爬虫煎蛋网的mm图片

import urllib.request
import os

url_list = [
    'http://jandan.net/ooxx/MjAyMDAxMTUtMTM3#comments',    #每一页的URL，当前是136页
    'http://jandan.net/ooxx/MjAyMDAxMTUtMTM2#comments',
    'http://jandan.net/ooxx/MjAyMDAxMTUtMTM1#comments',
    'http://jandan.net/ooxx/MjAyMDAxMTUtMTM0#comments',
    'http://jandan.net/ooxx/MjAyMDAxMTUtMTMz#comments',
    'http://jandan.net/ooxx/MjAyMDAxMTUtMTMy#comments',
    'http://jandan.net/ooxx/MjAyMDAxMTUtMTMx#comments',
    'http://jandan.net/ooxx/MjAyMDAxMTUtMTMw#comments',
    'http://jandan.net/ooxx/MjAyMDAxMTUtMTI5#comments',
    'http://jandan.net/ooxx/MjAyMDAxMTUtMTI4#comments'
]

def url_open(url):
    req = urllib.request.Request(url)
    req.add_header('User-Agent','Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.97 Safari/537.36 X-Requested-With: XMLHttpRequest')
    response = urllib.request.urlopen(url)
    html = response.read()
    return html


def find_imgs(url):       #获取图片的完整url信息
    html = url_open(url).decode('utf-8')
    img_addrs = []
    a = html.find('img src=')

    while a != -1:
        b = html.find('.jpg',a,a+255)
        if b != -1:
            img_addrs.append("http://"+ html[a+11:b+4])  #注意这里需要添加拼接“http://”
        else:
            b = a + 11
        a = html.find('img src=',b)
    return img_addrs

def save_imgs(folder,img_addrs):  #保存图片
    for each in img_addrs:
        filename = each.split('/')[-1]
        with open(filename,'wb') as f:
            img = url_open(each)
            f.write(img)

def download_mm(folder='ooxx',pages=10):
    os.mkdir(folder)
    os.chdir(folder)

    for i in url_list:
        img_addrs = find_imgs(i)
        save_imgs(folder,img_addrs)

if __name__ == "__main__":
    download_mm()