def main(index):#1、写url地址main_url = 'http://www.mmjpg.com/mm/%s' % index#2、获取翻页地址，写一个get_page()函数page = get_page(main_url)if os.path.exists(path) != True:os.mkdir(path) #创建工作目录#print(path)else:os.chdir(path) #切换到工作目录#3、遍历所有页，获取图片的地址for i in range(1, int(page) + 1):url = '%s/%s' % (main_url, i)try:get_img(url)  #获取图片地址except Exception as e:raise e

1、用网页检查拿到1570的html
''''<li><a href="http://www.mmjpg.com/mm/1570" target="_blank">切出来1570这个数字'''
#获取http://www.mmjpg.com/mm/1570的index:如：1570，1569
def get_index():#2、获取网页的htmlr = requests.get('http://www.mmjpg.com', headers=headers)r.encoding = 'utf-8'html = r.text#3、etree.HTML():构造了一个XPath解析对象并对HTML文本进行自动修正。#etree.tostring()：输出修正后的结果，类型是bytesselector = etree.HTML(html)#4、获取<li><a标签下的内容，[0]取第一个content = selector.xpath('//li/a')[0]#5、继续取href的内容，[0]取第一个：即：http://www.mmjpg.com/mm/1570num = content.xpath('@href')[0]#6、已斜杠为切片，获取不同的字符，即：['http:', '', 'www.mmjpg.com', 'mm', '1570']num = num.split('/')#7、取num最后一个字符，并强制转换成整形num = int(num[-1])#返回所有的index:1570,1569return range(1, num + 1)# for each in range(1,num+1):#     print(each)

#1、鼠标放到翻页的1上面右键检查，得到以下内容
'''
<div class="page" id="page"><em class="ch preno">没有了</em><em>1</em><a href="/mm/1570/2">2</a><a href="/mm/1570/3">3</a><a href="/mm/1570/4">4</a><a href="/mm/1570/5">5</a><a href="/mm/1570/6">6</a><i></i><a href="/mm/1570/50">50</a><em class="ch all" id="opic" οnclick="openall(1);">全部图片</em><a href="/mm/1570/2" class="ch next">下一张</a></div>
'''
def get_page(url):r = requests.get(url, headers=headers)r.encoding = 'utf-8'html = r.textselector = etree.HTML(html)#2、获取所有页：1、2...50、下一页，即获取下面<a>2<a>的2，3，4，5，6...50page = selector.xpath('//div[@id="page"]/a/text()')[-2]

#1、鼠标放到图片上，右键检查，获取以下内容
'''
<div class="content" id="content"><a href="http://www.mmjpg.com/mm/1570/2"><img src="http://fm.shiyunjj.com/2018/1570/1i28.jpg" data-img="http://fm.shiyunjj.com/2018/1570/1i28.jpg" alt="萌味十足的小尤奈雪白胴体相当性感"></a>
</div>
'''
#通过图片的地址来获取图片
def get_img(url):r = requests.get(url, headers=headers)r.encoding = 'utf-8'html = r.textselector = etree.HTML(html)try:#2、取img标签下的内容content = selector.xpath('//div[@id="content"]/a/img')[0]#3、获取图片url地址img_url = content.xpath('@src')[0]#4、取图片名字title = content.xpath('@alt')[0]#5、 #保存标题和对应的url地址
        sav_img(title, img_url) except Exception as e:print('Erro!!!')pass        

if __name__ == '__main__':indexs = get_index()#reversed()函数是返回序列seq的反向访问的迭代子,因为get_index()返回的是1570，1569，1568这样的序列，反向就是从1568，1569，1570for index in reversed(indexs):main(index)

import requests
import os
from lxml import etreeheaders = {'Referer': 'http://www.mmjpg.com/mm/','User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.186 Safari/537.36'
}#返回当前进程的工作目录
path = os.getcwd() + '\img'def get_index():r = requests.get('http://www.mmjpg.com',headers = headers)r.encoding= 'utf-8'html = r.textselector = etree.HTML(html)content = selector.xpath('//li/a')[0]num = content.xpath('@href')[0]num = num.split('/')num = int(num[-1])return range(1,num+1)def get_page(url):r = requests.get(url,headers=headers)r.encoding = 'utf-8'html = r.textselector = etree.HTML(html)page = selector.xpath('//div[@id="page"]/a/text()')[-2]return (page)def get_img(url):r = requests.get(url,headers=headers)r.encoding = 'utf-8'html = r.textselector = etree.HTML(html)try:content = selector.xpath('//div[@id = "content"]/a/img')[0]img_url = content.xpath('@src')[0]title = content.xpath('@alt')[0]save_img(title,img_url)except Exception as e:print('Erro!!!')passdef save_img(name,url):name = name + '.jpg'if name in os.listdir(path):print('重复文件')else:r = requests.get(url,headers=headers)with open(name,'wb') as f:f.write(r.content)print(name)def main(index):main_url = 'http://www.mmjpg.com/mm/%s'%indexpage = get_page(main_url)if os.path.exists(path)!= True:os.mkdir(path)else:os.chdir(path)for i in range(1,int(page)+1):url = '%s/%s'%(main_url,i)try:get_img(url)except Exception as e:raise eif __name__ == '__main__':index = get_index()for index in reversed(index):main(index)