Junmo Kang rapier83
rapier83
/ pressian_crawler.py
Last active
August 29, 2015 14:14
— forked from hyounggyu/pressian_crawler.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import sys | |
| import json | |
| import urllib.request | |
| from bs4 import BeautifulSoup | |
| from jinja2 import Template | |
| # TODO: Remove '\xa0' character | |
| def clean_text(text): |