HTML parsing python (output files for an installation piece)

givennames.py

#!/usr/bin/python

# get a list of androgynous names and write it to a .txt file
# requires BeautifulSoup library

# imports
from bs4 import BeautifulSoup
import urllib2
import sys
import os
import re
reload(sys)
sys.setdefaultencoding("utf-8")

# global variables
names = []
urls = [
"http://www.20000-names.com/androgynous_names_unisex_names.htm",
"http://www.20000-names.com/androgynous_names_unisex_names_02.htm",
"http://www.20000-names.com/androgynous_names_unisex_names_03.htm",
"http://www.20000-names.com/androgynous_names_unisex_names_04.htm",
"http://www.20000-names.com/androgynous_names_unisex_names_05.htm"
]
filename = "givennames.txt"
pattern = re.compile(r'^[A-Z\d]+$')

# if names.txt exists, delete it so we can write a new one
try:
    os.remove(filename)
except OSError:
    pass

# find each name in the html files
for url in urls:
    page = urllib2.urlopen(url)
    soup = BeautifulSoup(page.read())
    for name in soup.findAll('a', href=False):
        if re.match(pattern, name.get_text()):
            names.append(name.get_text().lower().capitalize())

# write the the list to a file, with each given name as a new line
with open(filename, "a") as f:
    for item in set(names):
        f.write(u"%s\n" % item)

imdb.py

#!/usr/bin/python

# get the IMDB Top 250 and write it to a .txt file
# requires BeautifulSoup library

# imports
from bs4 import BeautifulSoup
import urllib2
import sys
import os
reload(sys)
sys.setdefaultencoding("utf-8")

# global variables
movies = []
url = "http://www.imdb.com/chart/top"
filename = "movies.txt"

# load IMDB site as a temp file 
page = urllib2.urlopen(url)
soup = BeautifulSoup(page.read())

# if movies.txt exists, delete it so we can write a new one
try:
    os.remove(filename)
except OSError:
    pass

# find each movie in the html file
for entry in soup.findAll("table")[1].find_all('a'):
    movies.append(entry.get_text()) # add each movie to a list

# write the the list to a file, with each movie as a new line
with open(filename, "a") as f:
    for item in movies:
        f.write(u"%s\n" % item)

surnames.py

#!/usr/bin/python

# get a list of surnames and write it to a .txt file
# requires BeautifulSoup library

# imports
from bs4 import BeautifulSoup
import urllib2
import sys
import os
import re
reload(sys)
sys.setdefaultencoding("utf-8")

# global variables
surnames = []
url = "http://names.mongabay.com/most_common_surnames.htm"
filename = "surnames.txt"
pattern = re.compile(r'^[A-Z]+$')

# if surnames.txt exists, delete it so we can write a new one
try:
    os.remove(filename)
except OSError:
    pass

# find each name in the html files
page = urllib2.urlopen(url)
soup = BeautifulSoup(page.read())
for name in soup.findAll('td'):
    if re.match(pattern, name.get_text()):
        surnames.append(name.get_text().lower().capitalize())

# write the the list to a file, with each surname as a new line
with open(filename, "a") as f:
    for item in surnames:
        f.write(u"%s\n" % item)

universities.py

#!/usr/bin/python

# get a list of universities and write it to a .txt file
# requires BeautifulSoup library

# imports
from bs4 import BeautifulSoup
import urllib2
import sys
import os
reload(sys)
sys.setdefaultencoding("utf-8")

# global variables
universities = []
url = "http://www.utexas.edu/world/univ/alpha/"
filename = "universities.txt"

# load UT site as a temp file 
page = urllib2.urlopen(url)
soup = BeautifulSoup(page.read())

# if universities.txt exists, delete it so we can write a new one
try:
    os.remove(filename)
except OSError:
    pass

# find each university in the html file
for uni in soup.findAll('a',{'class':'institution'}):
    universities.append(uni.get_text()) # add each university to a list

# write the the list to a file, with each university as a new line
with open(filename, "a") as f:
    for item in universities:
        f.write(u"%s\n" % item)