pip install aiohttp

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# author: 鋼鐵知識庫
import time
import requests
# 同步請求
def main():
    start = time.time()
    for i in range(5):
        res = requests.get('http://httpbin.org/delay/2')
        print(f'當(dāng)前時間：{datetime.datetime.now()}, status_code = {res.status_code}')
    print(f'requests同步耗時：{time.time() - start}')
if __name__ == '__main__':
    main()
'''
當(dāng)前時間：2022-09-05 15:44:51.991685, status_code = 200
當(dāng)前時間：2022-09-05 15:44:54.528918, status_code = 200
當(dāng)前時間：2022-09-05 15:44:57.057373, status_code = 200
當(dāng)前時間：2022-09-05 15:44:59.643119, status_code = 200
當(dāng)前時間：2022-09-05 15:45:02.167362, status_code = 200
requests同步耗時：12.785893440246582
'''

#!/usr/bin/env python
# file: day6-9同步和異步.py
# author: 鋼鐵知識庫
import asyncio
import time
import aiohttp
async def async_http():
    # 聲明一個支持異步的上下文管理器
    async with aiohttp.ClientSession() as session:
        res = await session.get('http://httpbin.org/delay/2')
        print(f'當(dāng)前時間：{datetime.datetime.now()}, status_code = {res.status}')
tasks = [async_http() for _ in range(5)]
start = time.time()
# Python 3.7 及以后,不需要顯式聲明事件循環(huán),可以使用 asyncio.run()來代替最后的啟動操作
asyncio.run(asyncio.wait(tasks))
print(f'aiohttp異步耗時：{time.time() - start}')
'''
當(dāng)前時間：2022-09-05 15:42:32.363966, status_code = 200
當(dāng)前時間：2022-09-05 15:42:32.366957, status_code = 200
當(dāng)前時間：2022-09-05 15:42:32.374973, status_code = 200
當(dāng)前時間：2022-09-05 15:42:32.384909, status_code = 200
當(dāng)前時間：2022-09-05 15:42:32.390318, status_code = 200
aiohttp異步耗時：2.5826876163482666
'''

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Author  : 鋼鐵知識庫
import asyncio
import aiohttp
async def get_api(session, url):
    # 聲明一個支持異步的上下文管理器
    async with session.get(url) as response:
        return await response.text(), response.status
async def main():
    async with aiohttp.ClientSession() as session:
        html, status = await get_api(session, 'http://httpbin.org/delay/2')
        print(f'html: {html[:50]}')
        print(f'status : {status}')
if __name__ == '__main__':
    #  Python 3.7 及以后,不需要顯式聲明事件循環(huán),可以使用 asyncio.run(main())來代替最后的啟動操作
    asyncio.get_event_loop().run_until_complete(main())
'''
html: {
  "args": {}, 
  "data": "", 
  "files": {}, 
status : 200
Process finished with exit code 0
'''

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Author  : 鋼鐵知識庫
import aiohttp
import asyncio
async def main():
    params = {'name': '鋼鐵知識庫', 'age': 23}
    async with aiohttp.ClientSession() as session:
        async with session.get('https://www.httpbin.org/get', params=params) as res:
            print(await res.json())
if __name__ == '__main__':
    asyncio.get_event_loop().run_until_complete(main())
'''
{'args': {'age': '23', 'name': '鋼鐵知識庫'}, 'headers': {'Accept': '*/*', 'Accept-Encoding': 'gzip, deflate', 'Host': 'www.httpbin.org', 'User-Agent': 'Python/3.8 aiohttp/3.8.1', 'X-Amzn-Trace-Id': 'Root=1-63162e34-1acf7bde7a6d801368494c72'}, 'origin': '122.55.11.188', 'url': 'https://www.httpbin.org/get?name=鋼鐵知識庫&age=23'}
'''

session.post('http://httpbin.org/post', data=b'data')
session.put('http://httpbin.org/put', data=b'data')
session.delete('http://httpbin.org/delete')
session.head('http://httpbin.org/get')
session.options('http://httpbin.org/get')
session.patch('http://httpbin.org/patch', data=b'data')

#!/usr/bin/env python
# @Author  : 鋼鐵知識庫
import aiohttp
import asyncio
async def main():
    data = {'name': '鋼鐵知識庫', 'age': 23}
    async with aiohttp.ClientSession() as session:
        async with session.post('https://www.httpbin.org/post', data=data) as response:
            print('status:', response.status)  # 狀態(tài)碼
            print('headers:', response.headers)  # 響應(yīng)頭
            print('body:', await response.text())  # 響應(yīng)體
            print('bytes:', await response.read())  # 響應(yīng)體二進(jìn)制內(nèi)容
            print('json:', await response.json())  # 響應(yīng)體json數(shù)據(jù)
if __name__ == '__main__':
    asyncio.get_event_loop().run_until_complete(main())

'''
status: 200
headers: <CIMultiDictProxy('Date': 'Tue, 06 Sep 2022 00:18:36 GMT', 'Content-Type': 'application/json', 'Content-Length': '534', 'Connection': 'keep-alive', 'Server': 'gunicorn/19.9.0', 'Access-Control-Allow-Origin': '*', 'Access-Control-Allow-Credentials': 'true')>
body: {
  "args": {}, 
  "data": "", 
  "files": {}, 
  "form": {
    "age": "23", 
    "name": "\u94a2\u94c1\u77e5\u8bc6\u5e93"
  }, 
  "headers": {
    "Accept": "*/*", 
    "Accept-Encoding": "gzip, deflate", 
    "Content-Length": "57", 
    "Content-Type": "application/x-www-form-urlencoded", 
    "Host": "www.httpbin.org", 
    "User-Agent": "Python/3.8 aiohttp/3.8.1", 
    "X-Amzn-Trace-Id": "Root=1-631691dc-6aa1b2b85045a1a0481d06e1"
  }, 
  "json": null, 
  "origin": "122.55.11.188", 
  "url": "https://www.httpbin.org/post"
}
bytes: b'{\n  "args": {}, \n  "data": "", \n  "files": {}, \n  "form": {\n    "age": "23", \n    "name": "\\u94a2\\u94c1\\u77e5\\u8bc6\\u5e93"\n  }, \n  "headers": {\n    "Accept": "*/*", \n    "Accept-Encoding": "gzip, deflate", \n    "Content-Length": "57", \n    "Content-Type": "application/x-www-form-urlencoded", \n    "Host": "www.httpbin.org", \n    "User-Agent": "Python/3.8 aiohttp/3.8.1", \n    "X-Amzn-Trace-Id": "Root=1-631691dc-6aa1b2b85045a1a0481d06e1"\n  }, \n  "json": null, \n  "origin": "122.5.132.196", \n  "url": "https://www.httpbin.org/post"\n}\n'
json: {'args': {}, 'data': '', 'files': {}, 'form': {'age': '23', 'name': '鋼鐵知識庫'}, 'headers': {'Accept': '*/*', 'Accept-Encoding': 'gzip, deflate', 'Content-Length': '57', 'Content-Type': 'application/x-www-form-urlencoded', 'Host': 'www.httpbin.org', 'User-Agent': 'Python/3.8 aiohttp/3.8.1', 'X-Amzn-Trace-Id': 'Root=1-631691dc-6aa1b2b85045a1a0481d06e1'}, 'json': None, 'origin': '122.55.11.188', 'url': 'https://www.httpbin.org/post'}
'''

#!/usr/bin/env python
# @Author  : 鋼鐵知識庫
import aiohttp
import asyncio
async def main():
    # 設(shè)置 1 秒的超時 
    timeout = aiohttp.ClientTimeout(total=1)
    data = {'name': '鋼鐵知識庫', 'age': 23}
    async with aiohttp.ClientSession(timeout=timeout) as session:
        async with session.get('https://www.httpbin.org/delay/2', data=data) as response:
            print('status:', response.status)  # 狀態(tài)碼
if __name__ == '__main__':
    asyncio.get_event_loop().run_until_complete(main())
'''
Traceback (most recent call last):
####中間省略####
    raise asyncio.TimeoutError from None
asyncio.exceptions.TimeoutError
'''

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Author  : 鋼鐵知識庫
import asyncio
from datetime import datetime
import aiohttp
# 聲明最大并發(fā)量
semaphore = asyncio.Semaphore(2)
async def get_api():
    async with semaphore:
        print(f'scrapting...{datetime.now()}')
        async with session.get('https://www.baidu.com') as response:
            await asyncio.sleep(2)
            # print(f'當(dāng)前時間：{datetime.now()}, {response.status}')
async def main():
    global session
    session = aiohttp.ClientSession()
    tasks = [asyncio.ensure_future(get_api()) for _ in range(1000)]
    await asyncio.gather(*tasks)
    await session.close()
if __name__ == '__main__':
    asyncio.get_event_loop().run_until_complete(main())
'''
scrapting...2022-09-07 08:11:14.190000
scrapting...2022-09-07 08:11:14.292000
scrapting...2022-09-07 08:11:16.482000
scrapting...2022-09-07 08:11:16.504000
scrapting...2022-09-07 08:11:18.520000
scrapting...2022-09-07 08:11:18.521000
'''

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Author  : 鋼鐵知識庫
# 不合適就是不合適，真正合適的，你不會有半點猶豫。
import asyncio
import json,re
import logging
import aiohttp
import requests
from utils.conn_db import ConnDb
# 日志格式
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s: %(message)s')
# 章節(jié)目錄api
b_id = '4308080950'
url = 'https://dushu.baidu.com/api/pc/getCatalog?data={"book_id":"'+b_id+'"}'
headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
                  "Chrome/104.0.0.0 Safari/537.36"
}
# 并發(fā)聲明
semaphore = asyncio.Semaphore(5)
async def download(title,b_id, cid):
    data = {
        "book_id": b_id,
        "cid": f'{b_id}|{cid}',
    }
    data = json.dumps(data)
    detail_url = 'https://dushu.baidu.com/api/pc/getChapterContent?data={}'.format(data)
    async with semaphore:
        async with aiohttp.ClientSession(headers=headers) as session:
            async with session.get(detail_url) as response:
                res = await response.json()
                content = {
                    'title': title,
                    'content': res['data']['novel']['content']
                }
                # print(title)
                await save_data(content)
async def save_data(data):
    if data:
        client = ConnDb().conn_motor_mongo()
        db = client.baidu_novel
        collection = db.novel
        logging.info('saving data %s', data)
        await collection.update_one(
            {'title': data.get('title')},
            {'$set': data},
            upsert=True
        )
async def main():
    res = requests.get(url, headers=headers)
    tasks = []
    for re in res.json()['data']['novel']['items']:     # 拿到某小說目錄cid
        title = re['title']
        cid = re['cid']
        tasks.append(download(title, b_id, cid))    # 將請求放到列表里，再通過gather執(zhí)行并發(fā)
    await asyncio.gather(*tasks)
if __name__ == '__main__':
    asyncio.run(main())