Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

recipe: update yomiuri onlie world

Browse Source 
Signed-off-by: Hiroshi Miura <miurahr@linux.com>
This commit is contained in:
Hiroshi Miura 2014-05-06 23:16:13 +09:00
parent 521a8f93c1
commit 4bb290657d
2 changed files with 53 additions and 44 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

43
recipes/yomiuri.recipe
View File

@ -1,5 +1,5 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2010, Hiroshi Miura <miurahr@linux.com>' __copyright__ = '2010,2014, Hiroshi Miura <miurahr@linux.com>'
''' '''
www.yomiuri.co.jp www.yomiuri.co.jp
''' '''
@ -16,16 +16,13 @@ class YOLNews(BasicNewsRecipe):
publisher = 'Yomiuri Online News' publisher = 'Yomiuri Online News'
category = 'news, japan' category = 'news, japan'
language = 'ja' language = 'ja'
encoding = 'Shift_JIS' encoding = 'UTF-8'
index = 'http://www.yomiuri.co.jp/latestnews/' index = 'http://www.yomiuri.co.jp/latestnews/'
remove_javascript = True remove_javascript = True
masthead_title = u'YOMIURI ONLINE' masthead_title = u'YOMIURI ONLINE'
keep_only_tags = [{'class':"article-def"}]
remove_tags = [{'class':"RelatedArticle"}, keep_only_tags = [{'class':"article text-resizeable"}]
{'class':"sbtns"}
]
remove_tags_after = {'class':"date-def"}
def parse_feeds(self): def parse_feeds(self):
feeds = BasicNewsRecipe.parse_feeds(self) feeds = BasicNewsRecipe.parse_feeds(self)
@ -42,22 +39,22 @@ class YOLNews(BasicNewsRecipe):
def parse_index(self): def parse_index(self):
feeds = [] feeds = []
newsarticles = []
soup = self.index_to_soup(self.index) soup = self.index_to_soup(self.index)
topstories = soup.find('ul',attrs={'class':'list-def'}) listlatest = soup.find('ul', attrs={'class':'list-common list-common-latest'})
if topstories: if listlatest:
newsarticles = [] for itt in listlatest.findAll('li'):
for itt in topstories.findAll('li'): itema = itt.find('a',href=True)
itema = itt.find('a',href=True) if itema:
if itema: item_headline = itema.find('span',attrs={'class':'headline'})
itd1 = itema.findNextSibling(text = True) item_date = item_headline.find('span',attrs={'class':'update'})
itd2 = itd1.findNextSibling(text = True) newsarticles.append({
itd3 = itd2.findNextSibling(text = True) 'title' :item_headline.contents[0]
newsarticles.append({ ,'date' :item_date
'title' :itema.string ,'url' :itema['href']
,'date' :''.join([itd1, itd2, itd3]) ,'description':''
,'url' :'http://www.yomiuri.co.jp' + itema['href'] })
,'description':'' feeds.append(('latest', newsarticles))
})
feeds.append(('latest', newsarticles))
return feeds return feeds

54
recipes/yomiuri_world.recipe
View File

@ -1,5 +1,5 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2010, Hiroshi Miura <miurahr@linux.com>' __copyright__ = '2010,2014, Hiroshi Miura <miurahr@linux.com>'
''' '''
www.yomiuri.co.jp www.yomiuri.co.jp
''' '''
@ -16,16 +16,12 @@ class YOLNews(BasicNewsRecipe):
publisher = 'Yomiuri Online News' publisher = 'Yomiuri Online News'
category = 'news, japan' category = 'news, japan'
language = 'ja' language = 'ja'
encoding = 'Shift_JIS' encoding = 'UTF-8'
index = 'http://www.yomiuri.co.jp/world/' index = 'http://www.yomiuri.co.jp/world/'
remove_javascript = True remove_javascript = True
masthead_title = u"YOMIURI ONLINE" masthead_title = u"YOMIURI ONLINE"
keep_only_tags = [{'class':"article-def"}] keep_only_tags = [{'class':"article text-resizeable"}]
remove_tags = [{'class':"RelatedArticle"},
{'class':"sbtns"}
]
remove_tags_after = {'class':"date-def"}
def parse_feeds(self): def parse_feeds(self):
feeds = BasicNewsRecipe.parse_feeds(self) feeds = BasicNewsRecipe.parse_feeds(self)
@ -42,20 +38,36 @@ class YOLNews(BasicNewsRecipe):
def parse_index(self): def parse_index(self):
feeds = [] feeds = []
newsarticles = []
soup = self.index_to_soup(self.index) soup = self.index_to_soup(self.index)
topstories = soup.find('ul',attrs={'class':'list-def'}) mainspan = soup.find('div', attrs={'class':'pbNested span-main-inr'})
if topstories: if mainspan:
newsarticles = [] topstories = mainspan.find('ul',attrs={'class':'list-top'})
for itt in topstories.findAll('li'): if topstories:
itema = itt.find('a',href=True) for itt in topstories.findAll('li'):
if itema: itema = itt.find('a',href=True)
itd1 = itema.findNextSibling(text = True) if itema:
newsarticles.append({ item_headline = itema.find('span',attrs={'class':'headline'})
'title' :itema.string item_date = item_headline.find('span',attrs={'class':'update'})
,'date' :''.join([itd1]) newsarticles.append({
,'url' :'http://www.yomiuri.co.jp' + itema['href'] 'title' :item_headline.contents[0]
,'description':'' ,'date' :item_date
}) ,'url' :itema['href']
feeds.append(('World', newsarticles)) ,'description':''
})
secondstories = mainspan.find('ul', attrs={'class':'list-common'})
if secondstories:
for itt in secondstories.findAll('li'):
itema = itt.find('a',href=True)
if itema:
item_headline = itema.find('span',attrs={'class':'headline'})
item_date = item_headline.find('span',attrs={'class':'update'})
newsarticles.append({
'title' :item_headline.contents[0]
,'date' :item_date
,'url' :itema['href']
,'description':''
})
feeds.append(('World', newsarticles))
return feeds return feeds