多进程爬取表情包

# -*- coding: utf-8 -*-
"""
Created on Thu Dec 19 18:59:58 2019

@author: m
"""
import urllib,os
import requests
from lxml import etree
from multiprocessing import Pool
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.132 Safari/537.36"
}

def parse_page(url):
    response = requests.get(url,headers)
    html = response.text
    html = etree.HTML(html)
    lists = html.xpath('//div[@id="bqb"]/div[@class="ui segment imghover"]/div[@class="tagbqppdiv"]')
    srcs = []
    titles=[]
    for li in lists:
        src = li.xpath('./a/img/@data-original')[0]
        title = li.xpath('./a/@title')[0]
        srcs.append(src)
        titles.append(title)
    return srcs,titles
def download(srcs,titles):
    file_path='D:/book/imgews'  
    r=0
    try:
        for src in srcs:
            print(src)
            file_suffix = os.path.splitext(src)[1]
            file_name = titles[r][0:3]#截取前三个做文件名字
            file_name = file_name.replace('?','').replace(':','').replace('*','').replace('"','')
            filename = '{}{}{}{}'.format(file_path,os.sep,file_name,file_suffix)
            print(filename)
            urllib.request.urlretrieve(src,filename=filename)
            r+=1
    except IOError as e:
        print("IOError")
#    except Exception as e:
#        print("Exception")
if __name__ == "__main__":
    a= []
    p = Pool()        
    for i in range(0,100):
        url = "https://www.fabiaoqing.com/biaoqing/lists/page/{}.html".format(i)
        print("正在下载:..........................................................",url)       
        a.append(p.apply_async(parse_page,(url,)))
    p.close()
    p.join()
    p = Pool()
    for i in a:
        
        print(i.get()[1],i.get()[0])#是一个数组里面有两个列表
        p.apply_async(download,(i.get()[0],i.get()[1]))