Created
June 1, 2022 13:07
-
-
Save valdergallo/ed42886d4263d87c71cea60e18fb7573 to your computer and use it in GitHub Desktop.
Download Time Zone information from Wikipedia
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 requests | |
from lxml.html import document_fromstring | |
from django.core.exceptions import ValidationError | |
from pprint import pprint | |
def _parse_wiki_data(content): | |
table = content.xpath("/html/body/div[3]/div[3]/div[5]/div[1]/table[1]").pop() | |
tz_name = table.xpath("//tr/td[2]/a//text()") | |
iana_times_utc_std = table.xpath("//tr/td[5]/a//text()") | |
iana_times_utc_dst = table.xpath("//tr/td[6]/a//text()") | |
time_zone_abbreviation = table.xpath("//tr/td[7]/a//text()") | |
keys_list = ["tz_name", "tz_time_utc_std", "tz_time_utc_dst", "tz_abbreviation"] | |
lines = list( | |
zip(tz_name, iana_times_utc_std, iana_times_utc_dst, time_zone_abbreviation) | |
) | |
raw_data = [dict(zip(keys_list, line)) for line in lines] | |
return raw_data | |
def _load_iana_timezone_database(): | |
wiki_database_url = "https://en.wikipedia.org/wiki/List_of_tz_database_time_zones" | |
response = requests.get(wiki_database_url) | |
content = document_fromstring(response.content) | |
return _parse_wiki_data(content) | |
if __name__ == "__main__": | |
print("Download Time Zone names from Wikipedia") | |
print("Loading ...") | |
content = _load_iana_timezone_database() | |
iana_timezones = [i["tz_name"] for i in content] | |
print("-" * 80) | |
pprint(iana_timezones) | |
print("-" * 80) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment