def create_json_schema(source_key: str,
item_numbers: List[int] = None) -> dict:
client = ScrapinghubClient()
if helpers.is_collection_key(source_key):
store = api.get_collection(source_key)
items_count = store.count()
elif helpers.is_job_key(source_key):
job = client.get_job(source_key)
items_count = api.get_items_count(job)
store = job.items
else:
logger.error(f"{source_key} is not a job or collection key")
return
if items_count == 0:
logger.error(f"{source_key} does not have any items")
return
item_n_err = "{} is a bad item number, choose numbers between 0 and {}"
if item_numbers:
item_numbers.sort()
if item_numbers[-1] >= items_count or item_numbers[0] < 0:
logger.error(item_n_err.format(item_numbers[-1], items_count - 1))
return
else:
item_numbers = set_item_no(items_count)
samples = []
for n in item_numbers:
items = api.get_items(source_key, start_index=n, count=1)
samples.append(items[0])
return infer_schema(samples)
def data_quality_report(self, bucket: Optional[str] = None):
if helpers.is_collection_key(str(self.source)):
raise ValueError("Collections are not supported")
if not self.schema:
raise ValueError("Schema is empty")
IPython.display.clear_output()
DataQualityReport(self.source_items, self.schema, self.report, bucket)
def create_json_schema(source_key: str,
item_numbers: Optional[List[int]] = None) -> dict:
if helpers.is_collection_key(source_key):
store = api.get_collection(source_key)
items_count = store.count()
elif helpers.is_job_key(source_key):
job = ScrapinghubClient().get_job(source_key)
items_count = api.get_items_count(job)
else:
raise ValueError(
f"'{source_key}' is not a valid job or collection key")
if items_count == 0:
raise ValueError(f"'{source_key}' does not have any items")
item_n_err = "{} is a bad item number, choose numbers between 0 and {}"
if item_numbers:
item_numbers.sort()
if item_numbers[-1] >= items_count or item_numbers[0] < 0:
raise ValueError(
item_n_err.format(item_numbers[-1], items_count - 1))
else:
item_numbers = set_item_no(items_count)
samples = []
for n in item_numbers:
items = api.get_items(source_key, start_index=n, count=1, p_bar=None)
samples.append(items[0])
return infer_schema(samples)
def get_items(
source: Union[str, pd.DataFrame, RawItems],
start: int,
count: Optional[int],
filters: Optional[api.Filters],
expand: bool,
) -> Union[JobItems, CollectionItems]:
if isinstance(source, pd.DataFrame):
return Items.from_df(source, expand=expand)
elif isinstance(source, Iterable) and not isinstance(source, str):
return Items.from_array(source, expand=expand)
elif helpers.is_job_key(source):
return JobItems(key=source,
start=start,
count=count,
filters=filters,
expand=expand)
elif helpers.is_collection_key(source):
if start:
raise ValueError(
"Collections API does not support 'start' parameter")
return CollectionItems(key=source,
count=count,
filters=filters,
expand=expand)
else:
raise ValueError(
f"'{source}' is not a valid job or collection key")
def create_json_schema(source_key: str,
items_numbers: Optional[List[int]] = None) -> RawSchema:
"""Create schema based on sampled `source_key` items."""
if helpers.is_collection_key(source_key):
store = api.get_collection(source_key)
items_count = store.count()
start_mask = ""
elif helpers.is_job_key(source_key):
items_count = api.get_items_count(api.get_job(source_key))
start_mask = f"{source_key}/"
else:
raise ValueError(
f"'{source_key}' is not a valid job or collection key")
if items_count == 0:
raise ValueError(f"'{source_key}' does not have any items")
items_numbers = items_numbers or set_item_no(items_count)
if max(items_numbers) >= items_count or min(items_numbers) < 0:
raise ValueError(
f"Expected values between 0 and {items_count}, got '{items_numbers}'"
)
samples = []
for n in items_numbers:
item = api.get_items(source_key,
count=1,
start_index=n,
start=f"{start_mask}{n}",
p_bar=None)[0]
item.pop("_type", None)
item.pop("_key", None)
samples.append(item)
return infer_schema(samples)
def data_quality_report(self, bucket: Optional[str] = None):
if helpers.is_collection_key(self.source):
raise ValueError("Collections are not supported")
if not self.schema:
raise ValueError("Schema is empty")
if not self.report.results:
self.save_result(
schema_rules.validate(self.schema,
items_dicts=self.source_items.dicts,
fast=False))
DataQualityReport(self.source_items, self.schema, self.report, bucket)
def get_items(
source: Union[str, pd.DataFrame, RawItems],
count: Optional[int],
start: Optional[str],
filters: Optional[api.Filters],
) -> Items:
if isinstance(source, pd.DataFrame):
return Items.from_df(source)
elif isinstance(source, Iterable) and not isinstance(source, str):
return Items.from_array(cast(RawItems, source))
elif helpers.is_job_key(source):
return JobItems(source, count, int(start or 0), filters)
elif helpers.is_collection_key(source):
return CollectionItems(source, count, start, filters)
else:
raise ValueError(
f"'{source}' is not a valid job or collection key")
def get_items(
source: str,
start: int,
count: Optional[int],
filters: Optional[api.Filters],
expand: bool,
) -> Union[JobItems, CollectionItems]:
if helpers.is_job_key(source):
return JobItems(
key=source, start=start, count=count, filters=filters, expand=expand
)
elif helpers.is_collection_key(source):
if start:
raise ValueError("Collections API does not support 'start' parameter")
return CollectionItems(
key=source, count=count, filters=filters, expand=expand
)
else:
raise ValueError(f"'{source}' is not a valid job or collection key")
def get_source(source_key):
if helpers.is_collection_key(source_key):
return get_collection(source_key)
if helpers.is_job_key(source_key):
return ScrapinghubClient().get_job(source_key).items
def test_is_collection_key(c_key, expected):
assert h.is_collection_key(c_key) is expected
