import urllib, urllib2
import re, os, sys
from string import split, replace, find
imdb_Detail = []
imdb_Director = []
imdb_Writer = []
imdb_Genre = []
imdb_Details = urllib.urlopen("http://www.imdb.com/title/tt0076759/plotsummary")
imdb_Info = urllib.urlopen("http://www.imdb.com/title/tt0076759/")
imdb_HTML1 = imdb_Details.read()
imdb_HTML2 = imdb_Info.read()
imdb_Details.close()
imdb_Info.close()
imdb_re_Details = re.compile('
(.*)
')
imdb_re_Director = re.compile('Directed by
\n(.*)
')
imdb_re_Writer = re.compile('Writing credits\n\n
\n(.*)')
imdb_re_Genre = re.compile('')
imdb_List1 = imdb_re_Details.findall(imdb_HTML1)
imdb_List2 = imdb_re_Director.findall(imdb_HTML2)
imdb_List3 = imdb_re_Writer.findall(imdb_HTML2)
imdb_List4 = imdb_re_Genre.findall(imdb_HTML2)
imdb_Detail[0:50] = ""
imdb_Director[0:50] = ""
imdb_Writer[0:50] = ""
imdb_Genre[0:50] = ""
for a,b,c,d in zip(imdb_List1,imdb_List2,imdb_List3,imdb_List4):
Director = 'Director: %s' % (b[1])
Writer = 'Writer: %s' % (c[1])
Genre = 'Genre: %s' % (d)
imdb_Detail.append(a)
imdb_Director.append(Director)
imdb_Writer.append(Writer)
imdb_Genre.append(Genre)
""" An HTML Genre sample for recompiling on line 21: """
# Action / Adventure / Fantasy / Sci-Fi (more)
""" The script as-is prints the line below when executed: """
# ['Genre: Action/">Action / Adventure / Fantasy /