案例 - 异步爬取网站小说

 

小说 :

#https://dushu.baidu.com/api/pc/getCatalog?data={"book_id":"4306063500"}

#https://dushu.baidu.com/api/pc/getChapterContent?data={"book_id":"4306063500","cid":"4306063500|1569782244","need_bookinfo":1}

import requests
import asyncio
import aiohttp
import json
import aiofiles

async def aiodownload(cid, book_id, title):
    data = {
        "book_id": book_id,
        "cid": f"{book_id}|{cid}",
        "need_bookinfo": 1
    }

    data = json.dumps(data) #  将json 变成字符串

    url = f'https://dushu.baidu.com/api/pc/getChapterContent?data={data}'

    async with aiohttp.ClientSession() as session:
        async with session.get(url) as resp:
            dic = await resp.json()
            async with aiofiles.open(title, mode='w', encoding='utf-8') as f:
                await f.write(dic['data']['novel']['content'])


async def getCatlog(url):
    # 请求数据
    resp = requests.get(url)
    #循环出数据
    dic = resp.json()
    # 新建一个列表
    tasks = []


    for item in dic['data']['novel']['items']:
        title = item['title']
        cid = item['cid']

        #准备异步
        tasks.append(aiodownload(cid, book_id, title))

    await asyncio.wait(tasks)



if __name__ == '__main__':
    book_id = '4306063500'
    url = 'https://dushu.baidu.com/api/pc/getCatalog?data={"book_id":"' + book_id + '"}'  #链接拼接
    asyncio.run(getCatlog(url))