MMpa一pa

最新的某131网站精美套图爬取代码出炉，截至2020年4月13日有效，之后就不知道啦。
来，各位看客老爷们可以搞一下：

import requests
import json
import re
import time
import os

def find_img_src(html):    #这个函数其实没用到
    replace_pattern = r'<[meta|META].*?/>' 
    img_url_pattern = r'.+?content="(\S+)"' 
    img_url_list = []
    need_replace_list = re.findall(replace_pattern, html)
    for tag in need_replace_list:
        img_url_list.append(re.findall(img_url_pattern, tag))    
    return img_url_list

def find_set_span(html):
    paging_pattern = r'<div class="paging".*?</div>'
    span_pattern = r'<span.*?</span>'
    need_paging_list = re.findall(paging_pattern,html)
    # print(need_paging_list)
    for span_statement in need_paging_list:
        need_span_list = re.findall(span_pattern,span_statement)
        # print(need_span_list)
    final_pattern = r'>.*?<'
    span_number = re.findall(final_pattern,need_span_list[0])
    return (int(span_number[0][3:5]))

headers = {
    "User-Agent": "Mozilla/5.0",
    "referer":"https://m.mm131.net",
    "Host":"m.mm131.net",
}   

for i in range(5300,5350):     #这个套数ID数可以自己测试
    time.sleep(2)
    main_url = "https://m.mm131.net/xinggan/"+str(i)+".html"
    response = requests.get(main_url,headers = headers)
    if response.status_code == 200:
        try:
            # print(find_img_src(response.content.decode("gb2312"))[3],end="")     #返回url列表
            span_number = find_set_span(response.text)
            print(main_url, end="")
            print("  此套图页数："+str(span_number))
        except:
            print("  网页解码异常")

        #创建文件夹
        pic_path = r'D:\******\WWW\photo\mm131\%d' % (i)
        isExists = os.path.exists(pic_path)
        if not isExists:
            os.makedirs(pic_path)
            print(pic_path + "   创建成功")

            #爬取图片
            for sequence in range(1, span_number + 1):
                if sequence == 1:
                    referer_url = "https://m.mm131.net/xinggan/" + str(i) + ".html"
                else:
                    referer_url = "https://m.mm131.net/xinggan/" + str(i) + "_" + str(sequence) + ".html"
                # print("referer: "+referer_url + "    ", end="")
                pic_headers = {
                    "User-Agent": "Mozilla/5.0",
                    "referer": referer_url,
                    "host": "img1.mmmw.net",
                }
                img_url = "https://img1.mmmw.net/pic/" + str(i) + "/" + str(sequence) + ".jpg"
                # print("img_url:  "+img_url,end="")

                #下载图片
                pic_response = requests.get(img_url,headers = pic_headers)
                time.sleep(0.5)
                if (pic_response.content!=None):
                    open(r'D:\******\WWW\photo\mm131\%d\%d.jpg' % (i,sequence),'wb').write(pic_response.content)  # 将内容写入图片
                    # print("   图片已写入")
        else:
            print(pic_path + "  目录已存在")
    else:
        print(main_url+"  访问错误")