Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 10:14:46 -04:00
Code Issues Packages Projects Releases Wiki Activity

recipe: fix japanese recipes

Browse Source 
- mainichi news: handle ad pages
  - yomiuri: remove table tag
  - nikkei life: reduce feeds
This commit is contained in:
Hiroshi Miura 2010-12-03 00:43:59 +09:00
parent d41c66094e
commit 9c025f4736
5 changed files with 34 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
resources/recipes/mainichi.recipe
View File

@ -4,6 +4,7 @@ __copyright__ = '2010, Hiroshi Miura <miurahr@linux.com>'
www.mainichi.jp
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe
class MainichiDailyNews(BasicNewsRecipe):
@ -22,3 +23,18 @@ class MainichiDailyNews(BasicNewsRecipe):
remove_tags = [{'class':"RelatedArticle"}]
remove_tags_after = {'class':"Credit"}
def parse_feeds(self):
feeds = BasicNewsRecipe.parse_feeds(self)
for curfeed in feeds:
delList = []
for a,curarticle in enumerate(curfeed.articles):
if re.search(r'pheedo.jp', curarticle.url):
delList.append(curarticle)
if len(delList)>0:
for d in delList:
index = curfeed.articles.index(d)
curfeed.articles[index:index+1] = []
return feeds

16
resources/recipes/mainichi_it_news.recipe
View File

@ -14,5 +14,19 @@ class MainichiDailyITNews(BasicNewsRecipe):
remove_tags_before = {'class':"NewsTitle"}
remove_tags = [{'class':"RelatedArticle"}]
remove_tags_after = {'class':"Credit"}
def parse_feeds(self):
feeds = BasicNewsRecipe.parse_feeds(self)
for curfeed in feeds:
delList = []
for a,curarticle in enumerate(curfeed.articles):
if re.search(r'pheedo.jp', curarticle.url):
delList.append(curarticle)
if len(delList)>0:
for d in delList:
index = curfeed.articles.index(d)
curfeed.articles[index:index+1] = []
return feeds remove_tags_after = {'class':"Credit"}

5
resources/recipes/nikkei_sub_life.recipe
View File

@ -32,12 +32,9 @@ class NikkeiNet_sub_life(BasicNewsRecipe):
remove_tags_after = {'class':"cmn-pr_list"}
feeds = [ (u'\u304f\u3089\u3057', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=kurashi'),
(u'\u30b9\u30dd\u30fc\u30c4', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=sports'),
(u'\u793e\u4f1a', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=shakai'),
(u'\u30a8\u30b3', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=eco'),
(u'\u5065\u5eb7', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=kenkou'),
(u'\u7279\u96c6', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=special'),
(u'\u30e9\u30f3\u30ad\u30f3\u30b0', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=ranking')
(u'\u7279\u96c6', u'http://www.zou3.net/php/rss/nikkei2rss.php?head=special')
]
def get_browser(self):

2
resources/recipes/yomiuri.recipe
View File

@ -21,7 +21,7 @@ class YOLNews(BasicNewsRecipe):
remove_javascript = True
masthead_title = u'YOMIURI ONLINE'
remove_tags_before = {'class':"article-def"}
keep_only_tags = [{'class':"article-def"}]
remove_tags = [{'class':"RelatedArticle"},
{'class':"sbtns"}
]

2
resources/recipes/yomiuri_world.recipe
View File

@ -21,7 +21,7 @@ class YOLNews(BasicNewsRecipe):
remove_javascript = True
masthead_title = u"YOMIURI ONLINE"
remove_tags_before = {'class':"article-def"}
keep_only_tags = [{'class':"article-def"}]
remove_tags = [{'class':"RelatedArticle"},
{'class':"sbtns"}
]