简单爬虫入门

# get请求
import urllib.request
if __name__ == "__main__":
    response = urllib.request.urlopen("http://www.baidu.com")
    print(response.read().decode('utf-8'))
    
# post请求 
import urllib.request
if __name__ == "__main__":
    data = bytes(urllib.parse.urlencode({"name": "zero", "password": "123456"}), encoding='utf-8')
    response = urllib.request.urlopen("http://www.httpbin.org/post", data=data)
    print(response.read().decode('utf-8'))
    
# response  timeout    应用
import urllib.request
import urllib.error
if __name__ == "__main__": 
    try:
        data = bytes(urllib.parse.urlencode({"name": "zero", "password": "123456"}), encoding='utf-8')
        response = urllib.request.urlopen("http://www.httpbin.org/post", data=data, timeout=0.1)
        print(response.read().decode('utf-8'))
    except urllib.error.URLError as e:
        print(e.reason)
 #  获取response信息
import urllib.request
import urllib.error
if __name__ == "__main__": 
    try:
        data = bytes(urllib.parse.urlencode({'name': 'zero', 'password': '123456'}), encoding='utf-8')
        response = urllib.request.urlopen('http://www.httpbin.org/post', data=data, timeout=1)
        print(response.read().decode('utf-8'))
        print(response.status)
        print(response.getheaders())
        print(response.getheader('Server'))
    except urllib.error.URLError as e:
        print(e.reason)        

        
 # 模拟浏览器  
import urllib.request
import urllib.error
if __name__ == "__main__":
    header = {
        'User-Agent':
        'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:84.0) Gecko/20100101 Firefox/84.0'
    }
    url = 'https://www.douban.com/'
    req = urllib.request.Request(url, headers=header)
    response = urllib.request.urlopen(req)
    print(response.read().decode('utf-8'))