def main(source):
list = {}
datafile = open(source, "r")
sentences = regexhtml.article_clean(datafile.read())
if "." in sentences: sentences = re.sub(r".", r" ", sentences)
for word in sentences.split():
if not word in list:
list.update({word : 1})
else:
list.update({word : list[word] + 1})
list = OrderedDict(sorted(list.items(), key=lambda x:x[1]))
file = open(source + "-analytics.dat", "w")
for word in reversed(list):
file.write(word + ": " + str(list[word]) + "\n")
file.close()
def main():
list = {}
article_dir = "./article/"
for file in os.listdir(article_dir):
if file.endswith(".txt"):
title_file = open(article_dir + file, "r").read()
dat_file = open(article_dir + file + "-cloud.txt", "w")
file_title = re.findall("<title>(.*?)</title>", title_file)
print file_title[0]
dat_file.write(file_title[0] + "\n\n")
cache = regexhtml.article_clean(title_file)
for title in file_title[0].replace("\"", "").replace(":", "").split():
# print title
dat_file.write("\n" + title + "\n")
for sentence in cache.split("."):
if title in sentence:
# print sentence + ".\n"
dat_file.write(sentence + ".\n")
