jira.py

import feedparser
import re
import time

URL = 'https://waimaichaoren.atlassian.net/activity?maxResults=5&os_authType=basic'

COOKIE_STR = """"""

REQUEST_HEADER = {
    'Cookie': COOKIE_STR,
}

CHECKUP_INTERVAL = 10   # seconds


def clean_html(raw_html):
    cleanr =re.compile('<.*?>')
    return re.sub(cleanr,'', raw_html)


def get_stream_data(url, max_items):
    f = feedparser.parse(URL, request_headers=REQUEST_HEADER)
    entries = f.entries[:max_items]
    result = []
    for ent in entries:
        id = ent.id
        title = ent.title
        summary = ent.summary
        result.append({
            'id': id,
            'title': clean_html(title),
            'summary': clean_html(summary),
        })
    return result


if __name__ == '__main__':
    feed_dict = {}

    while 1:
        data = get_stream_data(URL, 5)
        for d in data:
            if feed_dict.get(d['id']):
                continue
            else:
                print '>>> ', d['title']
                print d['summary'], '\n\n' 
                feed_dict[d['id']] = d
        time.sleep(CHECKUP_INTERVAL)