Ideone.com

fork download

import re
html = """1.45;"  >1234 St1 St</p> <p class=3D"highlight-address" styl=\ne=3D"margin: 0; font-family: 'Montserrat', sans-serif; text-decoration: non=\ne; color: #323232; font-weight: 500; font-size: 13px; line-height: 1.45;"  =\n>City, ST 12345</p><p class=3D"highlight-specs" style=3D"margin: 0; fo=\nnt-family: 'Montserrat', sans-serif; text-decoration: none; color: #323232;=\n font-weight: 500; font-size: 13px; line-height: 1.45;"><span style=3D"disp=\nlay: inline-block;">4 bd</span><span style=3D"display: inline-block;">&nbsp=\n;=E2=80=A2&nbsp;</span><span style=3D"display: inline-block;">2 ba</span><s=\npan style=3D"display: inline-block;">&nbsp;=E2=80=A2&nbsp;</span><span styl=\ne=3D"display: inline-block;">1,596 sqft</span></p><p class=3D"highlight-spe=\ncs" style=3D"margin: 0; font-family: 'Montserrat', sans-serif; textdecorati=\n\n1.45;"  >5678 St2 Rd</p> <p class=3D"highlight-address" sty=\nle=3D"margin: 0; font-family: 'Montserrat', sans-serif; text-decoration: no=\nne; color: #323232; font-weight: 500; font-size: 13px; line-height: 1.45;" =\n >City2, ST 6789</p><p class=3D"highlight-specs" style=3D"margin: 0=\n; font-family: 'Montserrat', sans-serif; text-decoration: none; color: #323=\n232; font-weight: 500; font-size: 13px; line-height: 1.45;"><span style=3D"=\ndisplay: inline-block;">4 bd</span><span style=3D"display: inline-block;">&=\nnbsp;=E2=80=A2&nbsp;</span><span style=3D"display: inline-block;">4 ba</spa=\nn></p><p class=3D"highlight-specs" style=3D"margin: 0; font-family: 'Montse=\nrrat', sans-serif; textdecoration: none; color: #323232; font-weight: 500; =\n\n1.45;"  >91011 St3 Rd</p> <p class=3D"highlight-address" style=\n=3D"margin: 0; font-family: 'Montserrat', sans-serif; text-decoration: none=\n; color: #323232; font-weight: 500; font-size: 13px; line-height: 1.45;"  >=\nCity2, ST 10111</p><p class=3D"highlight-specs" style=3D"margi=\nn: 0; font-family: 'Montserrat', sans-serif; text-decoration: none; color: =\n#323232; font-weight: 500; font-size: 13px; line-height: 1.45;"><span style=\n=3D"display: inline-block;">4 bd</span><span style=3D"display: inline-block=\n;">&nbsp;=E2=80=A2&nbsp;</span><span style=3D"display: inline-block;">2 ba<=\n/span><span style=3D"display: inline-block;">&nbsp;=E2=80=A2&nbsp;</span><s=\npan style=3D"display: inline-block;">2,376 sqft</span></p><p class=3D"highl=\night-specs" style=3D"margin: 0; font-family: 'Montserrat', sans-serif; text="""
pattern = r"\b(\d+)\s*ba<(?:\S*(?:\s(?!ba<|sqft<)\S*)*>(\d[,.\d]*)\s*sqft\b)?"
matches = re.findall(pattern, html)
for ba,sqft in matches:
	if not sqft:
		sqft = "0"
	print(f"{ba}, {sqft}")

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

Success #stdin #stdout 0.02s 9444KB

stdin

Standard input is empty

stdout

2, 1,596
4, 0
2, 2,376

https://ideone.com/yV0Sxo

language:

Python 3 (python 3.12)

created:

visibility:

secret

Share or Embed source code

Discover > Sphere Engine API

The brand new service which powers Ideone!

Discover > IDE Widget

Widget for compiling and running the source code in a web browser!

Discover > Sphere Engine API

Discover > IDE Widget

Choose your language