把url更换为百度图片搜索结果的网站,就可以随意所欲地爬虫啦~
from urllib.request import *
import re
url="https://image.baidu.com/search/index?tn=baiduimage&ipn=r&ct=201326592&cl=2&lm=-1&st=-1&fm=result&fr=&sf=1&fmq=1585380918056_R&pv=&ic=0&nc=1&z=&hd=&latest=©right=&se=1&showtab=0&fb=0&width=&height=&face=0&istype=2&ie=utf-8&sid=&word=%E6%88%90%E9%83%BD"
html=urlopen(url)
obj=html.read().decode()
urls=re.findall(r'"objURL":"(.*?)"',obj)
index=0
for url in urls:
try:
print("downloading...%d"%index)
urlretrieve(url,'pic'+str(index)+'.jpg')
index+=1
except Exception:
print("download error...%d"%index)
else:
print("download complete...")
这里我们以搜索“成都”为例,效果如图所示:
还在心动什么?快来试试吧!!!