Skip to content

Instantly share code, notes, and snippets.

@podhmo
Created August 26, 2015 10:31
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save podhmo/b9c6992898f556f3e336 to your computer and use it in GitHub Desktop.
Save podhmo/b9c6992898f556f3e336 to your computer and use it in GitHub Desktop.
# -*- coding:utf-8 -*-
import json
from article.parsers import EntertainmentStationArticleParser
import os.path
def dump(filename):
with open(filename) as fp:
parser = EntertainmentStationArticleParser(fp.read())
result = parser.parse()
print(json.dumps(result, ensure_ascii=False, indent=2).encode("utf-8"))
if __name__ == "__main__":
import sys
try:
dump(sys.argv[1])
except IndexError:
filename = os.path.join(os.path.abspath(os.path.dirname(__file__)), "success/2827.html")
filename = os.path.join(os.path.abspath(os.path.dirname(__file__)), "success/3648.html")
filename = os.path.join(os.path.abspath(os.path.dirname(__file__)), "success/3244.html")
dump(filename)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment