Python 图片采集 Python爬虫入门案例之回车桌面壁纸网美女图片采集

import requests     # 第三方库 pip install requests
import parsel       # 第三方库 pip install parsel
import os           # 新建文件夹

response = requests.get('https://mm.enterdesk.com/bizhi/64011-348522.html')

data_html = response_1.text

selector_1 = parsel.Selector(data_html)
photo_url_list = selector_1.css('.egeli_pic_dl dd a::attr(href)').getall()
title_list = selector_1.css('.egeli_pic_dl dd a img::attr(title)').getall()
for photo_url, title in zip(photo_url_list, title_list):
    print(f'*****************正在爬取{title}*****************')
    response = requests.get(photo_url)
    # <Response [200]>: 请求成功的标识
    selector = parsel.Selector(response.text)
    # 提取想要的图片链接[第一个链接, 第二个链接,....]
    img_src_list = selector.css('.swiper-wrapper a img::attr(src)').getall()
    # 新建一个文件夹
    if not os.path.exists('img/' + title):
        os.mkdir('img/' + title)

for img_src in img_src_list:
    # 字符串的替换
    img_url = img_src.replace('_360_360', '_source')

# 图片 音频 视频 二进制数据content
img_data = requests.get(img_url).content
# 图片名称 字符串分割
# 分割完之后 会给我们返回一个列表
img_title = img_url.split('/')[-1]
with open(f'img/{title}/{img_title}', mode='wb') as f:
    f.write(img_data)
print(img_title, '保存成功!!!')

page_html = requests.get('https://mm.enterdesk.com/').text
counts = parsel.Selector(page_html).css('.wrap.no_a::attr(href)').get().split('/')[-1].split('.')[0]
for page in range(1, int(counts) + 1):
    print(f'------------------------------------正在爬取第{page}页------------------------------------')
    发送网络请求
    response_1 = requests.get(f'https://mm.enterdesk.com/{page}.html')