bs4 BeautifulSoup

#!/usr/bin/env python
# -*- coding:utf-8 -*-
# Author:woshinidaye

# <h1>i love you</h1>
# <h2 align="center">i love you</h2>
# <a href="http://www.cnblogs.com/woshinidaye123">woshinidaye</a>>
# <biaoqian 属性="属性"></biaoqian>


# pip install bs4
from bs4 import BeautifulSoup
import requests
#解析数据  requests
#把页面源代码交给BeautifulSoup进行处理，生成bs4对象
# test = BeautifulSoup('text','html.parser')  #指定html解析器
#从bs4对象中查找数据
    #find(标签,属性=值)
    #find_all(标签,属性=值)
# page.find('table',class_='ssss')  #python中已经有class类   前面加两个__表示私有属性，后面一个_表示区分
# page.find('table',attrs{'class':'sssss'})  #python中已经有class类，上述两种表示完全一样

# url = 'http://www.xinfadi.com.cn/getCat.html'
# headers = {
#     "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari"
# }
#
# req = requests.post(url,headers=headers)
# # print(req.json()['list'],type(req.json()['list']))
# for i in req.json()['list']:
#     print(i['id'],i['prodName'])

#实战案例
#思路
#1、拿到主页面的源代码，提取图片的连接地址，herf
#2、通过herf查看图片的下载连接；
#3、下载图片

import re,requests,time
from bs4 import BeautifulSoup
for i in range(2,100,1):
    url = 'https://www.umei.cc/meinvtupian/index_{0}.htm'.format(i)
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari"
    }

    resp = requests.get(url,headers=headers)
    resp.encoding = 'utf-8'  #处理乱码
    # print(resp.text)
    #把源代码给bs4
    girl_gape = BeautifulSoup(resp.text,'html.parser')
    aaa = girl_gape.find('div',class_= 'TypeList').find_all('a')
    for a in aaa:
        href = a.get('href')          #通过get获取属性
        href = 'https://www.umei.cc'+href
        #获取子页面的源代码
        child_page = requests.get(href,headers=headers)
        child_page.encoding = 'utf-8'
        child_page_text = child_page.text
        #从子页面中拿到图片的下载地址
        child_page_text_d = BeautifulSoup(child_page_text,'html.parser')
        bbb = child_page_text_d.find('div',class_ = 'ImageBody').find('img')
        src = bbb.get('src')
        #下载图片
        img = requests.get(src,headers=headers)
        img_name = src.split('/')[-1]
        img.content             #获取到图片，字节！！！！
        with open('E:\工作资料\python\Reptile\pic\{0}'.format(img_name),'wb') as f:
            f.write(img.content)
        print('===={0}  over===='.format(img_name))
        time.sleep(2)
print('====all done!!====')