京东百亿补贴上线，电商巨头价格战卷起来

import urllib.parse
import asyncio
import aiohttp
import lxml.html
import random

URL_TEMPLATE = 'https://search.jd.com/search?keyword=%E6%89%8B%E6%9C%BA/{}'
HEADERS_LIST = [
    'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36',
    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36 Edge/16.16299',
    'Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; AS; rv:11.0) like Gecko',
    # 添加更多 User-Agent
]

# 代理服务器( www.16yun.cn)
proxyHost = "t.16yun.cn"
proxyPort = "31111"

# 代理验证信息
proxyUser = "16yun"
proxyPass = "16ip"

PROXIES = "http://%(user)s:%(pass)s@%(host)s:%(port)s" % {
    "host" : proxyHost,
    "port" : proxyPort,
    "user" : proxyUser,
    "pass" : proxyPass,
}

async def query(content):
    async with aiohttp.ClientSession(headers=get_random_headers()) as session:
        url = URL_TEMPLATE.format(urllib.parse.quote(content))        
        async with session.get(url, proxy=PROXIES) as response:
            html = lxml.html.fromstring(await response.read())
            sen_list = html.xpath('//div[contains(@class,"lemma-summary") or contains(@class,"lemmaWgt-lemmaSummary")]//text()')
            sen_list_after_filter = [item.strip('\n') for item in sen_list]
            return '\n'.join(sen_list_after_filter).encode('utf-8')

async def main():
    async for content in get_input():
        result = await query(content)
        print("查询结果：\n%s" % result.decode('utf-8'))

async def get_input():
    while True:
        yield input('查询词语：')

def get_random_headers():
    return {'User-Agent': random.choice(HEADERS_LIST)}

if __name__ == '__main__':
    asyncio.run(main())