I extracted a table from a PDF so the data is quite messy and the data that
should be in 1 row is in 3 colums, like so:
year color location
1 1997 blue, MD
2 green,
3 and yellow
SO far my code is below, but I know I am missing data I am just not sure what
to put in it:
# Simply read and split an example Table 4
import sys
# Assigning count number and getting rid of right space
def main():
count = 0
pieces = []
for line in open(infile, 'U'):
if count < 130:
data = line.replace('"', '').rstrip().split("\t")
data = clean_data(data)
if data[1] == "year" and data[1] != "":
write_pieces(pieces)
pieces = data
str.join(pieces)
else:
for i in range(len(data)):
pieces[i] = pieces[i] + data[i]
str.join(pieces)
# Executing command to remove right space
def clean_data(s):
return [x.rstrip() for x in s]
def write_pieces(pieces):
print
if __name__ == '__main__':
infile = "file.txt"
main()
--
https://mail.python.org/mailman/listinfo/python-list
