Automated pre-season checks for result pages

1 files changed, 130 insertions, 0 deletions

diff --git a/preseason/checks.py b/preseason/checks.py
new file mode 100644
index 0000000..c9d1acb
--- /dev/null
+++ b/preseason/checks.py
@@ -0,0 +1,130 @@
+import difflib, json, sys
+
+import requests
+from bs4 import BeautifulSoup as bs
+
+
+with open(sys.argv[1]) as config_file:
+    config = json.load(config_file)
+
+
+def get_file(urlpart, prefixed=True):
+    url = config['source']['path'].strip('/') + '/'
+    if prefixed:
+        url += config['source']['prefix']
+    url += urlpart
+    r = requests.get(url)
+    r.raise_for_status()
+    r.encoding = 'utf8'
+    return r.text
+
+
+def check_round_date(round_no, round_date):
+    round_html = get_file('runda%d.html' % round_no)
+    round_content = bs(round_html, 'lxml')
+    date_cell = round_content.select('td.bdnt12')[0].text.split('\xa0\xa0')
+    if date_cell[1] != round_date:
+        print('Round date for round %d differs: expected "%s" got "%s"' % (
+            round_no, round_date, date_cell[1]))
+
+
+def check_dates():
+    for i in range(0, len(config['round_dates'])):
+        check_round_date(i+1, config['round_dates'][i])
+
+
+def check_logoh():
+    if 'custom_file' in config['logoh']:
+        html_logoh = get_file(config['logoh']['custom_file'], prefixed=False)
+    else:
+        html_logoh = get_file('logo.html')
+    with open('config/' + config['logoh']['template']) as logoh_file:
+        template_logoh = logoh_file.read()
+    for var, val in config['logoh'].get('variables', {}).items():
+        template_logoh = template_logoh.replace('%' + var + '%', val)
+    d = difflib.Differ()
+    for diff in d.compare(
+            [l.strip() for l in template_logoh.splitlines()],
+            [l.strip() for l in html_logoh.splitlines()]
+    ):
+        if not diff.startswith(' '):
+            print(diff)
+
+
+def check_vp_table():
+    with open('config/' + config['vp_table']) as vp_file:
+        vp_table = [l.strip().split(' - ') for l in vp_file.readlines() if l.strip()]
+    vp_html = bs(get_file('vptable.html'), 'lxml')
+    vp_row = 0
+    for row in vp_html.select('tr'):
+        imp_cells = row.select('td.bdc1')
+        vp_cells = row.select('td.bdc')
+        if len(imp_cells) == len(vp_cells) and len(imp_cells) > 0:
+            if imp_cells[0].parent == row:
+                for i in range(0, len(imp_cells)):
+                    if (imp_cells[i].text.strip().replace('\xa0', ' ') != vp_table[vp_row][0].strip()) or \
+                       (vp_cells[i].text.strip().replace('\xa0', ' ')  != vp_table[vp_row][1].strip()):
+                        print('VP table differs: expected (%s - %s), got (%s - %s)' % (
+                            *vp_table[vp_row],
+                            imp_cells[i].text.strip(), vp_cells[i].text.strip()))
+                    vp_row += 1
+
+
+def check_page_language():
+    leaderboard = bs(get_file('leaderb.html'), 'lxml')
+    place_str = leaderboard.select('tr > td.bdcc12')[0].text
+    if place_str != config['language']:
+        print('Page language does not match: expected "%s", got "%s"' % (
+            config['language'],
+            place_str))
+
+
+def get_cezar_team(team_id):
+    r = requests.get('https://msc.com.pl/cezar/?p=213&action=1&id=%d' % (team_id))
+    r.raise_for_status()
+    r.encoding = 'utf8'
+    cezar_html = bs(r.text, 'lxml')
+    title = cezar_html.select('p.msc_pagetitle')[0].contents[0].strip().replace('Drużyna ', '')
+    return title
+
+
+def get_cezar_names():
+    with open(config['team_names']) as team_file:
+        teams_lines = team_file.readlines()
+    teams = {}
+    for t in teams_lines:
+        t = t.strip()
+        if t:
+            t = t.split()
+            teams[int(t[0])] = int(t[1])
+    return { team_no: get_cezar_team(team_id) for team_no, team_id in teams.items() }
+
+
+def get_html_names():
+    leaderboard = bs(get_file('leaderb.html'), 'lxml')
+    cells = leaderboard.select('td.bd')
+    teams = {}
+    for cell in cells:
+        links = cell.select('a[onmouseover][href]')
+        for link in links:
+            if link['href'].startswith(config['source']['prefix'] + 'T'):
+                team_id = int(link['href'].replace(config['source']['prefix'] + 'T', '').split('.')[0])
+                team_name = link.text.strip()
+                teams[team_id] = team_name
+    return teams
+
+
+def check_team_names():
+    cezar_names = get_cezar_names()
+    html_names = get_html_names()
+    for team_id, team_name in cezar_names.items():
+        if html_names[team_id] != cezar_names[team_id]:
+            print('Team name differs: expected "%s", got "%s"' % (cezar_names[team_id], html_names[team_id]))
+
+
+print('Checking %s' % (sys.argv[1]))
+check_dates()
+check_logoh()
+check_vp_table()
+check_page_language()
+check_team_names()