Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-31 14:33:54 -04:00
Code Issues Packages Projects Releases Wiki Activity

Fix Nikkei News

Browse Source
This commit is contained in:
Kovid Goyal 2011-08-29 09:32:40 -06:00
parent d68ff1ebc1
commit cf18272419
1 changed files with 13 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
recipes/nikkei_news.recipe
View File

@ -37,24 +37,24 @@ class NikkeiNet_paper_subscription(BasicNewsRecipe):
#br.set_debug_responses(True) #br.set_debug_responses(True)
if self.username is not None and self.password is not None: 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/') 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() link = br.links(url_regex="www.nikkei.com/etc/accounts/login").next()
br.follow_link(link) br.follow_link(link)
#response = br.response() #response = br.response()
#print response.get_data() #print response.get_data()
print "----------------------------JS redirect(send autoPostForm)-----------------------" print "-------------------------JS redirect(send autoPostForm)--------------------"
br.select_form(name='autoPostForm') br.select_form(name='autoPostForm')
br.submit() br.submit()
#response = br.response() #response = br.response()
print "----------------------------got login form---------------------------------------" print "-------------------------got login form------------------------------------"
br.select_form(name='LA0210Form01') br.select_form(name='LA0210Form01')
br['LA0210Form01:LA0210Email'] = self.username br['LA0210Form01:LA0210Email'] = self.username
br['LA0210Form01:LA0210Password'] = self.password br['LA0210Form01:LA0210Password'] = self.password
br.submit() br.submit()
#response = br.response() #response = br.response()
print "----------------------------JS redirect------------------------------------------" print "-------------------------JS redirect---------------------------------------"
br.select_form(nr=0) br.select_form(nr=0)
br.submit() br.submit()
@ -64,18 +64,23 @@ class NikkeiNet_paper_subscription(BasicNewsRecipe):
return br return br
def cleanup(self): def cleanup(self):
print "----------------------------logout-----------------------------------------------" print "-------------------------logout--------------------------------------------"
self.browser.open('https://regist.nikkei.com/ds/etc/accounts/logout') self.browser.open('https://regist.nikkei.com/ds/etc/accounts/logout')
def parse_index(self): def parse_index(self):
print "----------------------------get index of paper-----------------------------------" print "-------------------------get index of paper--------------------------------"
result = [] result = []
soup = self.index_to_soup('http://www.nikkei.com/paper/') soup = self.index_to_soup('http://www.nikkei.com/paper/')
#soup = self.index_to_soup(self.test_data()) #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_title = sect.find('h3', 'cmnc-title').string
sect_result = [] sect_result = []
for elem in sect.findAll(attrs={'class':['cmn-article_title']}): 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 = 'http://www.nikkei.com' + elem.span.a['href']
url = re.sub("/article/", "/print-article/", url) # print version. url = re.sub("/article/", "/print-article/", url) # print version.
span = elem.span.a.span span = elem.span.a.span
@ -84,6 +89,5 @@ class NikkeiNet_paper_subscription(BasicNewsRecipe):
sect_result.append(dict(title=title, url=url, date='', sect_result.append(dict(title=title, url=url, date='',
description='', content='')) description='', content=''))
result.append([sect_title, sect_result]) result.append([sect_title, sect_result])
#pp.pprint(result)
return result return result