Created
November 13, 2018 09:06
-
-
Save SuvroBaner/03e501b28ff6aee95d85bc6a50799d52 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import pandas as pd | |
url_df = pd.read_csv('Book2.csv') | |
def fn_split_url(x): | |
list_of_tokens = x.split('/') | |
bad_words = ['https:', 'http:', 'www.juniper.net', 'en_US', ''] | |
final_tokens = [] | |
s = '' | |
for token in list_of_tokens: | |
if token not in bad_words: | |
s = s + " page_url LIKE '%/"+ ''.join(token) + "%' and " | |
#final_tokens.append(token) | |
else: | |
pass | |
s = s[0:len(s) - 7] | |
s = s + "'" | |
return s | |
url_df['url_cat'] = url_df['URL'].apply(lambda x: fn_split_url(x)) | |
url_df.to_csv('URL_new.csv') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment