Last active
August 29, 2015 14:10
-
-
Save whiteclover/c194e4a4b3bc2a371c69 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import tornado.ioloop | |
import tornado.iostream | |
import socket | |
class WebRequest(object): | |
LINE_END = b'\r\n' | |
def __init__(self, host, port=80, callback=None): | |
self.host = host | |
self.port =port | |
self.headers = {} | |
self.data = '' | |
self.callback = callback | |
self.transfer = 'stream' | |
self.http_ver_with_status = '' | |
s = socket.socket(socket.AF_INET, socket.SOCK_STREAM, 0) | |
self.stream = tornado.iostream.IOStream(s) | |
self.stream.connect((self.host, self.port), self.send_request) | |
def send_request(self): | |
self.stream.write(b"GET / HTTP/1.0\r\nHost: %s\r\n\r\n" %self.host) | |
self.stream.read_until(self.LINE_END*2, self.on_headers) | |
def on_headers(self, data): | |
lines = data.split(self.LINE_END) | |
self.http_ver_with_status = lines.pop(0) | |
for line in lines: | |
parts = line.split(b":", 1) | |
if len(parts) == 2: | |
self.headers[parts[0].strip()] = parts[1].strip() | |
if 'Content-Length' in self.headers: | |
if int(self.headers[b"Content-Length"]) > 0: | |
self.transfer = 'content_length' | |
self.stream.read_bytes(int(self.headers[b"Content-Length"]), self.on_body) | |
else: | |
self.callback(self) | |
self.stream.close() | |
elif self.headers.get(b'Transfer-Encoding') == 'chunked': | |
self.transfer = 'chunked' | |
self.on_chunk() | |
else: | |
self.transfer = 'stream' | |
callback = lambda data: self.on_stream(data, True) | |
streaming_callback = lambda data: self.on_stream(data, False) | |
self.stream.read_until_close(callback, streaming_callback) | |
def on_body(self, data): | |
self.data += data | |
self.callback(self) | |
self.stream.close() | |
def on_chunk(self): | |
self.stream.read_until_regex(self.LINE_END, self.on_chunk_header) | |
def on_chunk_header(self, data): | |
data = data.strip(self.LINE_END) | |
length = int(data, 16) | |
if length > 0: | |
self.stream.read_bytes(length+len(self.LINE_END), self.on_chunk_data) | |
else: | |
self.stream.read_bytes(length+len(self.LINE_END), self.on_chunk_end) | |
def on_chunk_end(self, data): | |
self.callback(self) | |
self.stream.close() | |
def on_chunk_data(self, data): | |
self.data += data | |
self.on_chunk() | |
def on_stream(self, data, finish=False): | |
# do some thing | |
if finish: | |
self.data += data | |
self.callback(self) | |
self.stream.close() | |
else: | |
self.data += data | |
def callback(req): | |
print req.http_ver_with_status | |
print "Transfer :" , req.transfer | |
print "Headers: ", req.headers | |
#print "Data: ", req.data | |
req = WebRequest('cn.bing.com', 80, on_bing) | |
def on_bing(req): | |
print req.http_ver_with_status | |
print "Transfer :" , req.transfer | |
print "Headers: ", req.headers | |
#print "Data: ", req.data | |
tornado.ioloop.IOLoop.instance().stop() | |
if __name__ == '__main__': | |
req = WebRequest('www.baidu.com', 80, callback) | |
tornado.ioloop.IOLoop.instance().start() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment