python 用socket向网页发送 GET 请求

web 客户端程序

'''
send request 'GET' to www.baidu.com
and save the receved content to a txt file
'''

from socket import *
import sys

header_send = b'GET / HTTP/1.1\r\nHost: www.baidu.com\r\nConnection: close\r\n\r\n'

HOST = 'www.baidu.com'
PORT = 80
BUFSIZ = 1024

# create a socket which support IPv4/IPv6
for res in getaddrinfo(HOST, PORT, AF_UNSPEC,
				SOCK_STREAM, 0, AI_PASSIVE):
	af, socktype, proto, canonname, sockaddr = res

	try:
		webClient = socket(af, socktype)
	except OSError as msg:
		webClient = None
		continue
	try:
		webClient.connect(sockaddr)
	except OSError as msg:
		webClient.close()
		webClient = None
		continue
	break

if webClient is None:
	print('could not open socket')
	sys.exit(1)

buf = []	# save the received content
with webClient:
	webClient.send(header_send)
	print('hugh')
	while True:
		recv = webClient.recv(BUFSIZ)	# bytes
#		print(recv)
		if recv:
			buf.append(recv.decode())
		else:
			break
	data = ''.join(buf).encode()	# list to str
	data = data.decode()

	print(data)
	# note "encoding = 'utf-8'", or it will raise UnicodeEncodeError
	with open('recv.txt', 'w', encoding = 'utf-8') as f:
		f.write(data)