python html parser doesnot return results? - python-2.7

Question

I am new to python, I have a folder of downloaded html files, from which I need to extract the text data and output it in the same folder as text file, below code works fine with individual files, however when i am trying to pass multiple files it doesn't work. Kindly suggest a solution, i will be extremely thankful. Its not even giving me any error, so I could work on it and figure out some solution.
from HTMLParser import HTMLParser
from re import sub
from sys import stderr
from traceback import print_exc
import glob
import os
class _DeHTMLParser(HTMLParser):
def __init__(self):
HTMLParser.__init__(self)
self.__text = []
def handle_data(self, data):
text = data.strip()
if len(text) > 0:
text = sub('[ \t\r\n]+', ' ', text)
self.__text.append(text + ' ')
def handle_starttag(self, tag, attrs):
if tag == 'p':
self.__text.append('\n\n')
elif tag == 'br':
self.__text.append('\n')
def handle_startendtag(self, tag, attrs):
if tag == 'br':
self.__text.append('\n\n')
def text(self):
return ''.join(self.__text).strip()
def dehtml(text):
try:
parser = _DeHTMLParser()
parser.feed(text)
parser.close()
return parser.text()
except:
print_exc(file=stderr)
return text
def main():
dir_path = r"/home/maitreyee/Downloads/SchoolCollege.com/multiple_states/"
results_dir = r"/home/maitreyee/Downloads/SchoolCollege.com/"
for file_name in glob.glob(os.path.join(dir_path, "*.html")):
text = open(file_name, "r")
results_file = os.path.splitext(file_name)[0] + '.txt'
with open(results_file, 'w') as outfile:
i = dehtml(text)
print(i)
outfile.write(i + '\n')
if __name__ == '__main__':
main()

Answer 1

I struggled a lot and then tried something simpler, for the above code we could just modify the main() function by the following code and then this would return .txt files for all the html files, we need to pass just the folder location.
def main():
dir_path = r"/home/maitreyee/Downloads/SchoolCollege.com/rajasthan_data/"
results_dir = r"/home/maitreyee/Downloads/SchoolCollege.com/rajasthan_data/"
for file_name in glob.glob(os.path.join(dir_path, "*.html")):
f = open(file_name)
text = f.read()
results_file = os.path.splitext(file_name)[0] + '.txt'
with open(results_file, "w") as fp:
fp.write(dehtml(text))
fp.close()
Where the directory paths are given then put in the directory path to your html file's folder. It was really helpful for me because I had to convert hundreds of html files, and I needed all the text from them, this gave me results in seconds.