Core script of an alfred workflow crawling news from 163.com

neteasenews.py

#! /usr/bin/env python
# coding=utf-8

__author__ = 'kingson_jeasinema'

import sys
import alfred
import requests

headers = {
    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.181 Safari/537.36',
}

topic = {
    'headline': ('headline/T1348647853363',),
    'sport': ('list/T1348649079062',),
    'finance': ('list/T1348648756099',),
    'gossip': ('list/T1348648517839',),
    'keji': ('list/T1348649580692',),
    'beijing': ('local/5YyX5Lqs',u'北京'),
    # 'soccer': ('list/T1399700447917',)
    'movie': ('list/T1348648650048',),
    'car': ('list/T1348654060988',),
    'joke': ('list/T1350383429665',),
    'game': ('list/T1348654151579',),
    'featured': ('list/T1370583240249',),
    'radio': ('list/T1379038288239',),
    'nba': ('list/T1348649145984',),
    'electronics': ('list/T1348649776727',),
    'mobile': ('list/T1351233117091',),
    'education': ('list/T1348654225495',),
    # 'forum': ('list/T1349837670307',),
    'travel': ('list/T1348654204705',),
    'phone': ('list/T1348649654285',),
    'blog': ('list/T1349837698345',),
    'society': ('list/T1348648037603',),
    'message': ('list/T1371543208049',),
    'mil': ('list/T1348648141035',),
}


def set_cache(query):
    """
    获取头条新闻并缓存
    """
    if query in list(topic.keys()):
        pid = topic[query][0].split('/')[-1] if len(topic[query]) == 1 else topic[query][1]
        result = requests.get('http://c.m.163.com/nc/article/{}/0-20.html'.format(topic[query][0]), headers=headers).json()
        response = result[pid]
        cache1 = []
        for i in range(len(response)):
            if 'url_3w' in response[i].keys():
                cache1.append(dict(title=response[i]['title'], digest=response[i]['digest'],
                                   url=response[i]['url_3w']))
        alfred.cache.set('{}.list'.format(query), cache1, expire=1)

def get_cache(query):
    """
    获取缓存信息
    """
    if query in list(topic.keys()):
        if alfred.cache.timeout('{}.list'.format(query)) == -1:
            set_cache(query)
        return alfred.cache.get('{}.list'.format(query))

def output(query):
    """
    返回结果给Alfred
    """
    workflows = get_cache(query)
    workflows = [w for w in workflows if query]
    feedback = alfred.Feedback()
    for w in workflows:
        feedback.addItem(
            title=w['title'],
            subtitle=w['digest'],
            arg=w['url']
        )
    feedback.output()

if __name__ == '__main__':
    output(sys.argv[1])