import urllib.request
import urllib.parse
#获取一个get请求
response=urllib.request.urlopen("http://www.baidu.com")
print(response.read().decode('utf-8'))
常用get or POST
import urllib.request
import urllib.parse
#获取post请求
#封装一个data
data=bytes(urllib.parse.urlencode({"hello":"world"}),encoding="utf-8")
response=urllib.request.urlopen("https://httpbin.org/post",data=data)
print(response.read().decode("utf-8"))
#超时处理
try:
response = urllib.request.urlopen("https://httpbin.org/get",timeout=0.01)
print(response.read().decode("utf-8"))
except urllib.error.URLError as e:
print("time out!")
测试网站:
https://httpbin.org/post
一般只需要headers & url
url="https://httpbin.org/post"
headers={
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.164 Safari/537.36"
}
data=bytes(urllib.parse.urlencode({'name':'Erica'}),encoding="utf-8")
#用一个函数存储数据:
req=urllib.request.Request(url=url,data=data,headers=headers,method="POST")
response=urllib.request.urlopen(req)
print(response.read().decode("utf-8"))
用lofter 首页测试
爬取成功
url="http://www.lofter.com/view?act=qbview_20130930_01"
headers={
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.164 Safari/537.36"
}
req=urllib.request.Request(url=url,headers=headers)
response=urllib.request.urlopen(req)
print(response.read().decode("utf-8"))
任务中,
写一个爬取豆瓣电影TOP250的第一页的函数
def main():
askURL("https://movie.douban.com/top250?start=0")
def askURL(url):
head={"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.164 Safari/537.36"
#模拟浏览器,向豆瓣服务器发送消息
}
request=urllib.request.Request(url,headers=head)
html=""
try:
response=urllib.request.urlopen(request)
html=response.read().decode("utf-8")
print(html)
except urllib.error.URLError as e:
if hasattr(e,"code"):
print(e.code)
if hasattr(e,"reason"):
print(e.reason)
if __name__=="__main__":
main()