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

Updated zaobao

Browse Source
This commit is contained in:
Kovid Goyal 2010-06-25 02:42:24 -06:00
parent 5f41fde25f
commit 4e4a69cdc5
1 changed files with 39 additions and 29 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

68
resources/recipes/zaobao.recipe
View File

@ -15,22 +15,22 @@ class ZAOBAO(BasicNewsRecipe):
no_stylesheets = True no_stylesheets = True
recursions = 1 recursions = 1
language = 'zh' language = 'zh'
encoding = 'gbk' encoding = 'gbk'
# multithreaded_fetch = True # multithreaded_fetch = True
keep_only_tags = [ keep_only_tags = [
dict(name='table', attrs={'cellpadding':'9'}), dict(name='td', attrs={'class':'text'}),
dict(name='table', attrs={'class':'cont'}),
dict(name='div', attrs={'id':'content'}),
dict(name='span', attrs={'class':'page'}), dict(name='span', attrs={'class':'page'}),
dict(name='div', attrs={'id':'content'})
] ]
remove_tags = [ remove_tags = [
dict(name='table', attrs={'cellspacing':'9'}), dict(name='table', attrs={'cellspacing':'9'}),
dict(name='fieldset'),
dict(name='div', attrs={'width':'30%'}),
] ]
extra_css = '\ extra_css = '\n\
@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)}\n\ @font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)}\n\
body{font-family: serif1, serif}\n\ body{font-family: serif1, serif}\n\
.article_description{font-family: serif1, serif}\n\ .article_description{font-family: serif1, serif}\n\
@ -41,7 +41,10 @@ class ZAOBAO(BasicNewsRecipe):
.article {font-size:medium}\n\ .article {font-size:medium}\n\
.navbar {font-size: small}\n\ .navbar {font-size: small}\n\
.feed{font-size: medium}\n\ .feed{font-size: medium}\n\
.small{font-size: small; padding-right: 8%}\n' .small{font-size: small;padding-right: 8pt}\n\
.text{padding-right: 8pt}\n\
p{text-indent: 0cm}\n\
div#content{padding-right: 10pt}'
INDEXES = [ INDEXES = [
(u'\u65b0\u95fb\u56fe\u7247', u'http://www.zaobao.com/photoweb/photoweb_idx.shtml') (u'\u65b0\u95fb\u56fe\u7247', u'http://www.zaobao.com/photoweb/photoweb_idx.shtml')
@ -51,27 +54,35 @@ class ZAOBAO(BasicNewsRecipe):
DESC_SENSE = u'\u8054\u5408\u65e9\u62a5\u7f51' DESC_SENSE = u'\u8054\u5408\u65e9\u62a5\u7f51'
feeds = [ feeds = [
(u'\u5373\u65f6\u62a5\u9053', u'http://realtime.zaobao.com/news.xml'), (u'\u5373\u65f6\u62a5\u9053', u'http://realtime.zaobao.com/news.xml'),
(u'\u4e2d\u56fd\u65b0\u95fb', u'http://www.zaobao.com/zg/zg.xml'), (u'\u4e2d\u56fd\u65b0\u95fb', u'http://www.zaobao.com/zg/zg.xml'),
(u'\u56fd\u9645\u65b0\u95fb', u'http://www.zaobao.com/gj/gj.xml'), (u'\u56fd\u9645\u65b0\u95fb', u'http://www.zaobao.com/gj/gj.xml'),
(u'\u4e16\u754c\u62a5\u520a\u6587\u8403', u'http://www.zaobao.com/wencui/wencui.xml'), (u'\u4e16\u754c\u62a5\u520a\u6587\u8403', u'http://www.zaobao.com/wencui/wencui.xml'),
(u'\u4e1c\u5357\u4e9a\u65b0\u95fb', u'http://www.zaobao.com/yx/yx.xml'), (u'\u4e1c\u5357\u4e9a\u65b0\u95fb', u'http://www.zaobao.com/yx/yx.xml'),
(u'\u65b0\u52a0\u5761\u65b0\u95fb', u'http://www.zaobao.com/sp/sp.xml'), (u'\u65b0\u52a0\u5761\u65b0\u95fb', u'http://www.zaobao.com/sp/sp.xml'),
(u'\u4eca\u65e5\u89c2\u70b9', u'http://www.zaobao.com/yl/yl.xml'), (u'\u4eca\u65e5\u89c2\u70b9', u'http://www.zaobao.com/yl/yl.xml'),
(u'\u4e2d\u56fd\u8d22\u7ecf', u'http://www.zaobao.com/cz/cz.xml'), (u'\u4e2d\u56fd\u8d22\u7ecf', u'http://www.zaobao.com/cz/cz.xml'),
(u'\u72ee\u57ce\u8d22\u7ecf', u'http://www.zaobao.com/cs/cs.xml'), (u'\u72ee\u57ce\u8d22\u7ecf', u'http://www.zaobao.com/cs/cs.xml'),
(u'\u5168\u7403\u8d22\u7ecf', u'http://www.zaobao.com/cg/cg.xml'), (u'\u5168\u7403\u8d22\u7ecf', u'http://www.zaobao.com/cg/cg.xml'),
(u'\u65e9\u62a5\u4f53\u80b2', u'http://www.zaobao.com/ty/ty.xml'), (u'\u65e9\u62a5\u4f53\u80b2', u'http://www.zaobao.com/ty/ty.xml'),
(u'\u65e9\u62a5\u526f\u520a', u'http://www.zaobao.com/fk/fk.xml'), (u'\u65e9\u62a5\u526f\u520a', u'http://www.zaobao.com/fk/fk.xml'),
] ]
def preprocess_html(self, soup):
for tag in soup.findAll(name='a'):
if tag.has_key('href'):
tag_url = tag['href']
if tag_url.find('http://') != -1 and tag_url.find('zaobao.com') == -1:
del tag['href']
return soup
def postprocess_html(self, soup, first): def postprocess_html(self, soup, first):
for tag in soup.findAll(name=['table', 'tr', 'td']): for tag in soup.findAll(name=['table', 'tr', 'td']):
tag.name = 'div' tag.name = 'div'
return soup return soup
def parse_feeds(self): def parse_feeds(self):
self.log.debug('ZAOBAO overrided parse_feeds()') self.log_debug(_('ZAOBAO overrided parse_feeds()'))
parsed_feeds = BasicNewsRecipe.parse_feeds(self) parsed_feeds = BasicNewsRecipe.parse_feeds(self)
for id, obj in enumerate(self.INDEXES): for id, obj in enumerate(self.INDEXES):
@ -88,7 +99,7 @@ class ZAOBAO(BasicNewsRecipe):
a_title = self.tag_to_string(a) a_title = self.tag_to_string(a)
date = '' date = ''
description = '' description = ''
self.log.debug('adding %s at %s'%(a_title,a_url)) self.log_debug(_('adding %s at %s')%(a_title,a_url))
articles.append({ articles.append({
'title':a_title, 'title':a_title,
'date':date, 'date':date,
@ -97,26 +108,25 @@ class ZAOBAO(BasicNewsRecipe):
}) })
pfeeds = feeds_from_index([(title, articles)], oldest_article=self.oldest_article, pfeeds = feeds_from_index([(title, articles)], oldest_article=self.oldest_article,
max_articles_per_feed=self.max_articles_per_feed, max_articles_per_feed=self.max_articles_per_feed)
log=self.log)
self.log.debug('adding %s to feed'%(title)) self.log_debug(_('adding %s to feed')%(title))
for feed in pfeeds: for feed in pfeeds:
self.log.debug('adding feed: %s'%(feed.title)) self.log_debug(_('adding feed: %s')%(feed.title))
feed.description = self.DESC_SENSE feed.description = self.DESC_SENSE
parsed_feeds.append(feed) parsed_feeds.append(feed)
for a, article in enumerate(feed): for a, article in enumerate(feed):
self.log.debug('added article %s from %s'%(article.title, article.url)) self.log_debug(_('added article %s from %s')%(article.title, article.url))
self.log.debug('added feed %s'%(feed.title)) self.log_debug(_('added feed %s')%(feed.title))
for i, feed in enumerate(parsed_feeds): for i, feed in enumerate(parsed_feeds):
# workaorund a strange problem: Somethimes the xml encoding is not apllied correctly by parse() # workaorund a strange problem: Somethimes the xml encoding is not apllied correctly by parse()
weired_encoding_detected = False weired_encoding_detected = False
if not isinstance(feed.description, unicode) and self.encoding and feed.description: if not isinstance(feed.description, unicode) and self.encoding and feed.description:
self.log.debug('Feed %s is not encoded correctly, manually replace it'%(feed.title)) self.log_debug(_('Feed %s is not encoded correctly, manually replace it')%(feed.title))
feed.description = feed.description.decode(self.encoding, 'replace') feed.description = feed.description.decode(self.encoding, 'replace')
elif feed.description.find(self.DESC_SENSE) == -1 and self.encoding and feed.description: elif feed.description.find(self.DESC_SENSE) == -1 and self.encoding and feed.description:
self.log.debug('Feed %s is strangely encoded, manually redo all'%(feed.title)) self.log_debug(_('Feed %s is weired encoded, manually redo all')%(feed.title))
feed.description = feed.description.encode('cp1252', 'replace').decode(self.encoding, 'replace') feed.description = feed.description.encode('cp1252', 'replace').decode(self.encoding, 'replace')
weired_encoding_detected = True weired_encoding_detected = True
@ -138,7 +148,7 @@ class ZAOBAO(BasicNewsRecipe):
article.text_summary = article.text_summary.encode('cp1252', 'replace').decode(self.encoding, 'replace') article.text_summary = article.text_summary.encode('cp1252', 'replace').decode(self.encoding, 'replace')
if article.title == "Untitled article": if article.title == "Untitled article":
self.log.debug('Removing empty article %s from %s'%(article.title, article.url)) self.log_debug(_('Removing empty article %s from %s')%(article.title, article.url))
# remove the article # remove the article
feed.articles[a:a+1] = [] feed.articles[a:a+1] = []
return parsed_feeds return parsed_feeds