so I did this:
def get_quotes(ticker:str, start_date:datetime.date, end_date:datetime.date)->list:
'''Downloads the quotes from Yahoo finance'''
start_month = str(start_date.month-1)
start_day = str(start_date.day)
start_year = str(start_date.year)
end_month = str(end_date.month-1)
end_day = str(end_date.day)
end_year = str(end_date.year)
try:
list = []
quote = 'http://ichart.yahoo.com/table.csv?s='+ticker+'&a'+start_month+'&b='+start_day+"&c="+start_year+'&d='+end_month+'&e='+ end_day +'&f='+end_year+'&g=d'
response = urllib.request.urlopen(quote)
data = response.read()
string_data = data.decode(encoding='utf-8')
lines = string_data.splitlines()
for x in lines:
data = [y for y in x.split(',')]
list.append(data[0:5])
return list
except URLError:
print('Page not found! Please enter a valid ticker')
But the resulting list is:
[['Date', 'Open', 'High', 'Low', 'Close'], ['2011-10-10', '26.58', '26.97', '26.47',
'26.94'], ['2011-10-07', '26.34', '26.51', '26.20', '26.25'], ['2011-10-06', '25.90',
'26.40', '25.70', '26.34']]
when it should be: ['Date', 'Open', 'High', 'Low', 'Close'], ['2011-10-10', '26.58', '26.97', '26.47', '26.94'], ['2011-10-07', '26.34', '26.51', '26.20', '26.25'], ['2011-10-06', '25.90', '26.40', '25.70', '26.34']
Can i eliminate the double list somehow?
Is this what you're looking for?
rows = ['Date,Open,High,Low,Close,Volume,Adj Close', '2012-11-30,691.31,699.22,685.69,698.37,3163600,698.37', '2012-11-29,687.78,693.90,682.00,691.89,2776500,691.89','2012-11-28,668.01,684.91,663.89,683.67,3042000,683.67', '2012-11-27,660.17,675.00,658.00,670.71,2508700,670.71']
def format_rows(rows, gap):
split_rows = [row.split(',') for row in rows]
# Splits each row up, by comma
column_lengths = [max(col_len) for col_len in zip(*[map(len, row) for row in split_rows])]
# Finds the maximum size of each column
for row in split_rows:
col_lengths = zip(row, column_lengths)
print ''.join(col.ljust(col_length + gap, ' ') for (col, col_length) in col_lengths)
# Prints out the data, making sure there's a minimum of "gap" spaces
# between each column
Doing format_rows(rows, 4) will result in the following table being printed out, with a gap of 4 spaces between each column:
Date Open High Low Close Volume Adj Close
2012-11-30 691.31 699.22 685.69 698.37 3163600 698.37
2012-11-29 687.78 693.90 682.00 691.89 2776500 691.89
2012-11-28 668.01 684.91 663.89 683.67 3042000 683.67
2012-11-27 660.17 675.00 658.00 670.71 2508700 670.71
You can modify the code so it returns a string instead by doing this:
def format_rows(rows, gap):
split_rows = [row.split(',') for row in rows]
# Splits each row up, by comma
column_lengths = [max(col_len) for col_len in zip(*[map(len, row) for row in split_rows])]
# Finds the maximum size of each column
output = []
for row in split_rows:
col_lengths = zip(row, column_lengths)
output.append(''.join(col.ljust(col_length + gap, ' ') for (col, col_length) in col_lengths))
return '\n'.join(output)
Edit:
If you want to only include the first n rows, you could use the below function and call format_rows(rows, 4, 5). In essence, we're truncating each row to the first five before printing it.
def format_rows(rows, gap, limit):
split_rows = [row.split(',') for row in rows]
# Splits each row up, by comma
column_lengths = [max(col_len) for col_len in zip(*[map(len, row) for row in split_rows])]
# Finds the maximum size of each column
for row in split_rows:
col_lengths = zip(row, column_lengths)[:limit]
# Prints out only the first `limit` columns
print ''.join(col.ljust(col_length + gap, ' ') for (col, col_length) in col_lengths)
# Prints out the data, making sure there's a minimum of "gap" spaces
# between each column