Python Forum

Hi All,

I can't get the response from the api to be recognised if I try and define tree. Any suggestions would be much appreciated.

import requests
import xml.etree.ElementTree as ET

def getXML():
    url="http://energywatch.natgrid.co.uk/EDP-PublicUI/PublicPI/InstantaneousFlowWebService.asmx"
    
    headers = {'content-type': 'application/soap+xml; charset=utf-8'}
    body ="""<soap12:Envelope xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:soap12="http://www.w3.org/2003/05/soap-envelope">
                <soap12:Body>
                <GetInstantaneousFlowData xmlns="http://www.NationalGrid.com/EDP/UI/" />
                </soap12:Body>
                </soap12:Envelope>"""

    response = requests.post(url,data=body,headers=headers)
    return response.content
    
    tree = ET.XML(response) 
    root = tree.getroot()
    root.tag
    print(root.tag)

    for EDPObjectName in root.iter('EDPObjectName'):
        print(EDPObjectName.text)

I can't work out what I'm doing wrong, because If I download the XML file then run the following code, it works:

import xml.etree.ElementTree as ET
tree = ET.parse("C:\\Users\\Hey Arnold\\Documents\\Python Scripts\\new1.xml")

root = tree.getroot()
root.tag
print(root.tag)

for EDPObjectName in root.iter('EDPObjectName'):
    print(EDPObjectName.text)

All of code is inside the function then after return nothing happens with lines 17-23.
Here a fix an i use BS with lxml as parser,i never use parser in standard library.

import requests
from bs4 import BeautifulSoup

def get_xml():
    url="http://energywatch.natgrid.co.uk/EDP-PublicUI/PublicPI/InstantaneousFlowWebService.asmx"
    headers = {'content-type': 'application/soap+xml; charset=utf-8'}
    body ="""<soap12:Envelope xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:soap12="http://www.w3.org/2003/05/soap-envelope">
                <soap12:Body>
                <GetInstantaneousFlowData xmlns="http://www.NationalGrid.com/EDP/UI/" />
                </soap12:Body>
                </soap12:Envelope>"""

    response = requests.post(url,data=body,headers=headers)
    return response.content

response = get_xml()
soup = BeautifulSoup(response, 'lxml')
for item in soup.find_all('EDPObjectName'.lower()):
    print(item.text)

Output:
ALDBROUGH
AVONMOUTH
BACTON BBL
BACTON IC
BACTON PERENCO
BACTON SEAL
BACTON SHELL
BARROW SOUTH
DYNEVOR ARMS
EASINGTON DIMLINGTON
EASINGTON LANGELED
EASINGTON ROUGH ST
.......

Thanks very much, but is it possible with element tree. It would be great to know what i was doing wrong.

OK, I think I'm close but no cigar.....yet! Does it look like I have the correct namespace root xpath etc?

import requests
from lxml import etree
    
fromDate = "2018-07-29"

def getXML():
    url="http://energywatch.natgrid.co.uk/EDP-PublicUI/PublicPI/InstantaneousFlowWebService.asmx"
    headers = {'content-type': 'application/soap+xml; charset=utf-8'}
    body ="""<soap12:Envelope xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:soap12="http://www.w3.org/2003/05/soap-envelope">
  <soap12:Body>
    <GetInstantaneousFlowData xmlns="http://www.NationalGrid.com/EDP/UI/" />
  </soap12:Body>
</soap12:Envelope>"""

    response = requests.post(url,data=body,headers=headers)
    return response.content

import pandas as pd
df1 = pd.DataFrame(columns=("applicable_at","name","value","created_date"))   
for pd_date in pd.date_range(fromDate, periods=1):
    day = pd_date.strftime('%Y-%m-%d')
     
    root = etree.fromstring(getXML())
    #map prefix 'd' to the default namespace URI
    ns = {'d': 'http://www.nationalgrid.com/EDP/BusinessEntities/Public'}
     
    publication_objects = root.xpath('//d:EDPObjectCollection', namespaces=ns)
     
    for obj in publication_objects:
        name = obj.find('d:EDPObjectName', ns).text
     
        for data in obj.findall('d:EnergyDataList/d:EDPEnergyDataBE', ns):
            applicable_at = pd.to_datetime(data.find('d:ApplicableAt', ns).text)    
            value = float(data.find('d:FlowRate', ns).text)
            created_date = pd.to_datetime(data.find('d:ScheduleTime', ns).text)

        
         
            df1.loc[len(df1) +1] = [applicable_at,name, value,created_date]

hey_arnold, Have you managed to find a solution?