From 4a6f674b2a5181e83fd6e216f20ac764e2e82119 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Thu, 15 Sep 2011 23:08:41 -0600 Subject: [PATCH] ... --- recipes/time_magazine.recipe | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) diff --git a/recipes/time_magazine.recipe b/recipes/time_magazine.recipe index 20942c209c..4b815bd7ce 100644 --- a/recipes/time_magazine.recipe +++ b/recipes/time_magazine.recipe @@ -15,12 +15,12 @@ class Time(BasicNewsRecipe): # ' publish complete articles on the web.') title = u'Time' __author__ = 'Kovid Goyal' - description = 'Weekly magazine' + description = ('Weekly US magazine.') encoding = 'utf-8' no_stylesheets = True language = 'en' remove_javascript = True - + #needs_subscription = 'optional' keep_only_tags = [ { @@ -41,6 +41,21 @@ class Time(BasicNewsRecipe): preprocess_regexps = [(re.compile( r''), lambda m:'')] + def get_browser(self): + br = BasicNewsRecipe.get_browser(self) + if False and self.username and self.password: + # This site uses javascript in its login process + res = br.open('http://www.time.com/time/magazine') + br.select_form(nr=1) + br['username'] = self.username + br['password'] = self.password + res = br.submit() + raw = res.read() + if '>Log Out<' not in raw: + raise ValueError('Failed to login to time.com, check' + ' your username and password') + return br + def parse_index(self): raw = self.index_to_soup('http://www.time.com/time/magazine', raw=True) root = html.fromstring(raw)