提升爬虫效率之线程池

Posted 2021-03-25 guniang

 

一、使用Flask模拟阻塞，利用线程池爬取数据

#模拟Flask

#pip install flask
from flask import Flask,render_template #返回一个模板文件需要导入render_tamplate
from time import sleep

app = Flask(__name__)

@app.route(‘/bobo‘)
def index_1():
    return ‘hello world‘


@app.route(‘/jay‘)
def index_2():
    sleep(2)
    return render_template(‘test.html‘)

@app.route(‘/tom‘)
def index_3():
    sleep(2)
    return render_template(‘test.html‘)

if __name__ == ‘__main__‘:
    app.run(threaded=True)   #括号里面也可以写debug=True 也可以不写

线程池代码：

# 同步代码
# import requests
# import time

#
# urls = [
#     ‘http://127.0.0.1:5000/jay‘,
#     ‘http://127.0.0.1:5000/tom‘,
#     ‘http://127.0.0.1:5000/jay‘,
#     ‘http://127.0.0.1:5000/tom‘,
# ]
# start = time.time()
# for url in urls:
#     page_text = requests.get(url).text
#     print(len(page_text))
#
# print(‘总耗时‘,time.time()-start)

#异步代码
import requests
import time
from multiprocessing.dummy import Pool
pool = Pool(4)

urls = [
    ‘http://127.0.0.1:5000/jay‘,
    ‘http://127.0.0.1:5000/tom‘,
    ‘http://127.0.0.1:5000/jay‘,
    ‘http://127.0.0.1:5000/tom‘,
]
start = time.time()
def get_request(url):
    page_text = requests.get(url).text
    print(len(page_text))

def parse(page_text):
    print(‘模仿解析‘)

page_text_list = pool.map(get_request,urls)  #这个map做数据请求
pool.map(parse,page_text_list) #这个map做数据解析
print(‘总耗时‘,time.time()-start)