senaduka/old-nlp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Lowercase and fix bug with regular expression

Browse Source
This commit is contained in:
Senad Uka
2019-10-20 13:53:38 +02:00
parent 233066caf4
commit d9c7848abb
1 changed files with 5 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
hamo.py
View File

@@ -6,6 +6,9 @@ import re
# download url # download url
url = 'https://www.olx.ba/artikal/33001845/stan-u-centru-ilidza-sa-balkona/' url = 'https://www.olx.ba/artikal/33001845/stan-u-centru-ilidza-sa-balkona/'
url = 'https://prostor.ba/prodaja/stan/dobrinja/9709'
res = requests.get(url) res = requests.get(url)
html_page = res.content html_page = res.content
@@ -39,8 +42,8 @@ print("======================================")
# translate to english # translate to english
translator = Translator() translator = Translator()
en_output = translator.translate(internationalized).text en_output = translator.translate(internationalized).text
sentences = sent_tokenize(en_output) sentences = sent_tokenize(en_output.lower())
no_whitespace = list(map(lambda s: re.sub(r'[^A-Za-z0-9\.,-_]+', ' ', s),sentences)) no_whitespace = list(map(lambda s: re.sub(r'[^A-Za-z0-9\.,\-_]+', ' ', s),sentences))
only_with_numbers = [sentence for sentence in no_whitespace if bool(re.search(r'\d', sentence))] only_with_numbers = [sentence for sentence in no_whitespace if bool(re.search(r'\d', sentence))]