head: fix .head and add response time
mutantmonkey
parent
9594c33266
commit
92ea5b5310
279
modules/head.py
279
modules/head.py
|
|
@ -7,7 +7,13 @@ Licensed under the Eiffel Forum License 2.
|
||||||
http://inamidst.com/phenny/
|
http://inamidst.com/phenny/
|
||||||
"""
|
"""
|
||||||
|
|
||||||
import re, urllib.request, urllib.parse, urllib.error, urllib.request, urllib.error, urllib.parse, http.client, urllib.parse, time, http.cookiejar
|
import re
|
||||||
|
import urllib.request
|
||||||
|
import urllib.parse
|
||||||
|
import urllib.error
|
||||||
|
import http.client
|
||||||
|
import http.cookiejar
|
||||||
|
import time
|
||||||
from html.entities import name2codepoint
|
from html.entities import name2codepoint
|
||||||
import web
|
import web
|
||||||
from tools import deprecated
|
from tools import deprecated
|
||||||
|
|
@ -17,55 +23,56 @@ opener = urllib.request.build_opener(urllib.request.HTTPCookieProcessor(cj))
|
||||||
urllib.request.install_opener(opener)
|
urllib.request.install_opener(opener)
|
||||||
|
|
||||||
def head(phenny, input):
|
def head(phenny, input):
|
||||||
"""Provide HTTP HEAD information."""
|
"""Provide HTTP HEAD information."""
|
||||||
uri = input.group(2)
|
uri = input.group(2)
|
||||||
uri = (uri or '')
|
uri = (uri or '')
|
||||||
if ' ' in uri:
|
if ' ' in uri:
|
||||||
uri, header = uri.rsplit(' ', 1)
|
uri, header = uri.rsplit(' ', 1)
|
||||||
else: uri, header = uri, None
|
else: uri, header = uri, None
|
||||||
|
|
||||||
if not uri and hasattr(phenny, 'last_seen_uri'):
|
if not uri and hasattr(phenny, 'last_seen_uri'):
|
||||||
try: uri = phenny.last_seen_uri[input.sender]
|
try: uri = phenny.last_seen_uri[input.sender]
|
||||||
except KeyError: return phenny.say('?')
|
except KeyError: return phenny.say('?')
|
||||||
|
|
||||||
if not uri.startswith('htt'):
|
if not uri.startswith('htt'):
|
||||||
uri = 'http://' + uri
|
uri = 'http://' + uri
|
||||||
# uri = uri.replace('#!', '?_escaped_fragment_=')
|
# uri = uri.replace('#!', '?_escaped_fragment_=')
|
||||||
|
|
||||||
|
start = time.time()
|
||||||
|
|
||||||
try: info = web.head(uri)
|
try:
|
||||||
except IOError: return phenny.say("Can't connect to %s" % uri)
|
info = web.head(uri)
|
||||||
except http.client.InvalidURL: return phenny.say("Not a valid URI, sorry.")
|
info['status'] = '200'
|
||||||
|
except urllib.error.HTTPError as e:
|
||||||
|
return phenny.say(str(e.code))
|
||||||
|
except http.client.InvalidURL:
|
||||||
|
return phenny.say("Not a valid URI, sorry.")
|
||||||
|
except IOError:
|
||||||
|
return phenny.say("Can't connect to %s" % uri)
|
||||||
|
|
||||||
if not isinstance(info, list):
|
resptime = time.time() - start
|
||||||
try: info = dict(info)
|
|
||||||
except TypeError:
|
|
||||||
return phenny.reply('Try .head http://example.org/ [optional header]')
|
|
||||||
info['Status'] = '200'
|
|
||||||
else:
|
|
||||||
newInfo = dict(info[0])
|
|
||||||
newInfo['Status'] = str(info[1])
|
|
||||||
info = newInfo
|
|
||||||
|
|
||||||
if header is None:
|
if header is None:
|
||||||
data = []
|
data = []
|
||||||
if 'Status' in info:
|
if 'Status' in info:
|
||||||
data.append(info['Status'])
|
data.append(info['Status'])
|
||||||
if 'content-type' in info:
|
if 'content-type' in info:
|
||||||
data.append(info['content-type'].replace('; charset=', ', '))
|
data.append(info['content-type'].replace('; charset=', ', '))
|
||||||
if 'last-modified' in info:
|
if 'last-modified' in info:
|
||||||
modified = info['last-modified']
|
modified = info['last-modified']
|
||||||
modified = time.strptime(modified, '%a, %d %b %Y %H:%M:%S %Z')
|
modified = time.strptime(modified, '%a, %d %b %Y %H:%M:%S %Z')
|
||||||
data.append(time.strftime('%Y-%m-%d %H:%M:%S UTC', modified))
|
data.append(time.strftime('%Y-%m-%d %H:%M:%S UTC', modified))
|
||||||
if 'content-length' in info:
|
if 'content-length' in info:
|
||||||
data.append(info['content-length'] + ' bytes')
|
data.append(info['content-length'] + ' bytes')
|
||||||
phenny.reply(', '.join(data))
|
data.append('{0:1.2f} s'.format(resptime))
|
||||||
else:
|
phenny.reply(', '.join(data))
|
||||||
headerlower = header.lower()
|
else:
|
||||||
if headerlower in info:
|
headerlower = header.lower()
|
||||||
phenny.say(header + ': ' + info.get(headerlower))
|
if headerlower in info:
|
||||||
else:
|
phenny.say(header + ': ' + info.get(headerlower))
|
||||||
msg = 'There was no %s header in the response.' % header
|
else:
|
||||||
phenny.say(msg)
|
msg = 'There was no %s header in the response.' % header
|
||||||
|
phenny.say(msg)
|
||||||
head.commands = ['head']
|
head.commands = ['head']
|
||||||
head.example = '.head http://www.w3.org/'
|
head.example = '.head http://www.w3.org/'
|
||||||
|
|
||||||
|
|
@ -74,118 +81,118 @@ r_entity = re.compile(r'&[A-Za-z0-9#]+;')
|
||||||
|
|
||||||
@deprecated
|
@deprecated
|
||||||
def f_title(self, origin, match, args):
|
def f_title(self, origin, match, args):
|
||||||
""".title <URI> - Return the title of URI."""
|
""".title <URI> - Return the title of URI."""
|
||||||
uri = match.group(2)
|
uri = match.group(2)
|
||||||
uri = (uri or '')
|
uri = (uri or '')
|
||||||
|
|
||||||
if not uri and hasattr(self, 'last_seen_uri'):
|
if not uri and hasattr(self, 'last_seen_uri'):
|
||||||
uri = self.last_seen_uri.get(origin.sender)
|
uri = self.last_seen_uri.get(origin.sender)
|
||||||
if not uri:
|
if not uri:
|
||||||
return self.msg(origin.sender, 'I need a URI to give the title of...')
|
return self.msg(origin.sender, 'I need a URI to give the title of...')
|
||||||
title = gettitle(uri)
|
title = gettitle(uri)
|
||||||
if title:
|
if title:
|
||||||
self.msg(origin.sender, origin.nick + ': ' + title)
|
self.msg(origin.sender, origin.nick + ': ' + title)
|
||||||
else: self.msg(origin.sender, origin.nick + ': No title found')
|
else: self.msg(origin.sender, origin.nick + ': No title found')
|
||||||
f_title.commands = ['title']
|
f_title.commands = ['title']
|
||||||
|
|
||||||
def noteuri(phenny, input):
|
def noteuri(phenny, input):
|
||||||
uri = input.group(1)
|
uri = input.group(1)
|
||||||
if not hasattr(phenny.bot, 'last_seen_uri'):
|
if not hasattr(phenny.bot, 'last_seen_uri'):
|
||||||
phenny.bot.last_seen_uri = {}
|
phenny.bot.last_seen_uri = {}
|
||||||
phenny.bot.last_seen_uri[input.sender] = uri
|
phenny.bot.last_seen_uri[input.sender] = uri
|
||||||
noteuri.rule = r'.*(http[s]?://[^<> "\x01]+)[,.]?'
|
noteuri.rule = r'.*(http[s]?://[^<> "\x01]+)[,.]?'
|
||||||
noteuri.priority = 'low'
|
noteuri.priority = 'low'
|
||||||
|
|
||||||
titlecommands = r'(?:' + r'|'.join(f_title.commands) + r')'
|
titlecommands = r'(?:' + r'|'.join(f_title.commands) + r')'
|
||||||
def snarfuri(phenny, input):
|
def snarfuri(phenny, input):
|
||||||
if re.match(r'(?i)' + phenny.config.prefix + titlecommands, input.group()):
|
if re.match(r'(?i)' + phenny.config.prefix + titlecommands, input.group()):
|
||||||
return
|
return
|
||||||
uri = input.group(1)
|
uri = input.group(1)
|
||||||
title = gettitle(uri)
|
title = gettitle(uri)
|
||||||
if title:
|
if title:
|
||||||
phenny.msg(input.sender, '[ ' + title + ' ]')
|
phenny.msg(input.sender, '[ ' + title + ' ]')
|
||||||
snarfuri.rule = r'.*(http[s]?://[^<> "\x01]+)[,.]?'
|
snarfuri.rule = r'.*(http[s]?://[^<> "\x01]+)[,.]?'
|
||||||
snarfuri.priority = 'low'
|
snarfuri.priority = 'low'
|
||||||
|
|
||||||
def gettitle(uri):
|
def gettitle(uri):
|
||||||
if not ':' in uri:
|
if not ':' in uri:
|
||||||
uri = 'http://' + uri
|
uri = 'http://' + uri
|
||||||
uri = uri.replace('#!', '?_escaped_fragment_=')
|
uri = uri.replace('#!', '?_escaped_fragment_=')
|
||||||
|
|
||||||
title = None
|
title = None
|
||||||
localhost = [
|
localhost = [
|
||||||
'http://localhost/', 'http://localhost:80/',
|
'http://localhost/', 'http://localhost:80/',
|
||||||
'http://localhost:8080/', 'http://127.0.0.1/',
|
'http://localhost:8080/', 'http://127.0.0.1/',
|
||||||
'http://127.0.0.1:80/', 'http://127.0.0.1:8080/',
|
'http://127.0.0.1:80/', 'http://127.0.0.1:8080/',
|
||||||
'https://localhost/', 'https://localhost:80/',
|
'https://localhost/', 'https://localhost:80/',
|
||||||
'https://localhost:8080/', 'https://127.0.0.1/',
|
'https://localhost:8080/', 'https://127.0.0.1/',
|
||||||
'https://127.0.0.1:80/', 'https://127.0.0.1:8080/',
|
'https://127.0.0.1:80/', 'https://127.0.0.1:8080/',
|
||||||
]
|
]
|
||||||
for s in localhost:
|
for s in localhost:
|
||||||
if uri.startswith(s):
|
if uri.startswith(s):
|
||||||
return phenny.reply('Sorry, access forbidden.')
|
return phenny.reply('Sorry, access forbidden.')
|
||||||
|
|
||||||
try:
|
try:
|
||||||
redirects = 0
|
redirects = 0
|
||||||
while True:
|
while True:
|
||||||
info = web.head(uri)
|
info = web.head(uri)
|
||||||
|
|
||||||
if not isinstance(info, list):
|
if not isinstance(info, list):
|
||||||
status = '200'
|
status = '200'
|
||||||
else:
|
else:
|
||||||
status = str(info[1])
|
status = str(info[1])
|
||||||
info = info[0]
|
info = info[0]
|
||||||
if status.startswith('3'):
|
if status.startswith('3'):
|
||||||
uri = urllib.parse.urljoin(uri, info['Location'])
|
uri = urllib.parse.urljoin(uri, info['Location'])
|
||||||
else: break
|
else: break
|
||||||
|
|
||||||
redirects += 1
|
redirects += 1
|
||||||
if redirects >= 25:
|
if redirects >= 25:
|
||||||
|
return None
|
||||||
|
|
||||||
|
try: mtype = info['content-type']
|
||||||
|
except:
|
||||||
return None
|
return None
|
||||||
|
if not (('/html' in mtype) or ('/xhtml' in mtype)):
|
||||||
|
return None
|
||||||
|
|
||||||
try: mtype = info['content-type']
|
bytes = web.get(uri)
|
||||||
except:
|
#bytes = u.read(262144)
|
||||||
return None
|
#u.close()
|
||||||
if not (('/html' in mtype) or ('/xhtml' in mtype)):
|
|
||||||
return None
|
|
||||||
|
|
||||||
bytes = web.get(uri)
|
except IOError:
|
||||||
#bytes = u.read(262144)
|
return
|
||||||
#u.close()
|
|
||||||
|
|
||||||
except IOError:
|
m = r_title.search(bytes)
|
||||||
return
|
if m:
|
||||||
|
title = m.group(1)
|
||||||
|
title = title.strip()
|
||||||
|
title = title.replace('\t', ' ')
|
||||||
|
title = title.replace('\r', ' ')
|
||||||
|
title = title.replace('\n', ' ')
|
||||||
|
while ' ' in title:
|
||||||
|
title = title.replace(' ', ' ')
|
||||||
|
if len(title) > 200:
|
||||||
|
title = title[:200] + '[...]'
|
||||||
|
|
||||||
|
def e(m):
|
||||||
|
entity = m.group(0)
|
||||||
|
if entity.startswith('&#x'):
|
||||||
|
cp = int(entity[3:-1], 16)
|
||||||
|
return chr(cp)
|
||||||
|
elif entity.startswith('&#'):
|
||||||
|
cp = int(entity[2:-1])
|
||||||
|
return chr(cp)
|
||||||
|
else:
|
||||||
|
char = name2codepoint[entity[1:-1]]
|
||||||
|
return chr(char)
|
||||||
|
title = r_entity.sub(e, title)
|
||||||
|
|
||||||
m = r_title.search(bytes)
|
if title:
|
||||||
if m:
|
title = title.replace('\n', '')
|
||||||
title = m.group(1)
|
title = title.replace('\r', '')
|
||||||
title = title.strip()
|
else: title = None
|
||||||
title = title.replace('\t', ' ')
|
return title
|
||||||
title = title.replace('\r', ' ')
|
|
||||||
title = title.replace('\n', ' ')
|
|
||||||
while ' ' in title:
|
|
||||||
title = title.replace(' ', ' ')
|
|
||||||
if len(title) > 200:
|
|
||||||
title = title[:200] + '[...]'
|
|
||||||
|
|
||||||
def e(m):
|
|
||||||
entity = m.group(0)
|
|
||||||
if entity.startswith('&#x'):
|
|
||||||
cp = int(entity[3:-1], 16)
|
|
||||||
return chr(cp)
|
|
||||||
elif entity.startswith('&#'):
|
|
||||||
cp = int(entity[2:-1])
|
|
||||||
return chr(cp)
|
|
||||||
else:
|
|
||||||
char = name2codepoint[entity[1:-1]]
|
|
||||||
return chr(char)
|
|
||||||
title = r_entity.sub(e, title)
|
|
||||||
|
|
||||||
if title:
|
|
||||||
title = title.replace('\n', '')
|
|
||||||
title = title.replace('\r', '')
|
|
||||||
else: title = None
|
|
||||||
return title
|
|
||||||
|
|
||||||
if __name__ == '__main__':
|
if __name__ == '__main__':
|
||||||
print(__doc__.strip())
|
print(__doc__.strip())
|
||||||
|
|
|
||||||
Loading…
Reference in New Issue