calibre/recipes/cnetjapan.recipe
2019-04-13 09:17:31 +05:30

53 lines
1.8 KiB
Plaintext

import re
from calibre.web.feeds.news import BasicNewsRecipe
class CNetJapan(BasicNewsRecipe):
title = u'CNET Japan'
oldest_article = 3
max_articles_per_feed = 30
__author__ = 'Hiroshi Miura'
feeds = [(u'CNet News', u'http://feed.japan.cnet.com/rss/index.rdf'),
(u'CNet Blog', u'http://feed.japan.cnet.com/rss/blog/index.rdf')
]
language = 'ja'
encoding = 'utf-8'
remove_javascript = True
preprocess_regexps = [
(re.compile(type(u'')(r'<!--\u25B2contents_left END\u25B2-->.*</body>'), re.DOTALL | re.IGNORECASE | re.UNICODE),
lambda match: '</body>'),
(re.compile(r'<!--AD_ELU_HEADER-->.*</body>', re.DOTALL | re.IGNORECASE),
lambda match: '</body>'),
(re.compile(type(u'')(r'<!-- \u25B2\u95A2\u9023\u30BF\u30B0\u25B2 -->.*<!-- \u25B2ZDNet\u25B2 -->'), re.UNICODE),
lambda match: '<!-- removed -->'),
]
remove_tags_before = dict(id="contents_l")
remove_tags = [
{'class': "social_bkm_share"},
{'class': "social_bkm_print"},
{'class': "block20 clearfix"},
dict(name="div", attrs={'id': 'bookreview'}),
{'class': "tag_left_ttl"},
{'class': "tag_right"}
]
remove_tags_after = {'class': "block20"}
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