实现爬取图片

参考网址：https://www.ivsky.com/

from requests_html import HTMLSession


session = HTMLSession()

BASE_URL = 'https://www.ivsky.com'

# 获取图片页码链接

def get_page_url():
    for i in  range(1,21):
        yield 'https://www.ivsky.com/tupian/ziranfengguang/index_{}.html'.format(i)


#　获取总图的链接 ==》》 单个图的所有

# 测试：
# r = session.get(url='https://www.ivsky.com/tupian/ziranfengguang/index_1.html')
#
# BASE_URL = 'https://www.ivsky.com'
# element_list = r.html.find('.il_img a')
# for element in element_list:
#     # print(element.attrs.get('href'))
#     a_url = BASE_URL + element.attrs.get('href')
#     print(a_url)
#     title = element.attrs.get('title')
#     # 进入到具体的图片内部
#     h = session.get(url=a_url)
#     element_list = h.html.find('.il_img img')
#     for element in element_list:
#         url = element.attrs.get('src')[15:]
#         url_detail = BASE_URL + url
#         print(url_detail)

def get_url_page(url):
    r = session.get(url=url)
    element_list = r.html.find('.il_img a')
    for element in element_list:
        a_url = BASE_URL + element.attrs.get('href')
        title = element.attrs.get('title')
        # 进入到具体的图片内部
        h = session.get(url=a_url)
        element_list = h.html.find('.il_img img')
        for element in element_list:
            url = element.attrs.get('src')[15:]
            url_detail = BASE_URL + url
            save(url_detail,title)

import os
def save(url,title):
    base_url = '风景图片'
    file_path = os.path.join(base_url,title+'.png')
    r = session.get(url=url)
    with open(file_path,'wb')as f:
        f.write(r.content)
    print('{}图片保存成功'.format(title))

if __name__ == '__main__':
    for page_url in get_page_url():
        get_url_page(page_url)


# 可以考虑单行打印进度条