Download Google Reader feeds.

greader.py

# -*- coding: utf-8 -*-
import requests
import urllib, time, sys
import string

def filename_string(feed):
	valid_chars = "-_() %s%s" % (string.ascii_letters, string.digits)
	return ''.join(c for c in feed if c in valid_chars)

def save(feed):
	page = 0
	while True:
		page += 1

		gurl = 'http://www.google.es/reader/api/0/stream/contents/feed/%s' % urllib.quote_plus(feed)
		params = {
			'r': 'n',
			'n': '20',
			'ck': int(time.time()),
			'client': 'scroll'
		}
		if (page > 1) and next:
			params['n'] = 40
			params['c'] = next

		try:
			r = requests.get(gurl, params=params)
			if (r.status_code == 404):
				print '    [Fail] Este feed no está en Google Reader'
				break
			j = r.json()
		except requests.RequestException:
			print 'Error (RequestException)'
			sys.exit()
		except ValueError:
			print 'Error (JSON)'
			sys.exit()

		filename = '%s-%s.json' % (filename_string(feed), str(page).zfill(2))
		with open(filename, 'w') as f:
			f.write(r.content)

		if not 'continuation' in j:
			print '    [Ok] %s archivo(s) descargado(s)' % page
			break
		else:
			next = j['continuation']

try:
	feeds = open('feeds.txt').read().splitlines()
except IOError:
	print 'No se ha podido cargar la lista de feeds en feeds.txt'
	sys.exit()

for feed in feeds:
	if (not feed) or (feed[0] == '#'):
		continue
	print '* Descargando %s' % feed
	save(feed)