weather_crawler.py

import datetime
import time

from BeautifulSoup import BeautifulSoup
import requests


def get_content(url):
    res = requests.get(url)
    return res.content

def html_parser():
    pass


if __name__ == '__main__':
    d = datetime.datetime.now()

    start_time = time.mktime(datetime.datetime(d.year, d.month, d.day).timetuple())
    start_time = str(int(start_time) * 1000)

    d = d + datetime.timedelta(days=1)
    end_time = time.mktime(datetime.datetime(d.year, d.month, d.day).timetuple())
    end_time = str(int(end_time) * 1000)
    #print start_time, end_time

    result = get_content('http://weather.tp.edu.tw/Ajax/jsonp/table.ashx?callback=schooltable&id=333609&by=minute&start=1407600000000&end=1407686400000')
    print result

#!/usr/bin/env python
# -*- encoding: utf-8
from datetime import datetime
import requests

if __name__ == '__main__':
    d = datetime.now()

    start = int(datetime(d.year, d.month, d.day).strftime('%s')) * 1000
    end = start + 86400*1000 # seconds/day

    request_url = 'http://weather.tp.edu.tw/Ajax/jsonp/table.ashx'
    request_params = dict(id='333609', by='minute', start=start, end=end)
    response = requests.get(request_url, params=request_params)
    if response.status_code == 200:
        result = response.json()
        print result['result'][0]
        print result['result'][0]['學校名稱'.decode('utf-8')].encode('utf-8')
    else:
        raise Exception('response.status_code=[%s]' % response.status_code)