Created
February 4, 2019 18:15
Star
You must be signed in to star a gist
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
defmodule Scraper.Parser.Date do | |
@dates [ | |
"ma 19:41", | |
"2019-01-14", | |
"2019. 01. 11.", | |
"2019.01.14 18:21", | |
"2019.01.14. 18:51", | |
"január 14. | 14:00", | |
"2019. 01. 14. 20:00", | |
"2019. jan. 13., 13:12", | |
"2019. január 14. 19:07", | |
"2019. január. 14. 20:00", | |
"/ 2018.08.03., péntek 13:00 /", | |
"2019. január 14. hétfő 12:20", | |
"2019. január 14. hétfő, 16:47", | |
"2019. január 14., hétfő 17:45", | |
"újságíró . 2019. 01. 14. 20:17", | |
"2019. január 14. 20:15 - szerző: Mészáros Márton", | |
"2018. április 10., kedd 10:43, frissítve: kedd 11:55", | |
] | |
@year_pattern "?<year>([\\d]{4})" | |
@january "jan|január" | |
@february "feb|február" | |
@march "már|március" | |
@april "ápr|április" | |
@may "már|március" | |
@june "jún|június" | |
@july "júl|július" | |
@august "aug|augusztus" | |
@september "szep|szeptember" | |
@october "okt|október" | |
@november "nov|november" | |
@december "dec|december" | |
@month_pattern "?<month>([0-1][0-2]|#{@january}|#{@february}|#{@march}|#{@april}|#{@may}|#{@june}|#{@july}|#{@august}|#{@september}|#{@october}|#{@november}|#{@december})" | |
@day_pattern "?<day>([0-3][0-9])" | |
@time_pattern "?<time>([\\d]{1,2}):[\\d]{2}" | |
@today_pattern "ma" | |
def get_dates(), do: @dates | |
def get_patterns(), do: [@year_pattern, @month_pattern, @day_pattern, @time_pattern] | |
def parse_date(datetime, patterns \\ [@time_pattern, @year_pattern, @month_pattern, @day_pattern]) do | |
patterns | |
|> compose_patterns() | |
|> IO.inspect | |
|> Regex.named_captures(datetime) | |
end | |
def compose_patterns(patterns) do | |
patterns | |
|> Enum.map(fn pattern -> "(#{pattern})" end) | |
|> Enum.join("|") | |
|> Regex.compile! | |
end | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment