1.简单获取网页单张图片:
2.拿取网页代码:
import requests
r = requests.get('http://www.kaotop.com/file/tupian/20220430/uyvkzZ.jpeg')
with open('图片.jpeg','wb') as f:
f.write(r.content)
f.close()
3.注意:有时获取的网页图片读不了时:
是因为网页反爬虫功能代码中需要添加:headers ={‘User-Agent’: 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) ’
‘Chrome/99.0.4844.84 Safari/537.36 OPR/85.0.4341.60’} #在网页检查代码内’控制台(console)'输入(window.navigator.userAgent)获取代码.
import requests
headers ={'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/99.0.4844.84 Safari/537.36 OPR/85.0.4341.60'}
r = requests.get('https://get.wallhere.com/photo/space-galaxy-planet-fantasy-'
'wallpaper-desktop-landscape-surreal-1579551.png')
with open('图片.png', 'wb') as f:
f.write(r.content)
f.close()
获取图片:
4.获取整个网页图片:
#解析网页;
获取代码:
import requests ,re
from bs4 import BeautifulSoup
def get_content(target):
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/99.0.4844.84 Safari/537.36 OPR/85.0.4341.60'}
r = requests.get(url = target,headers = headers)
textwrap = BeautifulSoup(r.content, 'lxml')
pictrues = textwrap.find('div', class_='hub-photomodal')
pictrues = pictrues.find_all('a')
for pictrue in pictrues:
response = requests.get(pictrue.get('href'))
return response
if __name__=='__main__':
headers ={'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/99.0.4844.84 Safari/537.36 OPR/85.0.4341.60'}
server = 'https://wallhere.com'
r = requests.get(server)
r.encoding = 'utf-8'
text = BeautifulSoup(r.text,'lxml')
picture_urls = text.find('div',class_ = 'hub-mediagrid hub-fleximages hub-loadphoto')
picture_urls = picture_urls .find_all('a')
# print(picture_urls )
for url in picture_urls:
urls = url.get('href')
# print(urls)
url_img = re.findall('wallpaper',urls)
# print(url_img)
# print(type(urls))
try:
if url_img[0] == 'wallpaper':
url = server + urls
# print(url)
else:
continue
except IndexError as e :
continue
response = get_content(url)
picture_r = requests.get(response)
with open('图片\%s' % (response.strip().split('-')[-1]), 'wb') as file:
file.write(picture_r.content)
file.close()
欢迎分享,转载请注明来源:内存溢出
评论列表(0条)