def get_xml(self, save_as=None, as_string=False) -> XMLElement:
"""
Provides full data (all pages) in XML.
Parameters
----------
save_as: Union[str, None]
If defined, the results will (also) be saved as a
file. [Default: ``None``]
The value must be a path to a file with the correct
extension -- i.e. ``.xml`` for XML).
as_string: bool
.. versionadded:: 1.1.4
If ``False`` (default), returns an ``ElementTree``
object. Otherwise, returns the data as an XML string.
Returns
-------
xml.etree.ElementTree.Element
Examples
--------
>>> from xml.etree.ElementTree import tostring
>>> filters = ["areaType=region"]
>>> structure = {
... "name": "areaName",
... "newCases": "newCasesBySpecimenDate"
... }
>>> data = Cov19API(
... filters=filters,
... structure=structure,
... latest_by='newCasesBySpecimenDate'
... )
>>> result_xml = data.get_xml()
>>> result_str = tostring(result_xml, encoding='unicode', method='xml')
>>> print(result_str)
<document>
<data>
<name>East Midlands</name>
<newCases>0</newCases>
</data>
...
</document>
"""
from xml.etree.ElementTree import SubElement, fromstring
resp = XMLElement("document")
for response in self._get(DataFormat.XML):
decoded_content = response.content.decode()
# Parsing the XML:
parsed_data = fromstring(decoded_content)
# Extracting "data" elements from the tree:
page_data = parsed_data.findall(".//data")
resp.extend(page_data)
extras = {
"lastUpdate": self.last_update,
"length": len(resp.findall(".//data")),
"totalPages": self._total_pages
}
for elm_name, value in extras.items():
elm = SubElement(resp, elm_name)
elm.text = str(value)
if save_as is None and not as_string:
return resp
from xml.etree.ElementTree import tostring
str_data = tostring(resp, encoding='unicode', method='xml')
if as_string:
return str_data
save_data(str_data, save_as, DataFormat.XML)
return resp
def get_csv(self, save_as=None) -> str:
"""
Provides full data (all pages) in CSV.
.. warning::
Please make sure that the ``structure`` is not hierarchical as
CSV outputs are defined as 2D tables and as such, do not support
hierarchies.
Parameters
----------
save_as: Union[str, None]
If defined, the results will (also) be saved as a
file. [Default: ``None``]
The value must be a path to a file with the correct
extension -- i.e. ``.csv`` for CSV).
Returns
-------
str
Raises
------
ValueError
If the structure is nested.
Examples
--------
>>> filters = ["areaType=region"]
>>> structure = {
... "name": "areaName",
... "newCases": "newCasesBySpecimenDate"
... }
>>> data = Cov19API(
... filters=filters,
... structure=structure,
... latest_by='newCasesBySpecimenDate'
... )
>>> result = data.get_csv()
>>> print(result)
name,newCases
East Midlands,0
...
"""
# Checks to ensure that the structure is
# not hierarchical.
if isinstance(self.structure, dict):
non_str = filter(lambda val: not isinstance(val, str),
self.structure.values())
if list(non_str):
struct = dumps(self.structure, indent=4)
raise ValueError(
"CSV structure cannot be nested. Received:\n%s" % struct)
linebreak = "\n"
resp = str()
for page_num, response in enumerate(self._get(DataFormat.CSV),
start=1):
decoded_content = response.content.decode()
# Removing CSV header (column names) where page
# number is greater than 1.
if page_num > 1:
data_lines = decoded_content.split(linebreak)[1:]
decoded_content = str.join(linebreak, data_lines)
resp += decoded_content.strip() + linebreak
if save_as is None:
return resp
save_data(resp, save_as, DataFormat.CSV)
return resp
def get_json(self,
save_as: Union[str, None] = None,
as_string: bool = False) -> Union[dict, str]:
"""
Provides full data (all pages) in JSON.
Parameters
----------
save_as: Union[str, None]
If defined, the results will (also) be saved as a
file. [Default: ``None``]
The value must be a path to a file with the correct
extension -- i.e. ``.json`` for JSON).
as_string: bool
.. versionadded:: 1.1.4
If ``False`` (default), returns the data as a dictionary.
Otherwise, returns the data as a JSON string.
Returns
-------
Union[Dict, str]
Examples
--------
>>> filters = ["areaType=region"]
>>> structure = {
... "name": "areaName",
... "newCases": "newCasesBySpecimenDate"
... }
>>> data = Cov19API(
... filters=filters,
... structure=structure,
... latest_by='newCasesBySpecimenDate'
... )
>>> result = data.get_json()
>>> print(result)
{'data': [{'name': 'East Midlands', 'newCases': 0}, ... }
"""
resp = {"data": list()}
for response in self._get(DataFormat.JSON):
current_data = response.json()
page_data = current_data['data']
resp["data"].extend(page_data)
resp["lastUpdate"] = self.last_update
resp["length"] = len(resp["data"])
resp["totalPages"] = self._total_pages
if as_string:
return dumps(resp, separators=(",", ":"))
if save_as is None:
return resp
data = dumps(resp, separators=(",", ":"))
save_data(data, save_as, DataFormat.JSON)
return resp