python爬虫实战-爬取糗图图片并保存至本地文件夹（正则）

python爬虫实战-爬取糗图图片并保存至本地文件夹（正则）

import urllib.request
import urllib.parse
import re
import os
import time

def handle_request(url,page):
	url=url+str(page)+'/'
	headers={
		'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36',
	}
	request=urllib.request.Request(url,headers=headers)
	return request

def download_image(content):
	pattern=re.compile(r'<div class="thumb">.*?<img src="(.*?)" alt=".*?">.*?</div>',re.S)
	ret=pattern.findall(content)
	for image_src in ret:
		image_src = 'https:'+image_src
		#创建文件夹
		dirname='qiutu'
		if not os.path.exists(dirname):
			os.mkdir(dirname)
		#图片的名称
		filename=image_src.split('/')[-1]
		filepath=dirname+'/'+filename
		print('%s图片正在下载......'%filename)
		urllib.request.urlretrieve(image_src,filepath)
		time.sleep(1)

def main():
	url="https://www.qiushibaike.com/pic/page/"
	start_page=int(input('请输入开始页码:'))
	end_page=int(input('请输入结束页码：'))
	for page in range(start_page,end_page+1):
		request=handle_request(url,page)
		content=urllib.request.urlopen(request).read().decode()
		print('第%s页开始下载......' %page)
		download_image(content)
		print('第%s页下载完毕......' %page)
		time.sleep(1)

#如果是主程序，则执行源代码，调运的话不执行
if __name__ == '__main__':
	main()