Bufferme

Bufferme.py

# -*- coding: utf-8 -*-
#!/usr/bin/env python

# Coded poorly by Brett Kelly
# http://nerdgap.com
# @inkedmn

# -*- coding: utf-8 -*-
import urllib2 
import urllib 
import re 
import clipboard 
import urlparse 
import notification 
import webbrowser
import requests
from bs4 import BeautifulSoup
import sys
import traceback

# Sent to Buffer between title and url
post_sep = "" 

def de_utmise(a):
	b = urlparse.urlparse(a)
	c = urlparse.parse_qs(b.query)

	non_utm = [
		c.pop(i, None) for i in c.keys()
		if re.match(r'^utm', i)
	]
	d = urllib.urlencode(c)
	x = urlparse.urlunparse([b.scheme, b.netloc, b.path, b.params, d, b.fragment])
	return x

def makeBufferUrl(url, title):
	"""Cobble together the Buffer URL containing our datums"""
	# em dashes avoid escaping in the quote() call, so
	# maybe we just get rid of them.
	if '—' in title:
		title = title.replace('—', '—')
	title = title.replace('»', '—')
	if title is None:
		title = "[no title]"
	title += post_sep
	nt = "\n\n« %s »\n" % (title)
	out = "bufferapp://"
	# UTF-8 encode and escape the page title
	t = urllib.quote(nt.encode('utf-8'), safe='')
	out += "?t=%s" % t
	# Escape the URL
	u = urllib.quote(url, safe='')
	out += "&u=%s" % u
	return out

# Grab url (or whatever) from the clipboard
u = clipboard.get()


# this won't throw an exception ever, apparently:
# http://docs.python.org/2/library/urlparse.html
parts = urlparse.urlparse(u)

if parts.scheme not in ['http', 'https']:
	# Not the droid we're looking for
	# Notify the user and exit.
	notification.schedule("Clipboard is not a URL")
	print u
	print 
	raise SystemExit	

else:
	# Yes, yes, I know. Parsing HTML with regexes is stupid.
	# It's ok because I'm not a real programmer.
	p = re.compile("<title>(.*)</title>", re.IGNORECASE|re.DOTALL)
	try:
		# open and read the web page
		u = de_utmise(u)
		r = requests.get(u)
		h = r.text
		try:
			soup = BeautifulSoup(h)
			t = soup.title
			if t is None:
				t = "<no title>"
			else:
				t = t.string
			print t
		except Exception, e:
			t = "(no title somehow)"
		
		# r = urllib2.urlopen(clipboard.get())
		# h = r.read()
		# find and extract the title
		# t = p.search(h).group(1)
		# construct the buffer URL
		burl = makeBufferUrl(u, t.strip())
		# open the Buffer URL (opens the Buffer app)
		webbrowser.open(burl)
	except Exception, e:
		# Something pooped the bed opening or reading the URL
		# This could either print this generic message
		# or just spit out whatever was on the clipboard.
		print u
		print e
		print '[Title Unavailable]'
		t_, v_, tb_ = sys.exc_info()
		traceback.format_exc(tb_)