def retrieve(cls,
pdbs,
suffix: str,
folder: Path,
file_suffix: Optional[str] = None,
concur_req: int = 20,
rate: float = 1.5,
ret_res: bool = True,
**kwargs):
res = UnsyncFetch.multi_tasks(cls.yieldTasks(pdbs, suffix, file_suffix,
folder),
concur_req=concur_req,
rate=rate,
ret_res=ret_res,
semaphore=kwargs.get('semaphore', None))
return res
def retrieve(cls,
suffix: str,
params_collection: Iterable[Dict],
folder: Union[Path, str],
concur_req: int = 20,
rate: float = 1.5,
ret_res: bool = True,
**kwargs):
assert suffix in cls.api_set, f"Invalid suffix! Valid set is \n{cls.api_set}"
folder = Path(folder)
res = UnsyncFetch.multi_tasks(cls.yieldTasks(suffix, params_collection,
folder),
concur_req=concur_req,
rate=rate,
ret_res=ret_res,
semaphore=kwargs.get('semaphore', None))
return res
def retrieve(cls,
unps,
folder: Optional[Union[Path, str]] = None,
params: Dict = dict(provider='swissmodel'),
concur_req: int = 20,
rate: float = 1.5,
file_format: str = 'json',
ret_res: bool = True,
**kwargs):
assert file_format in ('json', 'pdb'), "Invalid file format"
res = UnsyncFetch.multi_tasks(
cls.yieldTasks(unps, params, file_format,
cls.folder if folder is None else folder),
cls.process,
concur_req=concur_req,
rate=rate,
ret_res=ret_res,
semaphore=kwargs.get('semaphore', cls.web_semaphore))
return res
def retrieve(cls,
pdbs: Union[Iterable, Iterator],
suffix: str,
method: str,
folder: Union[str, Path],
chunksize: int = 20,
concur_req: int = 20,
rate: float = 1.5,
task_id: int = 0,
ret_res: bool = True,
**kwargs):
# t0 = time.perf_counter()
res = UnsyncFetch.multi_tasks(cls.yieldTasks(pdbs, suffix, method,
folder, chunksize,
task_id),
cls.process,
concur_req=concur_req,
rate=rate,
ret_res=ret_res,
semaphore=kwargs.get('semaphore', None))
# elapsed = time.perf_counter() - t0
# cls.logger.info('{} ids downloaded in {:.2f}s'.format(len(res), elapsed))
return res
def retrieve_all_meta(cls, dataset: str = 'complete', suffix: str = 'user_data/{organism}/download/{dataset}/'):
tasks = [cls.task_unit(cls.folder, f'{suffix.format(organism=organism, dataset=dataset)}interactions.dat', '.tsv', f'{organism}_{dataset}_interactions') for organism in cls.organisms]
return UnsyncFetch.multi_tasks(tasks, semaphore=cls.get_web_semaphore())