简单爬取京东商品信息
iimport requests
try:
url="https://item.jd.com/100008348542.html"
kv={'user-agent':'Mozilla/5.0'}
r=requests.get(url,headers=kv)
r.raise_for_status()
r.enciding=r.apparent_encoding
print(r.text[1000:2000])
print(r.request.headers)
except:
print( "产生异常")
爬取百度搜索信息
try:
keyword="Python"
kv={'wd':keyword}
r=requests.get("http://www.baidu.com/s",params=kv)
print(r.request.url)
r.raise_for_status()
print(len(r.text))
except:
print("爬取失败")
爬取国家地图图片
import os
url="https://www.nationalgeographic.com/animals/2020/07/lynx-long-journeys-mountains-alaska-canada/#/lynx-mather-03.jpg"
root="E//"
path=root+url.split("/")[-1]
try:
if not os.path.exists(root):
os.mkdir(root)
if not os.path.exists(path):
r=requests.get(url)
with open(path,"wb") as f:
f.write(r.content)
f.close()
print("文件保存成功")
else:
print("文件已存在")
except:
print("爬取失败")
部分来自北京理工大学-嵩天的爬虫课程