实现爬取图片

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(1,5):   # 事先知道一共有多少页，将参数修改即可
        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')
        length = len(element_list)   # 判断长度此处无用！
        leng = 0
        for element in element_list:
            url = element.attrs.get('src')[15:]
            url_detail = BASE_URL + url
            leng += 1
            name = title + '第{}张'.format(str(leng))
            save(url_detail,title,name)

# 文件夹下的名字有所区别  即风景图片/具体的标题/单个的图片.png，因此传name字段过去

import os
def save(url,title,name):
    base_url = '风景图片'
    file_path = os.path.join(base_url,title)
    if not os.path.exists(file_path):
        os.makedirs(file_path)

    file_path2 = os.path.join(file_path,name + '.png')
    r = session.get(url=url)

    with open(file_path2,'wb')as f:
        f.write(r.content)
    print('{}图片保存成功'.format(name))

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   前提是知道所有的图片长度不好弄
# from tqdm import tqdm
# import time
#
# pbar = tqdm(total=100,desc='michael')
# for i in range(100):
#     pbar.update(1)
#     time.sleep(0.05)
# pbar.close()