Python网络爬虫中的同步与异步示例详解

#同步编程（同一时间只能做一件事，做完了才能做下一件事情）
<-a_url-><-b_url-><-c_url->
#异步编程 (可以近似的理解成同一时间有多个事情在做，但有先后)
<-a_url->
 <-b_url->
 <-c_url->
 <-d_url->
 <-e_url->
  <-f_url->
  <-g_url->
  <-h_url->
  <--i_url-->
   <--j_url-->

import asyncio
#函数名:做现在的任务时不等待，能继续做别的任务。
async def donow_meantime_dontwait(url):
 response = await requests.get(url)
#函数名:快速高效的做任务
async def fast_do_your_thing():
 await asyncio.wait([donow_meantime_dontwait(url) for url in urls])
#下面两行都是套路，记住就好
loop = asyncio.get_event_loop()
loop.run_until_complete(fast_do_your_thing())

import asyncio
import requests
import time
import aiohttp
urls = ['https://book.douban.com/tag/小说','https://book.douban.com/tag/科幻',
 'https://book.douban.com/tag/漫画','https://book.douban.com/tag/奇幻',
 'https://book.douban.com/tag/历史','https://book.douban.com/tag/经济学']
async def requests_meantime_dont_wait(url):
 print(url)
 async with aiohttp.ClientSession() as session:
 async with session.get(url) as resp:
  print(resp.status)
  print("{url} 得到响应".format(url=url))
async def fast_requsts(urls):
 start = time.time()
 await asyncio.wait([requests_meantime_dont_wait(url) for url in urls])
 end = time.time()
 print("Complete in {} seconds".format(end - start))
loop = asyncio.get_event_loop()
loop.run_until_complete(fast_requsts(urls))

from gevent import monkey
import gevent
import requests
import time


monkey.patch_all()

def req(url):
 print(url)
 resp = requests.get(url)
 print(resp.status_code,url)
def synchronous_times(urls):
 """同步请求运行时间"""
 start = time.time()
 for url in urls:
 req(url)
 end = time.time()
 print('同步执行时间 {} s'.format(end-start))
def asynchronous_times(urls):
 """异步请求运行时间"""
 start = time.time()
 gevent.joinall([gevent.spawn(req,url) for url in urls])
 end = time.time()
 print('异步执行时间 {} s'.format(end - start))
urls = ['https://book.douban.com/tag/小说','https://book.douban.com/tag/科幻',
 'https://book.douban.com/tag/漫画','https://book.douban.com/tag/奇幻',
 'https://book.douban.com/tag/历史','https://book.douban.com/tag/经济学']
synchronous_times(urls)
asynchronous_times(urls)

import gevent
def foo():
 print('Running in foo')
 gevent.sleep(0)
 print('Explicit context switch to foo again')

def bar():
 print('Explicit context to bar')
 gevent.sleep(0)
 print('Implicit context switch back to bar')

gevent.joinall([
 gevent.spawn(foo),
 gevent.spawn(bar)
 ])

Running in foo
Explicit context to bar
Explicit context switch to foo again
Implicit context switch back to bar

import gevent
import random
def task(pid):
 """
 Some non-deterministic task
 """
 gevent.sleep(random.randint(0,2)*0.001)
 print('Task %s done' % pid)
#同步（结果更像串行）
def synchronous():
 for i in range(1,10):
 task(i)
#异步（结果更像乱步）
def asynchronous():
 threads = [gevent.spawn(task, i) for i in range(10)]
 gevent.joinall(threads)
print('Synchronous同步:')
synchronous()
print('Asynchronous异步:')
asynchronous()

Synchronous同步:
Task 1 done
Task 2 done
Task 3 done
Task 4 done
Task 5 done
Task 6 done
Task 7 done
Task 8 done
Task 9 done
Asynchronous异步:
Task 1 done
Task 5 done
Task 6 done
Task 2 done
Task 4 done
Task 7 done
Task 8 done
Task 9 done
Task 0 done
Task 3 done

#url构建只需要传入word即可
url = "http://dict.youdao.com/w/eng/{}/".format(word)

def fetch_word_info(word):
 url = "http://dict.youdao.com/w/eng/{}/".format(word)
 resp = requests.get(url,headers=headers)
 doc = pq(resp.text)
 pros = ''
 for pro in doc.items('.baav .pronounce'):
  pros+=pro.text()
 description = ''
 for li in doc.items('#phrsListTab .trans-container ul li'):
  description +=li.text()
 return {'word':word,'音标':pros,'注释':description}

import requests
from pyquery import PyQuery as pq
import gevent
import time
import gevent.monkey
gevent.monkey.patch_all()
words = ['good','bad','cool',
   'hot','nice','better',
   'head','up','down',
   'right','left','east']
def synchronous():
 start = time.time()
 print('同步开始了')
 for word in words:
  print(fetch_word_info(word))
 end = time.time()
 print("同步运行时间： %s 秒" % str(end - start))

#执行同步
synchronous()

import requests
from pyquery import PyQuery as pq
import gevent
import time
import gevent.monkey
gevent.monkey.patch_all()
words = ['good','bad','cool',
   'hot','nice','better',
   'head','up','down',
   'right','left','east']
def asynchronous():
 start = time.time()
 print('异步开始了')
 events = [gevent.spawn(fetch_word_info,word) for word in words]
 wordinfos = gevent.joinall(events)
 for wordinfo in wordinfos:
  #获取到数据get方法
  print(wordinfo.get())
 end = time.time()
 print("异步运行时间： %s 秒"%str(end-start))
#执行异步
asynchronous()

seqence = list(range(20))
size = 5 #子列表长度
output = [seqence[i:i+size] for i in range(0, len(seqence), size)]
print(output)

chunks = lambda seq, size: [seq[i: i+size] for i in range(0, len(seq), size)]
print(chunks(seq, 5))

def chunks(seq,size):
 for i in range(0,len(seq), size):
  yield seq[i:i+size]
prinT(chunks(seq,5))
 for x in chunks(req,5):
   print(x) 

import requests
from pyquery import PyQuery as pq
import gevent
import time
import gevent.monkey
gevent.monkey.patch_all()
words = ['good','bad','cool',
   'hot','nice','better',
   'head','up','down',
   'right','left','east']
def fetch_word_info(word):
 url = "http://dict.youdao.com/w/eng/{}/".format(word)
 resp = requests.get(url,headers=headers)
 doc = pq(resp.text)
 pros = ''
 for pro in doc.items('.baav .pronounce'):
  pros+=pro.text()
 description = ''
 for li in doc.items('#phrsListTab .trans-container ul li'):
  description +=li.text()
 return {'word':word,'音标':pros,'注释':description}
def asynchronous(words):
 start = time.time()
 print('异步开始了')
 chunks = lambda seq, size: [seq[i: i + size] for i in range(0, len(seq), size)]
 for subwords in chunks(words,3):
  events = [gevent.spawn(fetch_word_info, word) for word in subwords]
  wordinfos = gevent.joinall(events)
  for wordinfo in wordinfos:
   # 获取到数据get方法
   print(wordinfo.get())
  time.sleep(1)
  end = time.time()
 print("异步运行时间： %s 秒" % str(end - start))
asynchronous(words)