Google python babyname.py (python 2.7)
#!/usr/bin/pythonimport sys
import re
"""Baby Names exercise
Define the extract_names() function below and change main()
to call it.
For writing regex, it's nice to include a copy of the target
text for inspiration.
Here's what the html looks like in the baby.html files:
...
<h3 align="center">Popularity in 1990</h3>
....
<tr align="right"><td>1</td><td>Michael</td><td>Jessica</td>
<tr align="right"><td>2</td><td>Christopher</td><td>Ashley</td>
<tr align="right"><td>3</td><td>Matthew</td><td>Brittany</td>
...
Suggested milestones for incremental development:
-Extract the year and print it
-Extract the names and rank numbers and just print them
-Get the names data into a dict and print it
-Build the list and print it
-Fix main() to use the extract_names list
"""
def extract_names(filename):
"""
Given a file name for baby.html, returns a list starting with the year string
followed by the name-rank strings in alphabetical order.
['2006', 'Aaliyah 91', Aaron 57', 'Abagail 895', ' ...]
"""
if re.search(r'{4}',filename):
year=re.search(r'{4}',filename).group()
else:
sys.exit(1)
f=open(filename)
cont=f.read()
f.close()
dic=[]
male_dict=[]
all_dict=re.findall('<tr align="right"><td>(+)</td><td>(+)</td><td>(+)',cont)
for name in all_dict:
male_dict.append(name+''+name)
dic.append(name+''+name)
dic.sort()
male_dict.sort()
male_dict.insert(0,'-'*30+'Male'+'-'*30)
dic.insert(0,year)
dic.insert(1,'-'*30+'Female'+'-'*30)
dic.extend(male_dict)
return dic
def main():
# This command-line parsing code is provided.
# Make a list of command line arguments, omitting the element
# which is the script itself.
args = sys.argv
if not args:
print 'usage: [--summaryfile] file '
sys.exit(1)
# Notice the summary flag and remove it from args if it is present.
summary = False
if args == '--summaryfile':
summary = True
del args
for arg in args:
names=extract_names(arg)
print '\n'.join(names)
if summary:
sf=open(names+'.txt','w')
sf.write('\n'.join(names)+'\n')
if __name__ == '__main__':
main()
页:
[1]