#!/usr/bin/python
# -*- coding: utf-8 -*-
import sample
import sys
if __name__ == "__main__":
sentences = sample.get_summaries(sys.argv[1])
outFH = open(sys.argv[2], "w")
for sentence in sentences:
outFH.write(sentence[2])
outFH.close()
'zwei-glorreiche-halunken.html'
"""
regex = re.compile(ur'^(.*\.html).*$')
return regex.match(filename).group(1)
if __name__ == "__main__":
parser = argparse.ArgumentParser(description='Extracts movie summarys'
+ ' and movie ratings')
parser.add_argument('--input', required=True,
help='input directory')
parser.add_argument('--output', required=True,
help='output file name for CSV file')
parser.add_argument('--ratings-map', required=True,
help='Map from file name to rating')
args = parser.parse_args()
sentences = sample.get_summaries(args.input)
outFH = open(args.output, "w")
writer = csv.writer(outFH)
tmp = OrderedDict()
m = load_ratings_map(args.ratings_map)
for s in sentences:
curFile = clean_filename(s[0])
if not curFile in tmp:
tmp[curFile] = []
tmp[curFile].append(s[2].replace("\n", " "))
notFound = 0
invalid = 0
for (fileName, summaryFragments) in tmp.iteritems():
if not fileName in m:
notFound += 1
continue
