[Python知识库]python爬取“唯一图库-＞美图“前11页高清大图代码

import os
import requests
from lxml import etree
page = 1
while page <= 11:
    url = f"https://www.mmonly.cc/mmtp/qcmn/list_16_{page}.html"
    page+=1
    headers = {
        "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36"
    }
    response = requests.get(url,headers=headers)
    picture_html_str = response.content.decode("gbk")
    picture_html = etree.HTML(picture_html_str)
    picture_root = picture_html.xpath(".//div[@class='item masonry_brick masonry-brick']")
    for picture in picture_root:
        # time.sleep(2)
        #文件名
        dir_name = picture.xpath(".//div[@class='title']/span/a/text()")[0]
        #图片地址
        picture_adr = picture.xpath(".//div[@class='title']//a/@href")[0]
        #获取该类图片数位置
        picture_num_adr_str = picture.xpath(".//div[@class='items_likes']/text()")
        #对获取该位置的文本进行格式化
        picture_num_str = "".join(picture_num_adr_str).split("共")[-1]
        #获取该图片数量
        picture_num = int(picture_num_str.split("张")[0])
        # 创建目录
        try:
            os.mkdir(f"D:/图片及视频/图片/爬虫/{dir_name}")
        except Exception as e:
            print(e)
        #为防止第二次循环出现地址追加固定前部分地址字符
        picture_adr_fix = picture_adr[:-5]
        for i in range(picture_num):
            #获取每一种图的所有图链接
            img_response = requests.get(picture_adr, headers=headers)
            #每种图的地址
            picture_adr = picture_adr_fix + f"_{i+2}.html"
            img_html_str = img_response.content.decode("gbk")
            img_html = etree.HTML(img_html_str)
            # 获取图片的url
            img_url = img_html.xpath(".//div[@id='big-pic']//img/@src")[0]
            with open(f"D:/图片及视频/图片/爬虫/{dir_name}/{i}.jpg","wb") as f:
                f.write(requests.get(img_url).content)