#-*-coding:utf-8 -*-
‘‘‘爬取评论区的美女照片‘‘‘
import requests
import re
RE_PICTURE_NAME = re.compile(r‘(\w)+\.[A-Za-z]+$‘)
RE_URL = re.compile(r‘(\w)+\.(\w)+\.(\w)+/(\w)+\/(\w){2,}\/(\w)+.jpg‘)
request_top_list = requests.get(‘https://mm.taobao.com/json/request_top_list.htm‘)
RESPONSE = request_top_list.text #resp.text返回的是Unicode型的数据
def Get_Reuest_Picture_List(RESPONSE):
    ‘‘‘抓取页面的所有URL‘‘‘
    URLS = []
    for match in RE_URL.finditer(RESPONSE): #所有与pattern相匹配的全部字串，以迭代器的形式返回 与findall的区别,findall在字符串中找到正则表达式所匹配的所有子串，并组成一个列表返回
        URL = match.group()
        URLS.append(‘http://‘+URL)
    return URLS

def Download_Url_Picture(URL):
    ‘‘‘下载图片‘‘‘
    REQUEST_CONTENT = requests.get(URL).content #resp.content返回的是bytes型也就是二进制的数据
    PICTURE_NAME = RE_PICTURE_NAME.search(URL).group(0) #根据url获取图片名字
    FILE_OBJECT = open(str(PICTURE_NAME),‘wb‘) #以二进制的方式写文件
    FILE_OBJECT.write(‘picture\\‘+REQUEST_CONTENT)
    FILE_OBJECT.close()


def Save_All_Picture(URLS):
    ‘‘‘保存所有请求中的图片‘‘‘
    for URL in URLS:
        Download_Url_Picture(URL)

if __name__ == ‘__main__‘:
    URLS = Get_Reuest_Picture_List(RESPONSE)
    Save_All_Picture(URLS)