python爬虫抓取MM图（www.mmjpg.com）

运行输入开始抓取的页面，及结束的页面即可（注：开始，结束页面在1-70之间，具体看www.mmjpg.com更新情况可以改变范围）

（只有不断练习才会上升，之前写过一个，忘得差不多了。这个写起来费力，毕竟才开始不久，还没哟视频，只有慢慢摸）

#!/usr/bin/env Python
#coding = utf-8
import urllib.request
import random
import os
import re
import parser

url = "http://www.mmjpg.com/"#主网站网址

def re_html(url):  #返回HTML的内容
    #创建opener
    iplist = ['183.62.71.242:3128', '157.0.32.175:8998', '180.110.18.111:808', '112.252.165.21:8889']
    proxy_support = urllib.request.ProxyHandler({'https':random.choice(iplist)})
    opener = urllib.request.build_opener(proxy_support)
    urllib.request.install_opener(opener)

    ''''''#修改header

    header = {}

    header["User-Agent"] = "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36"

    ''''''

    #获取HTML,返回HTML

    req = urllib.request.Request(url)

    req.add_header = ("User-Agent", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36")

    response = urllib.request.urlopen(req)

    html = response.read()

    return html

def html_dec(html):#解码

    return html.decode("utf-8")

def  get_main_img_adr(html):#获得单个图片地址及其图片数

    p = r'<div class=\"content\".+img src="(.+\.jpg)".+</div>'

    result = re.findall(p,html)

    p1 = r'<div class=\"page\".+>(.+)</a><em.+</div>'

    picture_num = re.findall(p1,html)

    packge = []

    packge.append(result[0])

    packge.append(picture_num[0])

    return packge

def try_it():#返回图片地址，和图片可扩展的张数，例如返回['http://img.mmjpg.com/2015/1/1.jpg', '33']，表示图片地址的最后一位数可更换为33一下任何数值，对应也就是图片的地址

    picture = []

    start_page = int(input("输入开始下载页:  "))

    end_page = int(input("输入停止下载页:  "))

    for e in range(start_page,end_page):

        url_copy = url

        url_copy = url + "/mm/" + str(e)

        html1 = re_html(url_copy)

        html2 = html_dec(html1)

        result = get_main_img_adr(html2)

        picture.append(result)

    print(picture)

    return picture

def down_img(picture):   #下载图片

    i = 1

    for e in picture:

        x = 1

        while x <= int(e[1]):

            with open(str(i)+".jpg","wb") as f:

                adr = e[0][:-5]+str(x)+e[0][-4:]

                print(adr)

                img = re_html(adr)

                f.write(img)

            x += 1

            i += 1

def catch_mm(folder = "mm", main_page = 3):#下载MM图片

    os.mkdir(folder)#创建文件夹

    os.chdir(folder)

    picture = try_it()#得到图片地址，返回的是元素为[图片网址，图片数]的列表

    down_img(picture)#读出列表中的每个元素，并下载下来

if __name__ == "__main__" :

    catch_mm()