# 协程实现 （学习使用，请勿用于商业行为）

前言：具体分析过程请移步到我另外一篇文章：juejin.cn/post/715271…

import asyncio
import aiohttp
import parsel
from jsonpath import jsonpath


async def set_session_to_json(url, params, headers):
    async with aiohttp.ClientSession(connector=aiohttp.TCPConnector(ssl=False)) as session:
        async with session.get(url, params=params, headers=headers) as res:
            return await res.json()


async def set_session_to_text(url, params, headers):
    async with aiohttp.ClientSession(connector=aiohttp.TCPConnector(ssl=False)) as session:
        async with session.get(url, params=params, headers=headers) as res:
            return await res.text("utf-8", "ignore")

async def init_request(code):
    headers = {
        'Accept': '*/*',
        'Connection': 'keep-alive',
        'Accept-Language': 'zh-CN,zh;q=0.9',
        'Referer': 'https://www.eastmoney.com/',
        'Sec-Fetch-Dest': 'script',
        'Sec-Fetch-Mode': 'no-cors',
        'Sec-Fetch-Site': 'same-site',
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/105.0.0.0 Safari/537.36',
        'sec-ch-ua': '"Google Chrome";v="105", "Not)A;Brand";v="8", "Chromium";v="105"',
        'sec-ch-ua-mobile': '?0',
        'sec-ch-ua-platform': '"Windows"',
    }
    params = {
        'input': code,
        'type': '14',
    }
    url = 'https://searchapi.eastmoney.com/***/get'
    response = await set_session_to_json(url, params, headers)
    return response



async def get_overview_url_code(response):
    QuoteID = response['QuotationCodeTable']['Data'][0]['QuoteID']
    url = f'http://quote.eastmoney.com/***/{QuoteID}'
    response = await set_session_to_text(url, params=None, headers=None)
    selector = parsel.Selector(response)
    overview_url = selector.xpath('//a[text()="公司概况"]/@href').get()
    end_code = overview_url.split('=')[-1]
    return end_code


async def request_url(code):
    headers = {
        'Accept': '*/*',
        'Accept-Language': 'zh-CN,zh;q=0.9',
        'Connection': 'keep-alive',
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/105.0.0.0 Safari/537.36',
        'X-Requested-With': 'XMLHttpRequest',
    }
    params = {
        'code': f'{code}',
    }
    url = 'http://emweb.securities.eastmoney.com/***/PageAjax'
    response = await set_session_to_json(url, params=params, headers=headers)
    return response


async def parse_response(response):
    item = {}
    item['companyName'] = jsonpath(response, "$..ORG_NAME")[0]  # 公司名称
    item['numberOfEmployees'] = jsonpath(response, "$..EMP_NUM")[0]  # 雇员人数
    item['companyProfile'] = jsonpath(response, "$..ORG_PROFILE")[0]  # 公司简介
    item['sfcIndustry'] = jsonpath(response, "$..INDUSTRYCSRC1")[0]  # 所属证监会行业
    item['dateOfEstablishment'] = jsonpath(response, "$..FOUND_DATE")[0]  # 成立日期
    print(item)


async def run(code):
    response = await init_request(code)
    end_code = await get_overview_url_code(response)
    res = await request_url(end_code)
    await parse_response(res)


if __name__ == '__main__':
    import time

    start = time.time()
    code_list = [
        "300***",
        "688***",
        "300***",
        "603***",
        "300***",
        "688***",
        "300***",
        "300***",
        "600***",
        "002***",
        "300***",
        "601***",
        "836***",
        "688***",
        "301***", ]

    loop = asyncio.get_event_loop()
    tasks = [run(code) for code in code_list]
    loop.run_until_complete(asyncio.wait(tasks))
    loop.close()
    end = time.time()
    print(end-start)

以上均为学习分享，可能存在不足或者还有其他更优雅的方法，欢迎评论区留言交流！