线程:线程是计算机中工作的最小单元
IO请求(IO密集型)时多线程更好,计算密集型进程并发最好,IO请求不涉及CPU
自定义线程池
进程:进程默认有主线程,可以有多线程共存,并且共享内部资源
自定义进程
协程:使用进程中一个线程去完成多个任务,微线程(伪线程)
GIL:python特有,用于在进程中对线程枷锁,保证同一时刻只能有一个线程被CPU调度
# Author:wylkjj
# Date:2020/2/24
# -*- coding:utf-8 -*-
import requests
# 创建多线程
from concurrent.futures import ThreadPoolExecutor
# 创建多进程
from concurrent.futures import ProcessPoolExecutor
def async_url(url):
try:
response = requests.get(url)
except Exception as e:
print('异常结果', response.url, response.content)
print('获取结果', response.url, response.content)
url_list = [
'http://www.baidu.com',
'http://www.chouti.com',
'http://www.bing.com',
'http://www.google.com',
]
# 线程池pool:创建五个线程,IO请求线程更适合
# GIL线程锁,只针对cpu的调用权限,针对IO请求不会锁住
pool = ThreadPoolExecutor(5)
# 进程池pools:创建五个线程,进程浪费资源
pools = ProcessPoolExecutor(5)
for url in url_list:
print('开始请求:', url)
pool.submit(async_url, url)
pool.shutdown(wait=True)
# 回调函数:.add_done_callback(回调的函数)
异步IO模块:
import asyncio缺点:只提供TCP,提供sleep,不提供http
事件循环:get_event_loop()
@asyncio.coroutine和yield from要同时配套使用,固定写法
异步IO:
# Author:wylkjj
# Date:2020/2/24
# -*- coding:utf-8 -*-
# 异步IO模块
import asyncio
@asyncio.coroutine
def func1():
print('before...func1......')
yield from asyncio.sleep(5)
print('end...func1......')
tasks = [func1(), func1()]
loop = asyncio.get_event_loop() # 事件循环
loop.run_until_complete(asyncio.gather(*tasks)) # 把任务作为列表传进来
loop.close()
# Author:wylkjj
# Date:2020/2/25
# -*- coding:utf-8 -*-
import asyncio
@asyncio.coroutine
def fetch_async(host, url='/'):
print(host, url)
reader, writer = yield from asyncio.open_connection(host, 80)
request_header_content = """GET %s HTTP/1.0\r\nHost: %s\r\n\r\n""" % (url, host,)
request_header_content = bytes(request_header_content, encoding='utf-8')
writer.write(request_header_content)
yield from writer.drain()
text = yield from reader.read()
print(host, url, str(text, encoding='utf-8'))
writer.close()
tasks = [
fetch_async('www.cnblogs.com', '/eric/'),
fetch_async('dig.chouti.com', '/pic/show?nid=4073644713430508&lid=10273091')
]
loop = asyncio.get_event_loop()
results = loop.run_until_complete(asyncio.gather(*tasks))
loop.close()
# Author:wylkjj
# Date:2020/2/25
# -*- coding:utf-8 -*-
# 使用aiohttp和asyncio实现http请求 (aiohttp亲)
import aiohttp
import asyncio
@asyncio.coroutine
def fetch_async(url):
print(url)
response = yield from aiohttp.request('GET', url)
# data = yield from response.read()
# print(url, data)
print(url, response)
response.close()
# Author:wylkjj
# Date:2020/2/25
# -*- coding:utf-8 -*-
# asyncio和requests配合使用也可以支持HTTP (requests后)
import asyncio
import requests
@asyncio.coroutine
def fetch_async(func, *args):
print(args)
# 事件循环
loop = asyncio.get_event_loop()
future = loop.run_in_executor(None, func, *args)
response = yield from future
print(response.url, response.content)
tasks = [
fetch_async(requests.get, 'http://www.cnblogs.com/eric/'),
fetch_async(requests.get, 'http://dig.chouti.com/pic/show?nid=4073644713430508&lid=10273091')
]
loop = asyncio.get_event_loop()
results = loop.run_until_complete(asyncio.gather(*tasks))
loop.close()
# Author:wylkjj
# Date:2020/2/25
# -*- coding:utf-8 -*-
import gevent
from gevent import monkey
monkey.patch_all()
import requests
def fetch_async(method, url, req_kwargs):
print(method, url, req_kwargs)
response = requests.request(method=method, url=url, **req_kwargs)
print(response.url, response.content)
# ##### 发送请求 #####
gevent.joinall([
gevent.spawn(fetch_async, method='get', url='https://www.python.org/', req_kwargs={
}),
gevent.spawn(fetch_async, method='get', url='https://www.yahoo.com/', req_kwargs={
}),
gevent.spawn(fetch_async, method='get', url='https://github.com/', req_kwargs={
}),
])
# pip3 install twisted
# pip3 install wheel
# b. 下载twisted http://www.lfd.uci.edu/~gohlke/pythonlibs/#twisted
# c. 进入下载目录,执行 pip3 install Twisted‑17.1.0‑cp35‑cp35m‑win_amd64.whl
from twisted.web.client import getPage
from twisted.internet import reactor
REV_COUNTER = 0
REQ_COUNTER = 0
def callback(contents):
print(contents,)
global REV_COUNTER
REV_COUNTER += 1
if REV_COUNTER == REQ_COUNTER:
reactor.stop()
url_list = ['http://www.bing.com', 'http://www.baidu.com', ]
REQ_COUNTER = len(url_list)
for url in url_list:
print(url)
deferred = getPage(bytes(url, encoding='utf8'))
deferred.addCallback(callback)
reactor.run()
import socket:它提供了标准的 BSD Sockets API,可以访问底层操作系统Socket接口的全部方法。
tronado框架原理
自定义异步IO:
基于socket,setblocking(False)
IO多路复用(也是同步IO)
while True:
r,w,e = select.select([ ],[ ],[ ],1)
关于IO的详情博客:事件驱动IO模型:https://www.cnblogs.com/wylshkjj/p/10896994.html
Linux
pip3 install scrapy
Windows
1.
pip3 install wheel
安装Twisted:版本信息知识一个格式,非正确版本
a. http://www.lfd.uci.edu/~gohlke/pythonlibs/#twisted, 下载:Twisted-19.1.0-cp37-cp37m-win_amd64.whl
b. 进入文件所在目录
c. pip3 install Twisted-19.1.0-cp37-cp37m-win_amd64.whl
2.
pip3 install scrapy:,此版本与urllib3模块产生冲突,如有此模块需要先卸载此模块
3.
windows上scrapy依赖 https://sourceforge.net/projects/pywin32/files/
# 部分项目代码展示,爬取优美图库图片
# -*- coding: utf-8 -*-
import scrapy
from scrapy.http import Request
from bs4 import BeautifulSoup
class UmeiSpider(scrapy.Spider):
name = 'umei'
allowed_domains = ['umei.cc']
start_urls = ['https://www.umei.cc/meinvtupian/meinvxiezhen/1.htm']
visited_set = set()
def parse(self, response):
self.visited_set.add(response.url) # 已经爬取的网页
# 1.将当前页所有的meizi图片爬下来
# 获取a标签并且属性为 class = TypeBigPics
main_page = BeautifulSoup(response.text, "html.parser")
item_list = main_page.find_all("a", attrs={
'class': 'TypeBigPics'})
for item in item_list:
item = item.find_all("img",)
print(item)
# 2.获取:https://www.umei.cc/meinvtupian/meinvxiezhen/(\d+).htm
page_list = main_page.find_all("div", attrs={
'class': 'NewPages'})
a_urls = 'https://www.umei.cc/meinvtupian/meinvxiezhen/'
a_list = page_list[0].find_all("a")
a_href = set()
for a in a_list:
a = a.get('href')
if a:
a_href.add(a_urls+a)
else:
pass
for i in a_href:
if i in self.visited_set:
pass
else:
obj = Request(url=i, method='GET', callback=self.parse)
yield obj
print("obj:", obj)