Update for Nikkei Paper

[adonishi]

nikkei_news.recipe is no longer working. here is a patch for it.
please include this into calibre.
thank you.
( I also attached whole recipe )


--- calibre/recipes/nikkei_news.recipe 2011-08-28 01:05:34.184509000 +0900
+++ nikkei_news.recipe 2011-08-29 18:25:30.284952392 +0900
@@ -37,24 +37,24 @@
#br.set_debug_responses(True)

if self.username is not None and self.password is not None:
- print "----------------------------open top page----------------------------------------"
+ print "-------------------------open top page-------------------------------------"
br.open('http://www.nikkei.com/')
- print "----------------------------open first login form--------------------------------"
+ print "-------------------------open first login form-----------------------------"
link = br.links(url_regex="www.nikkei.com/etc/accounts/login").next()
br.follow_link(link)
#response = br.response()
#print response.get_data()
- print "----------------------------JS redirect(send autoPostForm)-----------------------"
+ print "-------------------------JS redirect(send autoPostForm)--------------------"
br.select_form(name='autoPostForm')
br.submit()
#response = br.response()
- print "----------------------------got login form---------------------------------------"
+ print "-------------------------got login form------------------------------------"
br.select_form(name='LA0210Form01')
br['LA0210Form01:LA0210Email'] = self.username
br['LA0210Form01:LA0210Password'] = self.password
br.submit()
#response = br.response()
- print "----------------------------JS redirect------------------------------------------"
+ print "-------------------------JS redirect---------------------------------------"
br.select_form(nr=0)
br.submit()

@@ -64,18 +64,23 @@
return br

def cleanup(self):
- print "----------------------------logout-----------------------------------------------"
+ print "-------------------------logout--------------------------------------------"
self.browser.open('https://regist.nikkei.com/ds/etc/accounts/logout')

def parse_index(self):
- print "----------------------------get index of paper-----------------------------------"
+ print "-------------------------get index of paper--------------------------------"
result = []
soup = self.index_to_soup('http://www.nikkei.com/paper/')
#soup = self.index_to_soup(self.test_data())
- for sect in soup.findAll('div', 'cmn-section kn-special JSID_baseSection'):
+ sections = soup.findAll('div', 'cmn-section kn-special JSID_baseSection')
+ if len(sections) == 0:
+ sections = soup.findAll('div', 'cmn-section kn-special')
+ for sect in sections:
sect_title = sect.find('h3', 'cmnc-title').string
sect_result = []
for elem in sect.findAll(attrs={'class':['cmn-article_title']}):
+ if elem.span.a == None or elem.span.a['href'].startswith('javascript') :
+ continue
url = 'http://www.nikkei.com' + elem.span.a['href']
url = re.sub("/article/", "/print-article/", url) # print version.
span = elem.span.a.span
@@ -84,6 +89,5 @@
sect_result.append(dict(title=title, url=url, date='',
description='', content=''))
result.append([sect_title, sect_result])
- #pp.pprint(result)
return result