This was my first(and the last one till date) Python script. It finds movies in a directory and uses the http://www.omdbapi.com/ to get and print details of the movie on the console.
''' Copyright Mad Piranha, Apr 10, 2012 Used 2to3.py to convert from python26 to python33 @author: Mad Piranha ''' import re import glob import http.client, urllib.request, urllib.parse, urllib.error import os import fnmatch apiURL="www.omdbapi.com" # Directory to find movies movieFolder="G:\MotionPics\__HIGHRES" # Ignore these directories ignore=['Sample', 'South Park', 'Tom&Jerry', 'Video clips', 'Subtitles', 'TV Serires', 'TELGU', 'TAMIL', 'MALAYALAM', 'KANNADA', 'HINDI', 'OTHERS', 'Hindi Cinema', 'BOLLYWOOD'] # File name filter regular expression FILE_NAME_MATCH_EXPR="(?P.*)\.(avi|divx|mkv|mpg|mp4|wmv|bin|ogm|vob|iso|img|bin|ts)" # Get RottenTomatoes data tomato = 'true' def moviedetails(moviename): # Create URL parameters. Check http://www.omdbapi.com for details params = urllib.parse.urlencode({'tomatoes':tomato, 't':moviename}) connection = http.client.HTTPConnection(apiURL) # Connect connection.request("GET", "/?"+params); response = connection.getresponse(); # Get/Read response and print print(response.status, response.reason) data1 = response.read() print(data1) connection.close() # Get the movie name from the file name def movienamefromfile(moviefilename): # Remove all characters after these special characters substr = re.sub("(\[|\()(.*)$", "", moviefilename, ) # Remove unnecessary words and anything after that substr = re.sub("(?i)(dvdrip|brrip|UNRATED|WEBSCR|KLAXXON|xvid|r5)(.*)$", "", substr, re.I) # Remove 4digits in a row (year of the movie ?) substr = re.sub("(\d{4})(.*)$", "", substr, ) # Replace . and _ with space substr = re.sub("(\.|_)", " ", substr, ) print(moviefilename, " -> ", substr) return substr.rstrip().lstrip() def parsemoviefolder(foldername): # For all the directories in the specified foldername for root, dirnames, filenames in os.walk(foldername, ): # Remove the directories mentioned in the ignore list. for val in ignore : if val in dirnames: dirnames.remove(val) for filename in filenames: # If the file name matches the movie file name expression moviefile = re.match(FILE_NAME_MATCH_EXPR, filename, re.I) if moviefile: # Get the movie name from the file name moviename = movienamefromfile(moviefile.group("name")) # Get and print the movie details moviedetails(moviename) print() parsemoviefolder(movieFolder)
