def process(self, document):
with get_source(document) as fh:
json_document = json.load(fh)
root_node = document.create_node(type='container')
self.parse_dict(json_document, root_node)
document.content_node = root_node
return document
def process(self, document):
with get_source(document) as fh:
data = fh.read()
try:
data = data.decode(self.encoding)
except (UnicodeDecodeError, AttributeError):
pass
text_node = document.create_node(type='text', content=data if self.decode else data)
document.content_node = text_node
return document
def execute_service(self, document, options, attach_source):
files = {}
if attach_source:
files["file"] = get_source(document)
else:
files["document"] = document.to_msgpack()
data = {"options": json.dumps(options)}
r = requests.post(
f"{self.cloud_url}/api/sessions/{self.cloud_session.id}/execute",
params={self.session_type: self.slug},
data=data,
headers={"x-access-token": self.access_token},
files=files)
execution = json.loads(r.text, object_hook=AttrDict)
print(execution)
return execution
def process(self, document):
"""
"""
with get_source(document) as fh:
if self.lines_as_child_nodes:
lines = fh.readlines()
document.content_node = document.create_node(node_type='text')
for data in lines:
text_node = document.create_node(
node_type='text',
content=self.decode_text(data).strip())
document.content_node.add_child(text_node)
else:
data = fh.read()
text_node = document.create_node(
node_type='text', content=self.decode_text(data))
document.content_node = text_node
document.add_mixin('text')
return document
def test_get_source():
document = Document.from_url('https://www.google.com')
with get_source(document) as fh:
data = fh.read()
print(data)