Created
April 1, 2018 08:44
-
-
Save Gedevan-Aleksizde/b914ff6eb9a51ab71d7b612b02f74f7d to your computer and use it in GitHub Desktop.
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
#!/usr/bin/env python3 | |
# -*- coding: utf-8 -*- | |
""" | |
Created on Sat Mar 31 22:57:58 2018 | |
https://www.quora.com/How-can-I-extract-only-text-data-from-HTML-pages | |
https://qiita.com/matsu0228/items/edf7dbba9b0b0246ef8f | |
@author: ks | |
""" | |
import sys, re, datetime | |
import urllib | |
from bs4 import BeautifulSoup | |
import MeCab as mc | |
fname = '_'.join(['out', | |
datetime.datetime.today().strftime('%Y-%m-%dT%H%M%S'), | |
]) + '.txt' | |
tagger = mc.Tagger('-Owakati') # 形態素は情報はいらない | |
# url = 'http://ill-identified.hatenablog.com/entry/2017/04/30/004258' | |
url = sys.argv[1] | |
print('URL: ' + url) | |
html = urllib.request.urlopen(url) | |
soup = BeautifulSoup(html, 'lxml') | |
for x in soup.find_all('pre'): | |
x.decompose() | |
for x in soup.find_all('table'): | |
x.decompose() | |
res = soup.find('div', attrs={'class': 'entry-content'}).get_text() | |
with open(fname, 'w') as f: | |
for x in re.sub('[ \t ]', '', res).split('\n'): | |
if x != '': | |
f.write(tagger.parse(x)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment