c79dc9",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.7",
"size": 21424,
"upload_time": "2024-11-20T20:06:56",
"upload_time_iso_8601": "2024-11-20T20:06:56.391243Z",
"url": "https://files.pythonhosted.org/packages/b9/8a/9654da3d59ce6a2d07a18129e1d76de0f2181f08c8cd5bb3d77f0b252218/repo2data-2.9.7.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-11-20 20:06:56",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "SIMEXP",
"github_project": "Repo2Data",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"circle": true,
"requirements": [
{
"name": "awscli",
"specs": [
[
"==",
"1.21.0"
]
]
},
{
"name": "patool",
"specs": [
[
"==",
"1.12"
]
]
},
{
"name": "datalad",
"specs": [
[
"==",
"0.15.0"
]
]
},
{
"name": "pytest",
"specs": [
[
"==",
"6.2.0"
]
]
},
{
"name": "osfclient",
"specs": [
[
"==",
"0.0.5"
]
]
},
{
"name": "gdown",
"specs": [
[
"==",
"v4.6.0"
]
]
},
{
"name": "zenodo-get",
"specs": [
[
"==",
"1.3.4"
]
]
},
{
"name": "requests",
"specs": []
}
],
"lcname": "repo2data"
}
