Created
August 1, 2017 08:01
-
-
Save bound2/813ee50072188c347c21c9e783ce839a to your computer and use it in GitHub Desktop.
extract mobile country codes from webpage
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
from bs4 import BeautifulSoup | |
import urllib2 | |
from collections import defaultdict | |
if __name__ == '__main__': | |
page = urllib2.urlopen("http://mcc-mnc.com") | |
html = page.read() | |
soup = BeautifulSoup(html, "html.parser") | |
table_body = soup.find("tbody") | |
rows = table_body.findAll("tr") | |
data = defaultdict(frozenset) | |
for row in rows: | |
columns = row.findAll("td") | |
mcc = columns[0].string.strip() | |
country_iso_code = columns[2].string.strip() | |
items = set(data[country_iso_code]) | |
items.add(mcc) | |
data[country_iso_code] = frozenset(items) | |
for key, values in data.iteritems(): | |
s = "" | |
for value in values: | |
s += value + ", " | |
s = s[:-2] | |
print('.put("%s", ImmutableList.of(%s))' % (key.upper(), s)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment