typhoon_dayoff_crawler.py

# coding=utf8
import urllib
import re
from bs4 import BeautifulSoup as BS

url = 'http://www.dgpa.gov.tw/'

html_content = urllib.urlopen(url).read()
soup_obj = BS(html_content, 'html.parser')

texts = []

for string in soup_obj.stripped_strings:  # get all string from page
    texts.append(string.encode('utf8'))

for text in texts:

    if re.search(r'^105', text):
        print 'title: ', text

    if re.search(u'臺北市', text.decode('utf8')):
        print 'city: ', text
        info = texts[texts.index(text)+1] # get next line
        print 'info: ', info