python（爬虫实战2）xpath唯一图库

从今天开始就要撸起袖子，直接写Python爬虫了，学习语言最好的办法就是有目的的进行，所以，本着美女是学习动力的第一原则，啊哈哈。写个程序把妹子们都下载下来吧。

福利时刻
妹子图片质量整体上还是不错呦，放两张不同风格的图大家感受下，O(∩_∩)O哈哈~


爬取结果

完整代码如下：

import re, os, requests, time
from lxml import etree
from mytool.randomUA import get_ua
from mytool.requests_plus import request_ssr



def mian():
    for page in range(1, 2):
        url = f"https://www.mmonly.cc/mmtp/qcmn/list_16_{page}.html"
        response = request_ssr(url, headers=get_ua())
        if response:
            html = response.content.decode("gbk")
            root = etree.HTML(html)
            div_list = root.xpath("//div[@id='infinite_scroll']/div[@class='item masonry_brick masonry-brick']")
            print(len(div_list))
            data_list = []
            for div in div_list:
                detail_url = div.xpath(".//div[@class='ABox']/a/@href")[0]
                title = div.xpath(".//div[@class='title']/span/a/text()")[0]
                data = {}
                data["detail_url"] = detail_url
                data["title"] = title
                data_list.append(data)
            detail(page, data_list)

    # 第二层首页面信息


def detail(page, data_list):
    for data in data_list:
        detail_url = data["detail_url"]
        title = data["title"]
        title = re.sub("[/\\\"\s]", "", title)
        os.makedirs(f"./{title}", exist_ok=True)
        print("创建目录：", f"./{title}")
        headers = {
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36"
        }
        response = request_ssr(detail_url, headers=headers)
        if response:
            detail_html = response.content.decode("gbk")
            root = etree.HTML(detail_html)
            img_url = root.xpath("//div[@id='big-pic']//img/@src")[0]
            total_page_num = root.xpath("//span[@class='totalpage']/text()")[0]
            print("当前下载链接：", img_url)
            with open(f"./{title}/1.jpg", "wb") as f:
                response = request_ssr(img_url, headers=headers)
                if response:
                    f.write(response.content)
        for i in range(2, int(total_page_num) + 1):
            next_url = detail_url[:-5] + f"_{i}.html"
            response = request_ssr(next_url, headers=headers)
            if response:
                detail_html = response.content.decode("gbk")
                root = etree.HTML(detail_html)
                img_url = root.xpath("//div[@id='big-pic']//img/@src")[0]
                print("当前下载链接：", img_url)
                with open(f"./{title}/{i}.jpg", "wb") as f:
                    response = request_ssr(img_url, headers=headers)
                    if response:
                        f.write(response.content)


if __name__ == '__main__':
    mian()

好了，今天的一个简单的爬虫成了