How can I extract address from raw text using NLTK in python?

Question

I have this text

'''Hi, Mr. Sam D. Richards lives here, 44 West 22nd Street, New York, NY 12345. Can you contact him now? If you need any help, call me on 12345678'''

. How the address part can be extracted from the above text using NLTK? I have tried Stanford NER Tagger, which gives me only New York as Location. How to solve this?

Most people would give regular [expressions](https://docs.python.org/2/howto/regex.html) a try. Besides that, a short search on SO will give you plenty of [inspiration](http://stackoverflow.com/questions/14087116/extract-address-from-string). — patrick, Jun 10 '16 at 21:22
here's a pretty solid [python, nltk write up](https://medium.com/@acrosson/extracting-names-emails-and-phone-numbers-5d576354baa). i'll type it into an answer here with the summary after i implement it myself. — Rohmer, Jun 13 '17 at 21:30

Alex · Accepted Answer · 2016-06-13T08:27:14.863

14

Definitely regular expressions :)

Something like

import re

txt = ...
regexp = "[0-9]{1,3} .+, .+, [A-Z]{2} [0-9]{5}"
address = re.findall(regexp, txt)

# address = ['44 West 22nd Street, New York, NY 12345']

Explanation:

[0-9]{1,3}: 1 to 3 digits, the address number

(space): a space between the number and the street name

.+: street name, any character for any number of occurrences

,: a comma and a space before the city

.+: city, any character for any number of occurrences

,: a comma and a space before the state

[A-Z]{2}: exactly 2 uppercase chars from A to Z

[0-9]{5}: 5 digits

re.findall(expr, string) will return an array with all the occurrences found.

edited Jun 13 '16 at 08:27

answered Jun 13 '16 at 08:21

Alex

6,171
6
17
35

1

Deep clear explanation. Where I can learn this regular expressions with details – Ragu Natarajan Dec 24 '18 at 11:02
Is there any way to detect the address from text like this using Node.js, not python @Alex – Lakshmi Oct 07 '21 at 10:53
@Lakshmi it's the very same approach, just copy over the RegExp – Alex Oct 09 '21 at 17:10
i always find regex101.com very helpful – Joey Baruch Jan 06 '22 at 20:36

score 6 · Answer 2 · answered Oct 11 '18 at 05:47

6

Pyap works best not just for this particular example but also for other addresses contained in texts.

text = ...
addresses = pyap.parse(text, country='US')

answered Oct 11 '18 at 05:47

Bhio

61
1
3

jujule · Answer 3 · 2020-05-28T15:40:02.860

3

Checkout libpostal, a library dedicated to address extraction

It cannot extract address from raw text but may help in related tasks

edited May 28 '20 at 15:40

answered Dec 14 '18 at 00:51

jujule

10,656
3
40
60

Libpostal is used for normalising strings that have already been identified as addresses, which is a completely different task. – Boris Jul 16 '20 at 10:05

How can I extract address from raw text using NLTK in python?

3 Answers3

Linked