Naudotojas:Powermelon/smėlio dėžė
Programa, analizuojanti ELIP {{dem}} lenteles:
from urllib.request import urlopen
import fileinput
import re
def decode_entities(match):
return chr( int( match.group(1) ) )
response = urlopen( 'http://lietuvai.lt/w/index.php?title=U%C5%BEulaukis_(Ukmerg%C4%97)&action=formedit' )
text = response.read().decode('utf-8')
text = re.sub( r'\&#(\d+);', decode_entities, text )
match = re.search( r'\{\{(\s*dem\s*\|[^}]+)\}\}', text )
dem = match.group(1)
table = dict()
year = None
for field in dem.split( '|' ):
field = re.sub( r'\s', '', field )
if field == 'dem' or re.search( r'=', field ) is not None:
continue
if year is None:
year = field
else:
table[year] = field
year = None
print(table)