mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
58 lines
2.3 KiB
Plaintext
58 lines
2.3 KiB
Plaintext
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
class AdvancedUserRecipe1277129332(BasicNewsRecipe):
|
|
title = u'People Daily - China'
|
|
oldest_article = 2
|
|
max_articles_per_feed = 100
|
|
__author__ = 'rty'
|
|
|
|
pubisher = 'people.com.cn'
|
|
description = 'People Daily Newspaper'
|
|
language = 'zh'
|
|
category = 'News, China'
|
|
remove_javascript = True
|
|
use_embedded_content = False
|
|
no_stylesheets = True
|
|
encoding = 'GB2312'
|
|
conversion_options = {'linearize_tables':True}
|
|
|
|
feeds = [(u'\u56fd\u5185\u65b0\u95fb', u'http://www.people.com.cn/rss/politics.xml'),
|
|
(u'\u56fd\u9645\u65b0\u95fb', u'http://www.people.com.cn/rss/world.xml'),
|
|
(u'\u7ecf\u6d4e\u65b0\u95fb', u'http://www.people.com.cn/rss/finance.xml'),
|
|
(u'\u4f53\u80b2\u65b0\u95fb', u'http://www.people.com.cn/rss/sports.xml'),
|
|
(u'\u53f0\u6e7e\u65b0\u95fb', u'http://www.people.com.cn/rss/haixia.xml')]
|
|
keep_only_tags = [
|
|
dict(name='div', attrs={'class':'left_content'}),
|
|
]
|
|
remove_tags = [
|
|
dict(name='table', attrs={'class':'title'}),
|
|
]
|
|
remove_tags_after = [
|
|
dict(name='table', attrs={'class':'bianji'}),
|
|
]
|
|
|
|
def append_page(self, soup, appendtag, position):
|
|
pager = soup.find('img',attrs={'src':'/img/next_b.gif'})
|
|
if pager:
|
|
nexturl = self.INDEX + pager.a['href']
|
|
soup2 = self.index_to_soup(nexturl)
|
|
texttag = soup2.find('div', attrs={'class':'left_content'})
|
|
#for it in texttag.findAll(style=True):
|
|
# del it['style']
|
|
newpos = len(texttag.contents)
|
|
self.append_page(soup2,texttag,newpos)
|
|
texttag.extract()
|
|
appendtag.insert(position,texttag)
|
|
|
|
|
|
def preprocess_html(self, soup):
|
|
mtag = '<meta http-equiv="content-type" content="text/html;charset=GB2312" />\n<meta http-equiv="content-language" content="utf-8" />'
|
|
soup.head.insert(0,mtag)
|
|
for item in soup.findAll(style=True):
|
|
del item['form']
|
|
self.append_page(soup, soup.body, 3)
|
|
#pager = soup.find('a',attrs={'class':'ab12'})
|
|
#if pager:
|
|
# pager.extract()
|
|
return soup
|