爬网页并协程下载图片

#!/usr/bin/env python3
#-*-coding:utf-8-*-
import re
from urllib import request
from gevent import monkey
import os
monkey.patch_socket() #遇到socket请求进行替换
import gevent
import requests

#1.抓取网页信息,保存在wallpaper.html
def digestPage():
    headers={
    'user-agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'
    }
    url = "https://wallhalla.com/random"
    webPage=requests.get(url,headers=headers)
    if webPage.status_code==200:
        data=webPage.content   #得到二进制数据
        print(type(data))
    else:
        print('无法抓取信息')
        return False

    with open('wallpaper.html','wb') as wall_file:  #必须以wb才能把网页数据写入文件中
        wall_file.write(data)
        return True


#2.定义协程逻辑(下载图片)代码
def download(url,file_name):
    headers = {
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'
    }
    print('图片%s下载等待'%file_name)
    response=requests.get(url,headers=headers)#使用url请求网络地址
    with open(file_name,'wb') as f:
        f.write(response.content)  #此处注意得保存二进制数据才能正常查看图片
    print('图片%s下载完毕'%file_name)

def locateAndDownload():
    with open('wallpaper.html','r',encoding='utf-8') as file:
        data=file.read()
        pattern=re.compile('<img.*src.{1,3}[\'|\"](\S*)[\'\"]')
        result=re.findall(pattern,data)#将我们所要的图片地址筛选出来
        #print(result)  #result就是我们的壁纸下载链接的相对地址
        prefix='https://wallhalla.com/'
        for i in range(len(result)):
            downloadlink = os.path.join(prefix, result[i][1:])
            # print(downlink)
            gevent.joinall( #使用joinall方法注册任务并执行任务
                [#gevent.spawn()方法创建任务
                    gevent.spawn(download, downloadlink, str(i) + '.jpg')
                ]
            )

if __name__=='__main__':
    if digestPage():
        locateAndDownload()
    else:
        print("Sorry,我们无法帮您下载图片哦")