#!/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('https://untappd.com/v/jbm-brew-lab-pub/4222393')
if not html:
exit(-1)
beerlib.process_untappd(html, 'JBM Brew Lab Pub', 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)
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import re, sys
from xml.etree import ElementTree as ET
import common as beerlib
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
div = checkin.find('.//div[@data-rating]')
if div is not None:
return div.get('data-rating')
return None
if len(sys.argv) != 3:
print("uuparser requires two arguments: untappd_username irc_nick")
exit(-1)
cwd = os.path.dirname(os.path.realpath(__file__))
CACHE_FILE = os.path.join(cwd, '../cache/untappd.json')
USER = sys.argv[1]
IRC_NICK = sys.argv[2]
html = beerlib.download_html('https://untappd.com/user/' + USER)
if not html:
exit(-2)
reg = re.compile('(<div id="main-stream.*?)<script', re.MULTILINE | re.DOTALL)
body = reg.search(html)
if not body:
exit(-3)
body = body.group(1)
content = re.sub('<script.*?</script>',
'',
body,
flags=re.MULTILINE | re.DOTALL)
content = re.sub('<img.*?>', '', content, flags=re.MULTILINE | re.DOTALL)
content = content.replace('&', '&')
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import sys
import common as beerlib
html = beerlib.download_html('https://untappd.com/v/fa-bar-oranzova/1728532')
if not html:
exit(-1)
beerlib.process_untappd(html, 'F.A. Bar Oranžová', sys.argv)
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import sys, re, json
from xml.etree import ElementTree as ET
import common as beerlib
curl_ua = 'curl/7.54.1'
# first we need the post ID
html = beerlib.download_html('https://m.facebook.com/page_content_list_view/more/?page_id=1871132519814729&start_cursor=10000&num_to_fetch=10&surface_type=timeline', curl_ua)
if not html:
exit(-1)
reg = re.compile('(<p>.*?</p>)')
# find post ids
ids = re.findall('top_level_post_id":"([0-9]+)', html)
# Look at all articles until some beers are found
for content_id in ids:
post_url = "https://m.facebook.com/story.php?story_fbid=%s&id=%s" % (content_id, '1871132519814729')
# print(post_url)
# Okay, let's get the post
post_html = beerlib.download_html(post_url, curl_ua)
if not post_html:
continue
paragraphs = reg.findall(post_html)
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import sys, re, json
from xml.etree import ElementTree as ET
import common as beerlib
# first we need the post ID
html = beerlib.download_html('https://m.facebook.com/Craftbeerbottleshopbar/')
if not html:
exit(-1)
# first we need the post ID
reg = re.compile('(<body.*</body>)', re.MULTILINE | re.DOTALL)
body = reg.search(html).group(0)
page = ET.XML(body)
#articles = page.findall(".//div[@role='article']")
articles = page.findall(".//article")
#print(body)
# Look at all articles until some beers are found
for article in articles:
data_element = article.get('data-ft')
if not data_element:
continue
data = json.loads(data_element)
post_url = "https://m.facebook.com/story.php?story_fbid=%s&id=%s" % (
data['top_level_post_id'], data['content_owner_id_new'])
# print(post_url)