html = beerlib.download_html('https://maltworm.cz/dnes-na-cepu/')
if not html:
exit(-1)
reg = re.compile('(<body.*</body>)', re.MULTILINE | re.DOTALL)
body = reg.search(html).group(0)
content = re.sub('<script.*</script>',
'',
body,
flags=re.MULTILINE | re.DOTALL)
table = ET.XML(content)
articles = table.findall(".//article")
headers = ['Pivo', 'Typ', 'EPM', 'Alk.', 'IBU', 'Pivovar', 'Město']
output = []
for article in articles:
beer = article.find(
".//p[@class='elementor-heading-title elementor-size-default']")
info = article.findall(".//span[@class='elementor-icon-list-text']")
info = iter(info)
values = [beer.text] + ["".join(i.itertext()) for i in info]
# get rid of 'IBU:' prefix
ibu_pos = headers.index('IBU')
values[ibu_pos] = values[ibu_pos].replace('IBU: ', '')
output = output + [values]
beerlib.parser_output(output, headers, 'Malt Worm', sys.argv)
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
from xml.etree import ElementTree as ET
import re, sys
import common as beerlib
html = beerlib.download_html('http://ochutnavkovapivnice.cz/prave_na_cepu/')
if not html:
exit(-1)
reg = re.compile('(<table.*</table>)', re.MULTILINE | re.DOTALL)
html = reg.search(html)
if not html:
exit(-2)
html = html.group(0)
html = html.replace('&', '&')
table = ET.XML(html)
rows = iter(table)
headers = [col[0].text for col in next(rows)]
output = []
for row in rows:
tds = iter(row)
beer = next(tds)[0][0].text
values = [beer] + [col.text for col in tds]
output = output + [values]
beerlib.parser_output(output, headers, 'Ochutnávková pivnice', sys.argv)
paragraphs = reg.findall(post_html)
# Hope that some paragraph of post contains beers
for p in paragraphs:
beers = ET.XML(p)
# Nothing? Give up
if not beers:
continue
beers = list(beers.itertext())
# Hope that the beer list format is the same
headers = ['Pivo', 'Alk.', 'Pivovar', 'Typ']
output = []
for line in beers:
# Black Label #4 8,1% (Raven, Wild Ale)
m = re.match(' *(.+?)(?: -)? +([0-9,\.]+%) +\(([^,]+), ?([^\)]+)\)?', line)
if not m:
# Zlaté Prasátko 6,5%
m = re.match(' *(.+?)(?: -)? +([0-9,\.]+%)()()', line)
if m:
output = output + [list(m.groups())]
if output:
beerlib.parser_output(output, headers, 'Craftbeer bottle shop & bar', sys.argv)
exit(0)
# nothing was found
exit(1)