高性能爬虫

最新推荐文章于 2024-07-30 21:19:19 发布

Mark Huo

最新推荐文章于 2024-07-30 21:19:19 发布

阅读量285

点赞数

分类专栏：爬虫

爬虫专栏收录该内容

8 篇文章

订阅专栏

本文介绍如何使用asyncio、aiohttp、requests、gevent、grequests、Twisted和Tornado等库进行异步IO操作和协程编程，通过实例展示了不同场景下异步请求的处理方式。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

asyncio

https://www.cnblogs.com/wupeiqi/p/6229292.html

单独使用socket，可以实现协程的IO操作(需要字节封装Http)

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, text)
    writer.close()

tasks = [
    fetch_async('www.cnblogs.com', '/wupeiqi/'),
    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()

配合aiphttp，可以实现协程发送HTTP请求

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()


tasks = [fetch_async('http://www.google.com/'), fetch_async('http://www.chouti.com/')]

event_loop = asyncio.get_event_loop()
results = event_loop.run_until_complete(asyncio.gather(*tasks))
event_loop.close()

配合requests,可以实现协程发送request请求

import asyncio
import requests


@asyncio.coroutine
def fetch_async(func, *args):
    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/wupeiqi/'),
    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()

gevent

使用gevent完成异步IO操作

import gevent

import requests
from gevent import monkey
monkey.patch_all()


def task(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(task, method='get', url='https://www.python.org/', req_kwargs={}),
#     gevent.spawn(task, method='get', url='https://www.yahoo.com/', req_kwargs={}),
#     gevent.spawn(task, method='get', url='https://github.com/', req_kwargs={}),
# ])
# ##### 发送请求（协程池控制最大协程数量） #####
from gevent.pool import Pool
pool = Pool(5)
gevent.joinall([
    pool.spawn(task, method='get', url='https://www.python.org/', req_kwargs={}),
    pool.spawn(task, method='get', url='https://www.yahoo.com/', req_kwargs={}),
    pool.spawn(task, method='get', url='https://www.github.com/', req_kwargs={}),
])

joinall等待参数中的协程运行完毕

使用grequests完成IO操作

import grequests


request_list = [
    grequests.get('http://httpbin.org/delay/1', timeout=0.001),
    grequests.get('http://fakedomain/'),
    grequests.get('http://httpbin.org/status/500')
]


# ##### 执行并获取响应列表 #####
response_list = grequests.map(request_list,size=5)
print(response_list)

Twisted

#!/usr/bin/env python
# -*- coding:utf-8 -*-
from twisted.internet import defer
from twisted.web.client import getPage
from twisted.internet import reactor

def one_done(arg):
    print(arg)

def all_done(arg):
    print('done')
    reactor.stop()

@defer.inlineCallbacks
def task(url):
    res = getPage(bytes(url, encoding='utf8')) # 立即发送Http请求，立即添加
    res.addCallback(one_done)
    yield res

url_list = [
    'http://www.cnblogs.com',
    'http://www.cnblogs.com',
    'http://www.cnblogs.com',
    'http://www.cnblogs.com',
]

defer_list = [] # [特殊，特殊，特殊(已经向url发送请求)]
for url in url_list:
    v = task(url)
    defer_list.append(v)

d = defer.DeferredList(defer_list)
d.addBoth(all_done)


reactor.run() # 死循环 ，需要在all_done中设置退出
# 该方法会循环查找，d中的哪些请求得到了响应

Tornado

与twisted类似

#!/usr/bin/env python
# -*- coding:utf-8 -*-
from tornado.httpclient import AsyncHTTPClient
from tornado.httpclient import HTTPRequest
from tornado import ioloop

COUNT = 0
def handle_response(response):
    global COUNT
    COUNT -= 1
    if response.error:
        print("Error:", response.error)
    else:
        print(response.body)
        # 方法同twisted
        # ioloop.IOLoop.current().stop()
    if COUNT == 0:
        ioloop.IOLoop.current().stop()

def func():
    url_list = [
        'http://www.baidu.com',
        'http://www.bing.com',
    ]
    global COUNT
    COUNT = len(url_list)
    for url in url_list:
        print(url)
        http_client = AsyncHTTPClient()
        http_client.fetch(HTTPRequest(url), handle_response)


ioloop.IOLoop.current().add_callback(func)
ioloop.IOLoop.current().start() # 死循环