爬取照片
爬取一张照片
import urllib.request # 导入所需的库
url = "http://placekitten.com/500/600" # 要爬取的地址
r = urllib.request.urlopen(url) # 请求这个网址,得到数据
cat_ing = r.read() # 读取数据
with open("cat.jpg","wb") as f: # 写入数据
f.write(cat_ing) # 将图片保存
print("下载成功!")
爬取多张照片
import urllib.request # 导入所需的库
# 下载的图片的地址
urls = [
"http://kr.shanghai-jiuxin.com/file/2020/1031/191468637cab2f0206f7d1d9b175ac81.jpg",
"http://kr.shanghai-jiuxin.com/file/2020/1031/a2c58d6d726fb7ef29390becac5d8643.jpg",
"http://kr.shanghai-jiuxin.com/file/2020/1031/563337d07af599a9ea64e620729f367e.jpg"
]
# 下载照片
def down(url):
name = url.split("1031/", 1)[1]
r = urllib.request.urlopen(url)
img = r.read()
with open(name,"wb") as f:
f.write(img)
print("下载成功!")
for url in urls:
down(url)
这样还是有些麻烦
如果爬取这个网站所有的图片
import urllib.request
# 请求这个地址
url = "https://cn.bing.com/images/search?q=%e7%85%a7%e7%89%87&qpvt=%e7%85%a7%e7%89%87&form=IGRE&first=1&tsc=ImageBasicHover"
r = urllib.request.urlopen(url)
# 经过一系列操作得到的每一个照片地址,然后放到urls列表中
urls = []
# 下载照片
def down(url):
name = url.split("1031/", 1)[1]
r = urllib.request.urlopen(url)
img = r.read()
with open(name,"wb") as f:
f.write(img)
print("下载成功!")
for url in urls:
down(url)