Update Harvard Business Review

This commit is contained in:
Kovid Goyal 2013-09-12 15:28:40 +05:30
parent 3bbfb055e7
commit 54501ee576

View File

@ -39,10 +39,10 @@ class HBR(BasicNewsRecipe):
br.visit('https://hbr.org/login?request_url=/', timeout=20)
except Timeout:
pass
br.click('#accordion div[tabindex="0"]', wait_for_load=False)
f = br.select_form('#signin-form')
f['signin-form:username'] = username
f['signin-form:password'] = password
br.click('#form-wrapper h3[tabindex="0"]', wait_for_load=False)
f = br.select_form('#login-form')
f['username'] = username
f['password'] = password
br.submit(wait_for_load=False)
br.run_for_a_time(30)
@ -56,7 +56,8 @@ class HBR(BasicNewsRecipe):
articles = []
for x in soup.find(id='issueFeaturesContent').findAll(['li', 'h4']):
if x.name == 'h4':
if x.get('class', None) == 'basic':continue
if x.get('class', None) == 'basic':
continue
if current_section is not None and articles:
feeds.append((current_section, articles))
current_section = self.tag_to_string(x).capitalize()
@ -64,7 +65,8 @@ class HBR(BasicNewsRecipe):
self.log('\tFound section:', current_section)
else:
a = x.find('a', href=True)
if a is None: continue
if a is None:
continue
title = self.tag_to_string(a)
url = a['href']
if '/ar/' not in url: