junte/Model
1
0
Fork 0
mirror of https://github.com/Hestia-Homes/Model.git synced 2026-06-08 11:17:27 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

add improvement detials

Browse source
This commit is contained in:
Michael Duong 2024-05-17 06:19:25 +01:00
parent ce2a4665de
commit 30e9de04bf
1 changed files with 7 additions and 9 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

16
etl/epc_recommendations/find_my_epc_pipeline.py
View file

@ -20,7 +20,7 @@ def retrieve_find_my_epc_data(uprn: int, postcode: str, address: str):
postcode_search = SEARCH_POSTCODE_URL.format(postcode_input=postcode_input)
postcode_response = requests.get(postcode_search, headers=headers)
postcode_res = BeautifulSoup(postcode_response.text)
postcode_res = BeautifulSoup(postcode_response.text, features="html.parser")
address_links_full = postcode_res.findAll('a', {'class': 'govuk-link', 'rel': 'nofollow'})
address_links = {element.text.lstrip().rstrip(): BASE_ENERGY_URL + element['href'] for element in address_links_full}
@ -31,19 +31,19 @@ def retrieve_find_my_epc_data(uprn: int, postcode: str, address: str):
epc_certificate = chosen_epc.split('/')[-1]
address_response = requests.get(chosen_epc, headers=headers)
address_res = BeautifulSoup(address_response.text)
address_res = BeautifulSoup(address_response.text, features="html.parser")
print("## Energy rating - current and potential")
# print("## Energy rating - current and potential")
ratings = address_res.find('desc', {'id': 'svg-desc'}).text
print('### Current EPC rating')
# print('### Current EPC rating')
current_rating = ratings.split(".")[0]
print("##### " + current_rating)
# print("##### " + current_rating)
print('### Potential EPC rating')
# print('### Potential EPC rating')
potential_rating = ratings.split(".")[1]
print("##### " + potential_rating)
# print("##### " + potential_rating)
new_property_df = pd.DataFrame(
{
@ -91,10 +91,8 @@ def retrieve_find_my_epc_data(uprn: int, postcode: str, address: str):
for i, element in enumerate(zip(changes, changes_impact)):
improvement_header = element[0].text
# print("#### " + improvement_header)
improvement_text = element[1].text
# print(improvement_text)
col_name = improvement_header.split(":")[1].strip()
cost = element[1].find('dd', {"class": "govuk-summary-list__value"}).text.lstrip().rstrip()