def make_html_peek_rows( self, dataset, skipchars=[] ):
out = [""]
comments = []
if not dataset.peek:
dataset.set_peek()
data = dataset.peek
lines = data.splitlines()
for line in lines:
line = line.rstrip( '\r\n' )
if not line:
continue
comment = False
for skipchar in skipchars:
if line.startswith( skipchar ):
comments.append( line )
comment = True
break
if comment:
continue
elems = line.split( '\t' )
if len( elems ) != dataset.metadata.columns:
# We may have an invalid comment line or invalid data
comments.append( line )
comment = True
continue
while len( comments ) > 0: # Keep comments
try:
out.append( '<tr><td colspan="100%">' )
except:
out.append( '<tr><td>' )
out.append( '%s</td></tr>' % escape( comments.pop(0) ) )
out.append( '<tr>' )
for elem in elems: # valid data
elem = escape( elem )
out.append( '<td>%s</td>' % elem )
out.append( '</tr>' )
# Peek may consist only of comments
while len( comments ) > 0:
try:
out.append( '<tr><td colspan="100%">' )
except:
out.append( '<tr><td>' )
out.append( '%s</td></tr>' % escape( comments.pop(0) ) )
return "".join( out )
def make_html_table(self, dataset, skipchars=[]):
"""Create HTML table, used for displaying peek"""
out = ['<table cellspacing="0" cellpadding="3">']
try:
out.append('<tr><th>Species: ')
for species in dataset.metadata.species:
out.append('%s ' % species)
out.append('</th></tr>')
if not dataset.peek:
dataset.set_peek()
data = dataset.peek
lines = data.splitlines()
for line in lines:
line = line.strip()
if not line:
continue
out.append('<tr><td>%s</td></tr>' % escape(line))
out.append('</table>')
out = "".join(out)
except Exception, exc:
out = "Can't create peek %s" % exc
def make_html_table( self, dataset, skipchars=[] ):
"""Create HTML table, used for displaying peek"""
out = ['<table cellspacing="0" cellpadding="3">']
try:
out.append('<tr><th>Species: ')
for species in dataset.metadata.species:
out.append( '%s ' % species )
out.append( '</th></tr>' )
if not dataset.peek:
dataset.set_peek()
data = dataset.peek
lines = data.splitlines()
for line in lines:
line = line.strip()
if not line:
continue
out.append( '<tr><td>%s</td></tr>' % escape( line ) )
out.append( '</table>' )
out = "".join( out )
except Exception, exc:
out = "Can't create peek %s" % exc
def create_players_list(filename):
data = open(filename, 'r').read()
lines = data.splitlines()
players = []
player_info = []
# appends each line of file (which corresponds to a single player) to list of players
for info in lines:
if info == 'View More':
players.append(player_info)
player_info = []
else:
player_info.append(info)
## first pass of cleanup of list of players -specificaly on Club and Age columns,
## to align properties of players
for player in players:
for club in clubs:
if club in player[0]:
#print('team found:', club)
team = club
player[0] = player[0].replace(club,'')
player.insert(1, team)
# removes and aligns column of 'Age:' where applicable
for meta in player:
if meta == 'Age:':
continue
else:
if 'Age:' in meta:
meta_indx = meta.index('Age:')
player_indx = player.index(meta)
age = 'Age:'
player.insert((player_indx + 1), age)
player[player_indx] = player[player_indx].replace('Age:', '')
return players
def make_html_table(self, data, skipchar=None):
out = ['<table cellspacing="0" cellpadding="3">']
first = True
comments = []
try:
lines = data.splitlines()
for line in lines:
if skipchar and line.startswith(skipchar):
comments.append(line.strip())
continue
line = line.strip()
if not line:
continue
elems = line.split("\t")
if first: #generate header
first = False
out.append('<tr>')
for index, elem in enumerate(elems):
out.append("<th>%s</th>" % (index+1))
out.append('</tr>')
while len(comments)>0:
out.append('<tr><td colspan="100%">')
out.append(escape(comments.pop(0)))
out.append('</td></tr>')
out.append('<tr>') # body
for elem in elems:
elem = escape(elem)
out.append("<td>%s</td>" % elem)
out.append('</tr>')
out.append('</table>')
out = "".join(out)
except Exception, exc:
out = "Can't create peek %s" % exc
def make_html_table(self, data, skipchar=None):
out = ['<table cellspacing="0" cellpadding="3">']
first = True
comments = []
try:
lines = data.splitlines()
for line in lines:
if skipchar and line.startswith(skipchar):
comments.append(line.strip())
continue
line = line.strip()
if not line:
continue
elems = line.split("\t")
if first: #generate header
first = False
out.append('<tr>')
for index, elem in enumerate(elems):
out.append("<th>%s</th>" % (index + 1))
out.append('</tr>')
while len(comments) > 0:
out.append('<tr><td colspan="100%">')
out.append(escape(comments.pop(0)))
out.append('</td></tr>')
out.append('<tr>') # body
for elem in elems:
elem = escape(elem)
out.append("<td>%s</td>" % elem)
out.append('</tr>')
out.append('</table>')
out = "".join(out)
except Exception, exc:
out = "Can't create peek %s" % exc
file = open(filename,"w")
file.write(blob)
file.close()
####
#### PART 3
#### open txt file with data, clean and format row to [category, year, team, region, state]
####
filename = 'us_youth_national_champions_raw.txt'
data = open(filename, 'r').read()
lines = data.splitlines()
all_winners = []
for line in lines:
try:
line = line.strip()
if (line[0] == 'G' or line[0] == 'B'):
categories = line.split('-')
category = categories[0]
else:
year = int(line[0:4])
team, region = line.split(',')
team = team.replace(str(year), '').strip()