> def category_iterator(source):
> source = iter(source)
> try:
> while True:
> item = source.next()
This gave me a lot of inspiration. After a couple of days of banging
my head against the wall, I finally figured out a code that could
attach headers, titles, numbers, and categories in their appropriate
combinations--basically one BIG logic puzzle.
It's not the prettiest thing in the world, but it works. If anyone
has a better way to do it, then I'll be all ears. Anyways, thank you
all for your input, it helped me think outside the box.
import re
data = ['RULES', 'Approval and Promulgation of Air Quality
Implementation Plans:', 'Illinois; Revisions to Emission Reduction
Market System, ', '11042 [E8-3800]', 'E8-3800.pdf', 'Ohio; Oxides of
Nitrogen Budget Trading Program; Correction, ', '11192 [Z8-2506]',
'Z8-2506.pdf', 'NOTICES', 'Agency Information Collection Activities;
Proposals, Submissions, and Approvals, ', '11108-11110 [E8-3934]',
'E8-3934.pdf', 'Data Availability for Lead National Ambient Air
Quality Standard Review, ', '11110-11111 [E8-3935]', 'E8-3935.pdf',
'Environmental Impacts Statements; Notice of Availability, ', '11112
[E8-3917]', 'E8-3917.pdf']
NOTICES = re.compile(r'NOTICES')
RULES = re.compile(r'RULES')
TITLE = re.compile(r'[A-Z][a-z].*')
NUM = re.compile(r'\d.*')
PDF = re.compile(r'.*\.pdf')
counted = []
sorted = []
title = []
tot = len(data)
x=0
while x < tot:
try:
item = data[x]
title = []
if NOTICES.match(item) or RULES.match(item):
module = item
header = ''
if TITLE.match(data[x+1]) and TITLE.match(data[x+2]) and
NUM.match(data[x+3]):
#Header
header = data[x+1]
counted.append(data[x+1])
sorted.append(data[x+1])
#Title
counted.append(data[x+2])
sorted.append(data[x+2])
#Number
counted.append(data[x+3])
sorted.append(data[x+3])
title.append(''.join(sorted))
print title, module
print
sorted = []
x+=1
elif TITLE.match(data[x+1]) and NUM.match(data[x+2]):
#Title
counted.append(data[x+1])
sorted.append(data[x+1])
#Number
counted.append(data[x+2])
sorted.append(data[x+2])
title.append(''.join(sorted))
print title, module
print
sorted = []
x+=1
else:
print item, "strange1"
break
x+=1
else:
if item in counted:
x+=1
elif PDF.match(item):
x+=1
elif TITLE.match(data[x]) and TITLE.match(data[x+1]) and
NUM.match(data[x+2]):
#Header
header = data[x]
counted.append(data[x])
sorted.append(data[x])
#Title
counted.append(data[x+1])
sorted.append(data[x+1])
#Number
counted.append(data[x+2])
sorted.append(data[x+2])
title.append(''.join(sorted))
sorted = []
print title, module
print
x+=1
elif TITLE.match(data[x]) and NUM.match(data[x+1]):
#Title
sorted.append(header)
counted.append(data[x])
sorted.append(data[x])
#Number
counted.append(data[x+1])
sorted.append(data[x+1])
title.append(''.join(sorted))
sorted = []
print title, module
print
x+=1
else:
print item, "strange2"
x+=1
break
except IndexError:
break
--
http://mail.python.org/mailman/listinfo/python-list
