All pastes #57028 Raw Edit

Something

public python v1 · immutable
#57028 ·published 2006-05-19 05:56 UTC
rendered paste body
import urllib, urllib2import re, os, sysfrom string import split, replace, findimdb_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('<p class="plotpar">(.*)</p>')imdb_re_Director = re.compile('Directed by</b><br>\n<a href="/name/nm(.*)/">(.*)</a><br>')imdb_re_Writer = re.compile('Writing credits</b>\n\n<br>\n<a href="/name/nm(.*)/">(.*)</a>')imdb_re_Genre = re.compile('<a href="/Sections/Genres/(.*)/">')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: """#   <a href="/Sections/Genres/Action/">Action</a> / <a href="/Sections/Genres/Adventure/">Adventure</a> / <a href="/Sections/Genres/Fantasy/">Fantasy</a> / <a href="/Sections/Genres/Sci-Fi/">Sci-Fi</a> <a href="/rg/title-tease/keywords/title/tt0076759/keywords">(more)</a>""" The script as-is prints the line below when executed: """#   ['Genre:          Action/">Action</a> / <a href="/Sections/Genres/Adventure/">Adventure</a> / <a href="/Sections/Genres/Fantasy/">Fantasy</a> / <a href="/Sections/Genres/Sci-Fi']""" I need imdb_Genre to recompile all of the  "Sections/Genres/(.*)/"  and have those entries print a line like the example: """#   Action / Adventure / Fantasy / Sci-Fiprint imdb_Detailprint imdb_Directorprint imdb_Writerprint imdb_Genre