import requests
import bs4
import urllib.request
url = "http://www.ligui.org/aiss/"
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.80 Safari/537.36'}
def get_page():
response = requests.get(url, headers=headers)
html = response.text
return html
def page_parse(html):
soup = bs4.BeautifulSoup(html, 'lxml')
imgs = soup.find('ul', class_='img')
imgs_list = imgs.find_all('li')
i = 1
for img_list in imgs_list:
img = img_list.find('a').find('img')['src']
urllib.request.urlretrieve(img,'G:\python\爬虫实战\images\\' + str(i) + '.png')
i += 1
def main():
html = get_page()
page_parse(html)
if __name__ == '__main__':
main()
爬虫实战11:爬取aiss图片并保存
最新推荐文章于 2024-01-08 01:30:37 发布