爬取网页图片

import re
import requests
import sys

respose=requests.get('http://www.xiaohuar.com/v/')



# print(respose.status_code)# 响应的状态码
# print(respose.content)  #返回字节信息
# print(respose.text)  #返回文本内容
urls=re.findall(r'class="items".*?href="(.*?)"',respose.text,re.S)  #re.S 把文本信息转换成1行匹配
url=urls[4]
result=requests.get(url)
mp4_url=re.findall(r'id="media".*?src="(.*?)"',result.text,re.S)[0]

video=requests.get(mp4_url,stream=True, verify=False)
# 既然要实现下载进度，那就要知道你文件大小啊，下面这句就是得到总大小
total_size = int(video.headers['Content-Length'])
temp_size = 0
#
with open('D:\\b.mp4','wb') as f:
    for chunk in video.iter_content(chunk_size=1024):
        temp_size += len(chunk)
        f.write(chunk)
        f.flush()
        #############花哨的下载进度部分###############
        done = int(50 * temp_size / total_size)
        sys.stdout.write("\r[%s%s] %d%%" % ('█' * done, ' ' * (50 - done), 100 * temp_size / total_size))
        sys.stdout.flush()
print('下载完成')

原文：http://www.cnblogs.com/Axi8/p/5757270.html

转载于:https://www.cnblogs.com/dongma/p/10127028.html