Geek Answers Handbook

Convert HTTP (string) headers to python dictionary

Is there a standard function that converts HTTP headers to a python dictionary, and another one for conversion?

Of course, they will need to maintain a summary of the headers.

+7
source share
5 answers

Instead of creating my own sockets, etc., I would use httplib . Thus, they will receive data from the http server and analyze the headers in a dictionary for example.

import httplib
conn = httplib.HTTPConnection("www.python.org")
conn.request("GET", "/index.html")
r1 = conn.getresponse()

dict = r1.getheaders()
print(dict)

gives

[('content-length', '16788'), ('accept-range', 'bytes'), ('server', 'Apache/2.2.9 (Debian) DAV/2 SVN/1.5.1 mod_ssl/2.2.9 OpenSSL/0.9.8g mod_wsgi/2.5 Python/2.5.2 '), (' last-modified ',' Mon, 15 Feb 2010 07:30:46 GMT '), (' etag ',' "105800d-4194-47f9e9871d580" '), (' date ',' Mon, 15 Feb 2010 21:34:18 GMT '), (' content-type ',' text/html ')]

.

+5

- , , , :

def fold(header):
  line = "%s: %s" % (header[0], header[1])
  if len(line) < 998: 
    return line
  else: #fold
    lines = [line]
    while len(lines[-1]) > 998:
      split_this = lines[-1]
      #find last space in longest chunk admissible
      split_here = split_this[:998].rfind(" ")
      del lines[-1]
      lines = lines + [split_this[:split_here]),
                       split_this[split_here:])] #this may still be too long
                                                 #hence the while on lines[-1]
    return "\n".join(lines)

def dict2header(data):
  return "\n".join((fold(header) for header in data.items()))

def header2dict(data):
  data = data.replace("\n ", " ").splitlines()
  headers = {}
  for line in data:
    split_here = line.find(":")
    headers[line[:split_here]] = line[split_here:]
  return headers
+4

, ,

+1

, 2010 , , . , dict.

getheaders , dict -, , , :

import httplib
conn = httplib.HTTPConnection("www.python.org")
conn.request("GET", "/index.html")
response = conn.getresponse()

headers = dict(response.getheaders())
print(headers)

:

{'content-length': '18891', 'accept-range': 'bytes', 'server': 'Apache/2.2.16 (Debian)', 'last-modified': 'Mon, 30 May 2011 19:50:25 GMT ',' etag ':' "105800d-49cb-4a48399368240" ',' date ':' , 30 2011 21:29:32 GMT ',' content-type ':' text/HTML '}

, headers.items().

+1

:

import re
req_line = re.compile(r'(?P<method>GET|POST)\s+(?P<resource>.+?)\s+(?P<version>HTTP/1.1)')
field_line = re.compile(r'\s*(?P<key>.+\S)\s*:\s+(?P<value>.+\S)\s*')

def parse(http_post):
    first_line_end = http_post.find('\n')
    headers_end = http_post.find('\n\n')
    request = req_line.match(
        http_post[:first_line_end]
    ).groupdict()
    headers = dict(
        field_line.findall(
            http_post[first_line_end:headers_end]
        )
    )
    body = http_post[headers_end + 2:]
    return request, headers, body
0

More articles:


All Articles