python爬取可爱女生图片

爬虫学的好，私货少不了

• 复习金融学实属无聊，思想开了点小差，巧了，最近正好在学爬虫，很快啊，漂亮小姐姐们嗖嗖嗖的跑到小的地文件夹来啦!
• 爬取mz图片链接: https://sc.chinaz.com/tupian/xingganmeinvtupian.html
• 因为临近考试秃头夜，这里就不细说啦，具体看下面代码啦!

import urllib.request
import urllib.parse
from lxml import etree
import time
import os


def handle_request(url, page):
    # 构造url
    # 由于第一页和后面的页码规律不一样，所有进行判断
    if (page == 1) or (page == 0):
        # 页面位1或0时的链接
        # https://sc.chinaz.com/tupian/xingganmeinvtupian.html
        url = url.format('')
    else:
        # 其余链接
        # https://sc.chinaz.com/tupian/xingganmeinvtupian_2.html
        url = url.format('_' + str(page))
    # print(url)
    # ua伪装
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.149 Safari/537.36',
        'Cookie': 'UM_distinctid=172bafc075930f-0b3214295ea2fd-f313f6d-1fa400-172bafc075a521; __gads=ID=7343205fec19267e:T=1592274993:S=ALNI_MZuCx78VBx2WBiIEBOXsKZoldvefg'

    }
    # 发起请求
    request = urllib.request.Request(url=url, headers=headers)
    return request


# 解析内容，下载图片
def parse_content(content):
    # 将内容转化位xpath能抓取的对象
    tree = etree.HTML(content)
    # 抓取图片列表
    # //*[@id="container"]/div[2]/div/a/img
    image_list = tree.xpath('//div[@id="container"]/div/div/a/img/@src2')  # 懒加载技术  可视区只有那么大，只要图片出现在眼前，就会加载
    # 实现方式:
    # <img  src2=<"图片路径"> 通过js代码动态添加<img src = "图片路径",src2="">
    for image_src in image_list:
        download_image(image_src)


def download_image(image_src):
    dirpath = '站长美女图片爬取'
    # 创建文件夹
    if not os.path.exists(dirpath):
        os.mkdir(dirpath)
    # 搞个文件名
    filename = os.path.basename(image_src)
    print(filename)
    # 搞图片路径
    filepath = os.path.join(dirpath, filename)
    print(filepath)
    # 发送请求保存图片
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.149 Safari/537.36',
        'Cookie': 'UM_distinctid=172bafc075930f-0b3214295ea2fd-f313f6d-1fa400-172bafc075a521; __gads=ID=7343205fec19267e:T=1592274993:S=ALNI_MZuCx78VBx2WBiIEBOXsKZoldvefg'

    }
    # https://sc.chinaz.com/tupian/201228241995.htm
    # 进行拼接
    image_src = 'https:' + image_src
    # 像美女图片发起请求
    request = urllib.request.Request(url=image_src, headers=headers)
    # 获取响应
    response = urllib.request.urlopen(request)
    # 以二进制的形式保存下来
    with open(filepath, 'wb') as fp:
        print(f'正在爬取{filename}')
        fp.write(response.read())
        print(f'{filename}爬取完毕')
        time.sleep(2)


def main():
    url = 'http://sc.chinaz.com/tupian/xingganmeinvtupian{}.html'
    start_page = int(input('请输入起始页码:'))
    end_page = int(input('请输入结束页码:'))

    for page in range(start_page, end_page + 1):
        request = handle_request(url, page)
        print('开始爬取第{}页'.format(page))
        response = urllib.request.urlopen(request)
        content = response.read().decode()
        # print(content)
        parse_content(content)
        print('第{}页爬取结束'.format(page))


if __name__ == '__main__':
    start = time.time()
    main()
    print('蜘蛛结网完毕，收工')
    end = time.time()
    print(f'爬取所有妹子图片用时: {end-start}s')

• 爬取程序运行部分结果如下所示:

• 在这个星球上，你很重要，请珍惜你的珍贵! ~~~夜斗小神社