1. """
    2. 需求:正则抓取糗事百科13页的所有图片
    3. """
    4. import requests
    5. import re
    6. import os
    7. if __name__ == '__main__':
    8. if not os.path.exists('糗图') :
    9. os.mkdir('糗图')
    10. headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/93.0.4577.63 Safari/537.36'}
    11. for page in range(1,14):
    12. url = f'https://www.qiushibaike.com/imgrank/page/{page}/'
    13. page_text = requests.get(url, headers=headers).text
    14. img_src_list = re.findall('<div class="thumb">.*?src="(.*?)" alt.*?</div>', page_text, re.S)
    15. for pic_url in img_src_list:
    16. pic_url = 'https:' + pic_url
    17. img_data = requests.get(pic_url, headers=headers).content
    18. filename = pic_url.split('/')[-1]
    19. with open('糗图/' + filename, 'wb') as f:
    20. f.write(img_data)
    21. print(filename, '下载完成')
    22. print(f'第{page}页已经下载完成!!!')
    23. print('所有图片已经下载完毕!!')
    24. """
    25. 总结:
    26. 01. 判断是否存在这个路径
    27. os.path.exists('路径')
    28. 02. 创建文件夹
    29. os.mkdir('文件夹名')
    30. """