Pytho中urllib的简单应用

简单爬取网页内容

# encoding = 'utf-8'
import urllib.request
import urllib.parse #解析

# Get请求
# response = urllib.request.urlopen("http://www.baidu.com")
# print(response.read().decode('utf-8'))


'''
# Post
data = bytes(urllib.parse.urlencode({"User":"Password"}), encoding = 'utf-8')
response = urllib.request.urlopen("http://httpbin.org/post", data = data)
print(response.read().decode("utf-8"))
'''

# try :
# 	response = urllib.request.urlopen("http://httpbin.org/get", timeout = 3)
# 	print(response.read().decode("utf-8"))
# except urllib.error.URLError as e : 
# 	print("timeout") # 超时处理


# 响应头
# response = urllib.request.urlopen("http://www.baidu.com", timeout = 3)
# print(response.getheader("Server")) # 状态码 200 404 

# 伪装浏览器

'''
# url = "http://www.douban.com"
url = "http://httpbin.org/post"
headers = {
	"User-Agent" : "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.61 Safari/537.36"
}
data = bytes(urllib.parse.urlencode({"name":"eric"}), encoding = 'utf-8')
req = urllib.request.Request(url = url, data = data, headers = headers, method = "POST")
response = urllib.request.urlopen(req)
print(response.read().decode('utf-8'))
'''

url = "http://81.68.109.40:30004/"
headers = {
	"User-Agent" : "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.61 Safari/537.36"
}
req = urllib.request.Request(url = url, headers = headers)
response = urllib.request.urlopen(req)
print(response.read().decode("utf-8"))