Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-08 02:34:06 -04:00
Code Issues Packages Projects Releases Wiki Activity

Fix People's Daily China

Browse Source
This commit is contained in:
Kovid Goyal 2012-01-21 21:33:24 +05:30
parent 89729ad3b0
commit 541b8cc368
1 changed files with 1 additions and 32 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

33
recipes/people_daily.recipe
View File

@ -12,6 +12,7 @@ class AdvancedUserRecipe1277129332(BasicNewsRecipe):
category = 'News, China' category = 'News, China'
remove_javascript = True remove_javascript = True
use_embedded_content = False use_embedded_content = False
auto_cleanup = True
no_stylesheets = True no_stylesheets = True
encoding = 'GB2312' encoding = 'GB2312'
conversion_options = {'linearize_tables':True} conversion_options = {'linearize_tables':True}
@ -21,37 +22,5 @@ class AdvancedUserRecipe1277129332(BasicNewsRecipe):
(u'\u7ecf\u6d4e\u65b0\u95fb', u'http://www.people.com.cn/rss/finance.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'\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')] (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