煎蛋网爬妹子图

白two

刚学了煎蛋网爬图片，由于煎蛋网改了，所以很多东西和小甲鱼录视频的时候不一样，就没按小甲鱼的来，感觉模块化还是没做好
代理ip就自己找了，因为只用了一个ip，所以加了个time模块防止被封

import requests
import bs4
import time
import os

#请求头
headers ={}
headers['User-Agent'] = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 11_1_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36'

#代理IP
proxies = {'https':'175.146.211.249:9999'}

#初始网址
url = 'http://i.jandan.net/ooxx'

#现在的煎蛋网址里面的页码不是page=多少了
#获得下一页网址，每一页网页源代码里面都有有下一页地址
def get_site(url):
    response = requests.get(url,headers =headers,proxies = proxies)
    soup = bs4.BeautifulSoup(response.text,'html.parser')
    item = soup.find('a',title='Older Comments')
    link = item.get('href')
    return 'http:'+link
    
#下载每一页的图片，图片地址在网页源代码里面
def download_mm(url,):
    response = requests.get(url,headers =headers,proxies = proxies)
    soup = bs4.BeautifulSoup(response.text,'html.parser')
    items = soup.select('div.commenttext a')
    for each in items:
        link = each['href']
        res = requests.get('http:'+link)
        mm_img = res.content
        with open('mm-{}.jpg'.format(link[-9:-5]),'wb') as f:
            f.write(mm_img)

folder=input('请输入文件名：')
os.mkdir(folder)
os.chdir(folder)

n = int(input('请输入要爬取多少页图片：'))

for i in range(n):
    download_mm(url)
    url = get_site(url)
    time.sleep(1)