Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-06-23 15:30:45 -04:00
Code Issues Packages Projects Releases Wiki Activity

Updated Ming Pao and Various Taiwanese news sources by Eddie Lau

Browse Source
This commit is contained in:
Kovid Goyal 2011-05-12 10:10:14 -06:00
parent c7c9ade376
commit 16c92f3d23
4 changed files with 505 additions and 304 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

42
recipes/china_times.recipe Normal file
View File

@ -0,0 +1,42 @@
# -*- coding: utf-8 -*-
__license__ = 'GPL v3'
# dug from http://www.mobileread.com/forums/showthread.php?p=1012294
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1277443634(BasicNewsRecipe):
title = u'中時電子報'
oldest_article = 1
max_articles_per_feed = 100
feeds = [(u'焦點', u'http://rss.chinatimes.com/rss/focus-u.rss'),
(u'政治', u'http://rss.chinatimes.com/rss/Politic-u.rss'),
(u'社會', u'http://rss.chinatimes.com/rss/social-u.rss'),
(u'國際', u'http://rss.chinatimes.com/rss/international-u.rss'),
(u'兩岸', u'http://rss.chinatimes.com/rss/mainland-u.rss'),
(u'地方', u'http://rss.chinatimes.com/rss/local-u.rss'),
(u'言論', u'http://rss.chinatimes.com/rss/comment-u.rss'),
(u'科技', u'http://rss.chinatimes.com/rss/technology-u.rss'),
(u'運動', u'http://rss.chinatimes.com/rss/sport-u.rss'),
(u'藝文', u'http://rss.chinatimes.com/rss/philology-u.rss'),
#(u'旺報', u'http://rss.chinatimes.com/rss/want-u.rss'),
#(u'財經', u'http://rss.chinatimes.com/rss/finance-u.rss'), # broken links
#(u'股市', u'http://rss.chinatimes.com/rss/stock-u.rss') # broken links
]
__author__ = 'einstuerzende, updated by Eddie Lau'
__version__ = '1.0'
language = 'zh'
publisher = 'China Times Group'
description = 'China Times (Taiwan)'
category = 'News, Chinese, Taiwan'
remove_javascript = True
use_embedded_content = False
no_stylesheets = True
encoding = 'big5'
conversion_options = {'linearize_tables':True}
masthead_url = 'http://www.fcuaa.org/gif/chinatimeslogo.gif'
cover_url = 'http://www.fcuaa.org/gif/chinatimeslogo.gif'
keep_only_tags = [dict(name='div', attrs={'class':['articlebox','articlebox clearfix']})]
remove_tags = [dict(name='div', attrs={'class':['focus-news']})]

44
recipes/liberty_times.recipe Normal file
View File

@ -0,0 +1,44 @@
# -*- coding: utf-8 -*-
__license__ = 'GPL v3'
# dug from http://www.mobileread.com/forums/showthread.php?p=1012294
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1277443634(BasicNewsRecipe):
title = u'自由電子報'
oldest_article = 1
max_articles_per_feed = 100
feeds = [(u'焦點新聞', u'http://www.libertytimes.com.tw/rss/fo.xml'),
(u'政治新聞', u'http://www.libertytimes.com.tw/rss/p.xml'),
(u'生活新聞', u'http://www.libertytimes.com.tw/rss/life.xml'),
(u'國際新聞', u'http://www.libertytimes.com.tw/rss/int.xml'),
(u'自由廣場', u'http://www.libertytimes.com.tw/rss/o.xml'),
(u'社會新聞', u'http://www.libertytimes.com.tw/rss/so.xml'),
(u'體育新聞', u'http://www.libertytimes.com.tw/rss/sp.xml'),
(u'財經焦點', u'http://www.libertytimes.com.tw/rss/e.xml'),
(u'證券理財', u'http://www.libertytimes.com.tw/rss/stock.xml'),
(u'影視焦點', u'http://www.libertytimes.com.tw/rss/show.xml'),
(u'北部新聞', u'http://www.libertytimes.com.tw/rss/north.xml'),
(u'中部新聞', u'http://www.libertytimes.com.tw/rss/center.xml'),
(u'南部新聞', u'http://www.libertytimes.com.tw/rss/south.xml'),
(u'大台北新聞', u'http://www.libertytimes.com.tw/rss/taipei.xml'),
(u'藝術文化', u'http://www.libertytimes.com.tw/rss/art.xml'),
]
extra_css = '''span[class='insubject1'][id='newtitle'] {font-size:200%; font-weight:bold;}'''
__author__ = 'einstuerzende, updated by Eddie Lau'
__version__ = '1.1'
language = 'zh'
publisher = 'Liberty Times Group'
description = 'Liberty Times (Taiwan)'
category = 'News, Chinese, Taiwan'
remove_javascript = True
use_embedded_content = False
no_stylesheets = True
encoding = 'big5'
conversion_options = {'linearize_tables':True}
masthead_url = 'http://www.libertytimes.com.tw/2008/images/img_auto/005/logo_new.gif'
cover_url = 'http://www.libertytimes.com.tw/2008/images/img_auto/005/logo_new.gif'
keep_only_tags = [dict(name='td', attrs={'id':['newsContent']})]

656
recipes/ming_pao.recipe
View File

@ -1,15 +1,18 @@
# -*- coding: utf-8 -*-
__license__ = 'GPL v3'
__copyright__ = '2010-2011, Eddie Lau'
# Users of Kindle 3 (with limited system-level CJK support)
# Users of Kindle 3 with limited system-level CJK support
# please replace the following "True" with "False".
__MakePeriodical__ = True
# Turn it to True if your device supports display of CJK titles
# Turn below to true if your device supports display of CJK titles
__UseChineseTitle__ = False
# Trun below to true if you wish to use life.mingpao.com as the main article source
__UseLife__ = True
'''
Change Log:
2011/05/12: switch the main parse source to life.mingpao.com, which has more photos on the article pages
2011/03/06: add new articles for finance section, also a new section "Columns"
2011/02/28: rearrange the sections
[Disabled until Kindle has better CJK support and can remember last (section,article) read in Sections & Articles
@ -32,41 +35,43 @@ import os, datetime, re
from calibre.web.feeds.recipes import BasicNewsRecipe
from contextlib import nested
from calibre.ebooks.BeautifulSoup import BeautifulSoup
from calibre.ebooks.metadata.opf2 import OPFCreator
from calibre.ebooks.metadata.toc import TOC
from calibre.ebooks.metadata import MetaInformation
class MPHKRecipe(BasicNewsRecipe):
title = 'Ming Pao - Hong Kong'
oldest_article = 1
max_articles_per_feed = 100
__author__ = 'Eddie Lau'
description = 'Hong Kong Chinese Newspaper (http://news.mingpao.com)'
publisher = 'MingPao'
category = 'Chinese, News, Hong Kong'
remove_javascript = True
use_embedded_content = False
no_stylesheets = True
language = 'zh'
encoding = 'Big5-HKSCS'
recursions = 0
conversion_options = {'linearize_tables':True}
timefmt = ''
extra_css = 'img {display: block; margin-left: auto; margin-right: auto; margin-top: 10px; margin-bottom: 10px;} font>b {font-size:200%; font-weight:bold;}'
masthead_url = 'http://news.mingpao.com/image/portals_top_logo_news.gif'
keep_only_tags = [dict(name='h1'),
title = 'Ming Pao - Hong Kong'
oldest_article = 1
max_articles_per_feed = 100
__author__ = 'Eddie Lau'
description = 'Hong Kong Chinese Newspaper (http://news.mingpao.com)'
publisher = 'MingPao'
category = 'Chinese, News, Hong Kong'
remove_javascript = True
use_embedded_content = False
no_stylesheets = True
language = 'zh'
encoding = 'Big5-HKSCS'
recursions = 0
conversion_options = {'linearize_tables':True}
timefmt = ''
extra_css = 'img {display: block; margin-left: auto; margin-right: auto; margin-top: 10px; margin-bottom: 10px;} font>b {font-size:200%; font-weight:bold;}'
masthead_url = 'http://news.mingpao.com/image/portals_top_logo_news.gif'
keep_only_tags = [dict(name='h1'),
dict(name='font', attrs={'style':['font-size:14pt; line-height:160%;']}), # for entertainment page title
dict(name='font', attrs={'color':['AA0000']}), # for column articles title
dict(attrs={'id':['newscontent']}), # entertainment and column page content
dict(attrs={'id':['newscontent01','newscontent02']}),
dict(attrs={'class':['photo']})
dict(attrs={'class':['photo']}),
dict(name='img', attrs={'width':['180'], 'alt':['按圖放大']}) # images for source from life.mingpao.com
]
remove_tags = [dict(name='style'),
dict(attrs={'id':['newscontent135']}), # for the finance page
dict(name='table')] # for content fetched from life.mingpao.com
remove_attributes = ['width']
preprocess_regexps = [
remove_tags = [dict(name='style'),
dict(attrs={'id':['newscontent135']}), # for the finance page from mpfinance.com
dict(name='table')] # for content fetched from life.mingpao.com
remove_attributes = ['width']
preprocess_regexps = [
(re.compile(r'<h5>', re.DOTALL|re.IGNORECASE),
lambda match: '<h1>'),
(re.compile(r'</h5>', re.DOTALL|re.IGNORECASE),
@ -80,10 +85,10 @@ class MPHKRecipe(BasicNewsRecipe):
lambda match: "</b>")
]
def image_url_processor(cls, baseurl, url):
# trick: break the url at the first occurance of digit, add an additional
# '_' at the front
# not working, may need to move this to preprocess_html() method
def image_url_processor(cls, baseurl, url):
# trick: break the url at the first occurance of digit, add an additional
# '_' at the front
# not working, may need to move this to preprocess_html() method
# minIdx = 10000
# i0 = url.find('0')
# if i0 >= 0 and i0 < minIdx:
@ -115,314 +120,357 @@ class MPHKRecipe(BasicNewsRecipe):
# i9 = url.find('9')
# if i9 >= 0 and i9 < minIdx:
# minIdx = i9
return url
return url
def get_dtlocal(self):
dt_utc = datetime.datetime.utcnow()
# convert UTC to local hk time - at around HKT 6.00am, all news are available
dt_local = dt_utc - datetime.timedelta(-2.0/24)
return dt_local
def get_dtlocal(self):
dt_utc = datetime.datetime.utcnow()
# convert UTC to local hk time - at around HKT 6.00am, all news are available
dt_local = dt_utc - datetime.timedelta(-2.0/24)
return dt_local
def get_fetchdate(self):
return self.get_dtlocal().strftime("%Y%m%d")
def get_fetchdate(self):
return self.get_dtlocal().strftime("%Y%m%d")
def get_fetchformatteddate(self):
return self.get_dtlocal().strftime("%Y-%m-%d")
def get_fetchformatteddate(self):
return self.get_dtlocal().strftime("%Y-%m-%d")
def get_fetchday(self):
# convert UTC to local hk time - at around HKT 6.00am, all news are available
return self.get_dtlocal().strftime("%d")
def get_fetchday(self):
# dt_utc = datetime.datetime.utcnow()
# convert UTC to local hk time - at around HKT 6.00am, all news are available
# dt_local = dt_utc - datetime.timedelta(-2.0/24)
return self.get_dtlocal().strftime("%d")
def get_cover_url(self):
cover = 'http://news.mingpao.com/' + self.get_fetchdate() + '/' + self.get_fetchdate() + '_' + self.get_fetchday() + 'gacov.jpg'
br = BasicNewsRecipe.get_browser()
try:
br.open(cover)
except:
cover = None
return cover
def get_cover_url(self):
cover = 'http://news.mingpao.com/' + self.get_fetchdate() + '/' + self.get_fetchdate() + '_' + self.get_fetchday() + 'gacov.jpg'
br = BasicNewsRecipe.get_browser()
try:
br.open(cover)
except:
cover = None
return cover
def parse_index(self):
feeds = []
dateStr = self.get_fetchdate()
def parse_index(self):
feeds = []
dateStr = self.get_fetchdate()
for title, url in [(u'\u8981\u805e Headline', 'http://news.mingpao.com/' + dateStr + '/gaindex.htm'),
(u'\u6e2f\u805e Local', 'http://news.mingpao.com/' + dateStr + '/gbindex.htm'),
(u'\u6559\u80b2 Education', 'http://news.mingpao.com/' + dateStr + '/gfindex.htm')]:
articles = self.parse_section(url)
if articles:
feeds.append((title, articles))
if __UseLife__:
for title, url, keystr in [(u'\u8981\u805e Headline', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalga', 'nal'),
(u'\u6e2f\u805e Local', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalgb', 'nal'),
(u'\u6559\u80b2 Education', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalgf', 'nal'),
(u'\u793e\u8a55/\u7b46\u9663 Editorial', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalmr', 'nal'),
(u'\u8ad6\u58c7 Forum', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalfa', 'nal'),
(u'\u4e2d\u570b China', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalca', 'nal'),
(u'\u570b\u969b World', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalta', 'nal'),
(u'\u7d93\u6fdf Finance', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalea', 'nal'),
(u'\u9ad4\u80b2 Sport', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalsp', 'nal'),
(u'\u5f71\u8996 Film/TV', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalma', 'nal'),
(u'\u5c08\u6b04 Columns', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=ncolumn', 'ncl')]:
articles = self.parse_section2(url, keystr)
if articles:
feeds.append((title, articles))
# special- editorial
ed_articles = self.parse_ed_section('http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalmr')
if ed_articles:
feeds.append((u'\u793e\u8a55/\u7b46\u9663 Editorial', ed_articles))
for title, url in [(u'\u526f\u520a Supplement', 'http://news.mingpao.com/' + dateStr + '/jaindex.htm'),
(u'\u82f1\u6587 English', 'http://news.mingpao.com/' + dateStr + '/emindex.htm')]:
articles = self.parse_section(url)
if articles:
feeds.append((title, articles))
else:
for title, url in [(u'\u8981\u805e Headline', 'http://news.mingpao.com/' + dateStr + '/gaindex.htm'),
(u'\u6e2f\u805e Local', 'http://news.mingpao.com/' + dateStr + '/gbindex.htm'),
(u'\u6559\u80b2 Education', 'http://news.mingpao.com/' + dateStr + '/gfindex.htm')]:
articles = self.parse_section(url)
if articles:
feeds.append((title, articles))
for title, url in [(u'\u8ad6\u58c7 Forum', 'http://news.mingpao.com/' + dateStr + '/faindex.htm'),
(u'\u4e2d\u570b China', 'http://news.mingpao.com/' + dateStr + '/caindex.htm'),
(u'\u570b\u969b World', 'http://news.mingpao.com/' + dateStr + '/taindex.htm')]:
articles = self.parse_section(url)
if articles:
feeds.append((title, articles))
# special- editorial
ed_articles = self.parse_ed_section('http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=nalmr')
if ed_articles:
feeds.append((u'\u793e\u8a55/\u7b46\u9663 Editorial', ed_articles))
# special - finance
#fin_articles = self.parse_fin_section('http://www.mpfinance.com/htm/Finance/' + dateStr + '/News/ea,eb,ecindex.htm')
fin_articles = self.parse_fin_section('http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalea')
if fin_articles:
feeds.append((u'\u7d93\u6fdf Finance', fin_articles))
for title, url in [(u'\u8ad6\u58c7 Forum', 'http://news.mingpao.com/' + dateStr + '/faindex.htm'),
(u'\u4e2d\u570b China', 'http://news.mingpao.com/' + dateStr + '/caindex.htm'),
(u'\u570b\u969b World', 'http://news.mingpao.com/' + dateStr + '/taindex.htm')]:
articles = self.parse_section(url)
if articles:
feeds.append((title, articles))
for title, url in [('Tech News', 'http://news.mingpao.com/' + dateStr + '/naindex.htm'),
(u'\u9ad4\u80b2 Sport', 'http://news.mingpao.com/' + dateStr + '/spindex.htm')]:
articles = self.parse_section(url)
if articles:
feeds.append((title, articles))
# special - finance
#fin_articles = self.parse_fin_section('http://www.mpfinance.com/htm/Finance/' + dateStr + '/News/ea,eb,ecindex.htm')
fin_articles = self.parse_fin_section('http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalea')
if fin_articles:
feeds.append((u'\u7d93\u6fdf Finance', fin_articles))
# special - entertainment
ent_articles = self.parse_ent_section('http://ol.mingpao.com/cfm/star1.cfm')
if ent_articles:
feeds.append((u'\u5f71\u8996 Film/TV', ent_articles))
for title, url in [('Tech News', 'http://news.mingpao.com/' + dateStr + '/naindex.htm'),
(u'\u9ad4\u80b2 Sport', 'http://news.mingpao.com/' + dateStr + '/spindex.htm')]:
articles = self.parse_section(url)
if articles:
feeds.append((title, articles))
for title, url in [(u'\u526f\u520a Supplement', 'http://news.mingpao.com/' + dateStr + '/jaindex.htm'),
(u'\u82f1\u6587 English', 'http://news.mingpao.com/' + dateStr + '/emindex.htm')]:
articles = self.parse_section(url)
if articles:
feeds.append((title, articles))
# special - entertainment
ent_articles = self.parse_ent_section('http://ol.mingpao.com/cfm/star1.cfm')
if ent_articles:
feeds.append((u'\u5f71\u8996 Film/TV', ent_articles))
for title, url in [(u'\u526f\u520a Supplement', 'http://news.mingpao.com/' + dateStr + '/jaindex.htm'),
(u'\u82f1\u6587 English', 'http://news.mingpao.com/' + dateStr + '/emindex.htm')]:
articles = self.parse_section(url)
if articles:
feeds.append((title, articles))
# special- columns
col_articles = self.parse_col_section('http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=ncolumn')
if col_articles:
feeds.append((u'\u5c08\u6b04 Columns', col_articles))
# special- columns
col_articles = self.parse_col_section('http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=ncolumn')
if col_articles:
feeds.append((u'\u5c08\u6b04 Columns', col_articles))
return feeds
return feeds
def parse_section(self, url):
dateStr = self.get_fetchdate()
soup = self.index_to_soup(url)
divs = soup.findAll(attrs={'class': ['bullet','bullet_grey']})
current_articles = []
included_urls = []
divs.reverse()
for i in divs:
a = i.find('a', href = True)
title = self.tag_to_string(a)
url = a.get('href', False)
url = 'http://news.mingpao.com/' + dateStr + '/' +url
if url not in included_urls and url.rfind('Redirect') == -1:
current_articles.append({'title': title, 'url': url, 'description':'', 'date':''})
included_urls.append(url)
current_articles.reverse()
return current_articles
# parse from news.mingpao.com
def parse_section(self, url):
dateStr = self.get_fetchdate()
soup = self.index_to_soup(url)
divs = soup.findAll(attrs={'class': ['bullet','bullet_grey']})
current_articles = []
included_urls = []
divs.reverse()
for i in divs:
a = i.find('a', href = True)
title = self.tag_to_string(a)
url = a.get('href', False)
url = 'http://news.mingpao.com/' + dateStr + '/' +url
if url not in included_urls and url.rfind('Redirect') == -1:
current_articles.append({'title': title, 'url': url, 'description':'', 'date':''})
included_urls.append(url)
current_articles.reverse()
return current_articles
def parse_ed_section(self, url):
self.get_fetchdate()
soup = self.index_to_soup(url)
a = soup.findAll('a', href=True)
a.reverse()
current_articles = []
included_urls = []
for i in a:
title = self.tag_to_string(i)
url = 'http://life.mingpao.com/cfm/' + i.get('href', False)
if (url not in included_urls) and (not url.rfind('.txt') == -1) and (not url.rfind('nal') == -1):
current_articles.append({'title': title, 'url': url, 'description': ''})
included_urls.append(url)
current_articles.reverse()
return current_articles
# parse from life.mingpao.com
def parse_section2(self, url, keystr):
self.get_fetchdate()
soup = self.index_to_soup(url)
a = soup.findAll('a', href=True)
a.reverse()
current_articles = []
included_urls = []
for i in a:
title = self.tag_to_string(i)
url = 'http://life.mingpao.com/cfm/' + i.get('href', False)
if (url not in included_urls) and (not url.rfind('.txt') == -1) and (not url.rfind(keystr) == -1):
current_articles.append({'title': title, 'url': url, 'description': ''})
included_urls.append(url)
current_articles.reverse()
return current_articles
def parse_fin_section(self, url):
self.get_fetchdate()
soup = self.index_to_soup(url)
a = soup.findAll('a', href= True)
current_articles = []
included_urls = []
for i in a:
#url = 'http://www.mpfinance.com/cfm/' + i.get('href', False)
url = 'http://life.mingpao.com/cfm/' + i.get('href', False)
#if url not in included_urls and not url.rfind(dateStr) == -1 and url.rfind('index') == -1:
if url not in included_urls and (not url.rfind('txt') == -1) and (not url.rfind('nal') == -1):
title = self.tag_to_string(i)
current_articles.append({'title': title, 'url': url, 'description':''})
included_urls.append(url)
return current_articles
def parse_ed_section(self, url):
self.get_fetchdate()
soup = self.index_to_soup(url)
a = soup.findAll('a', href=True)
a.reverse()
current_articles = []
included_urls = []
for i in a:
title = self.tag_to_string(i)
url = 'http://life.mingpao.com/cfm/' + i.get('href', False)
if (url not in included_urls) and (not url.rfind('.txt') == -1) and (not url.rfind('nal') == -1):
current_articles.append({'title': title, 'url': url, 'description': ''})
included_urls.append(url)
current_articles.reverse()
return current_articles
def parse_ent_section(self, url):
self.get_fetchdate()
soup = self.index_to_soup(url)
a = soup.findAll('a', href=True)
a.reverse()
current_articles = []
included_urls = []
for i in a:
title = self.tag_to_string(i)
url = 'http://ol.mingpao.com/cfm/' + i.get('href', False)
if (url not in included_urls) and (not url.rfind('.txt') == -1) and (not url.rfind('star') == -1):
current_articles.append({'title': title, 'url': url, 'description': ''})
included_urls.append(url)
current_articles.reverse()
return current_articles
def parse_fin_section(self, url):
self.get_fetchdate()
soup = self.index_to_soup(url)
a = soup.findAll('a', href= True)
current_articles = []
included_urls = []
for i in a:
#url = 'http://www.mpfinance.com/cfm/' + i.get('href', False)
url = 'http://life.mingpao.com/cfm/' + i.get('href', False)
#if url not in included_urls and not url.rfind(dateStr) == -1 and url.rfind('index') == -1:
if url not in included_urls and (not url.rfind('txt') == -1) and (not url.rfind('nal') == -1):
title = self.tag_to_string(i)
current_articles.append({'title': title, 'url': url, 'description':''})
included_urls.append(url)
return current_articles
def parse_col_section(self, url):
self.get_fetchdate()
soup = self.index_to_soup(url)
a = soup.findAll('a', href=True)
a.reverse()
current_articles = []
included_urls = []
for i in a:
title = self.tag_to_string(i)
url = 'http://life.mingpao.com/cfm/' + i.get('href', False)
if (url not in included_urls) and (not url.rfind('.txt') == -1) and (not url.rfind('ncl') == -1):
current_articles.append({'title': title, 'url': url, 'description': ''})
included_urls.append(url)
current_articles.reverse()
return current_articles
def parse_ent_section(self, url):
self.get_fetchdate()
soup = self.index_to_soup(url)
a = soup.findAll('a', href=True)
a.reverse()
current_articles = []
included_urls = []
for i in a:
title = self.tag_to_string(i)
url = 'http://ol.mingpao.com/cfm/' + i.get('href', False)
if (url not in included_urls) and (not url.rfind('.txt') == -1) and (not url.rfind('star') == -1):
current_articles.append({'title': title, 'url': url, 'description': ''})
included_urls.append(url)
current_articles.reverse()
return current_articles
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
for item in soup.findAll(style=True):
del item['width']
for item in soup.findAll(stype=True):
del item['absmiddle']
return soup
def parse_col_section(self, url):
self.get_fetchdate()
soup = self.index_to_soup(url)
a = soup.findAll('a', href=True)
a.reverse()
current_articles = []
included_urls = []
for i in a:
title = self.tag_to_string(i)
url = 'http://life.mingpao.com/cfm/' + i.get('href', False)
if (url not in included_urls) and (not url.rfind('.txt') == -1) and (not url.rfind('ncl') == -1):
current_articles.append({'title': title, 'url': url, 'description': ''})
included_urls.append(url)
current_articles.reverse()
return current_articles
def create_opf(self, feeds, dir=None):
if dir is None:
dir = self.output_dir
if __UseChineseTitle__ == True:
title = u'\u660e\u5831 (\u9999\u6e2f)'
else:
title = self.short_title()
# if not generating a periodical, force date to apply in title
if __MakePeriodical__ == False:
title = title + ' ' + self.get_fetchformatteddate()
if True:
mi = MetaInformation(title, [self.publisher])
mi.publisher = self.publisher
mi.author_sort = self.publisher
if __MakePeriodical__ == True:
mi.publication_type = 'periodical:'+self.publication_type+':'+self.short_title()
else:
mi.publication_type = self.publication_type+':'+self.short_title()
#mi.timestamp = nowf()
mi.timestamp = self.get_dtlocal()
mi.comments = self.description
if not isinstance(mi.comments, unicode):
mi.comments = mi.comments.decode('utf-8', 'replace')
#mi.pubdate = nowf()
mi.pubdate = self.get_dtlocal()
opf_path = os.path.join(dir, 'index.opf')
ncx_path = os.path.join(dir, 'index.ncx')
opf = OPFCreator(dir, mi)
# Add mastheadImage entry to <guide> section
mp = getattr(self, 'masthead_path', None)
if mp is not None and os.access(mp, os.R_OK):
from calibre.ebooks.metadata.opf2 import Guide
ref = Guide.Reference(os.path.basename(self.masthead_path), os.getcwdu())
ref.type = 'masthead'
ref.title = 'Masthead Image'
opf.guide.append(ref)
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
for item in soup.findAll(style=True):
del item['width']
for item in soup.findAll(stype=True):
del item['absmiddle']
return soup
manifest = [os.path.join(dir, 'feed_%d'%i) for i in range(len(feeds))]
manifest.append(os.path.join(dir, 'index.html'))
manifest.append(os.path.join(dir, 'index.ncx'))
def create_opf(self, feeds, dir=None):
if dir is None:
dir = self.output_dir
if __UseChineseTitle__ == True:
title = u'\u660e\u5831 (\u9999\u6e2f)'
else:
title = self.short_title()
# if not generating a periodical, force date to apply in title
if __MakePeriodical__ == False:
title = title + ' ' + self.get_fetchformatteddate()
if True:
mi = MetaInformation(title, [self.publisher])
mi.publisher = self.publisher
mi.author_sort = self.publisher
if __MakePeriodical__ == True:
mi.publication_type = 'periodical:'+self.publication_type+':'+self.short_title()
else:
mi.publication_type = self.publication_type+':'+self.short_title()
#mi.timestamp = nowf()
mi.timestamp = self.get_dtlocal()
mi.comments = self.description
if not isinstance(mi.comments, unicode):
mi.comments = mi.comments.decode('utf-8', 'replace')
#mi.pubdate = nowf()
mi.pubdate = self.get_dtlocal()
opf_path = os.path.join(dir, 'index.opf')
ncx_path = os.path.join(dir, 'index.ncx')
opf = OPFCreator(dir, mi)
# Add mastheadImage entry to <guide> section
mp = getattr(self, 'masthead_path', None)
if mp is not None and os.access(mp, os.R_OK):
from calibre.ebooks.metadata.opf2 import Guide
ref = Guide.Reference(os.path.basename(self.masthead_path), os.getcwdu())
ref.type = 'masthead'
ref.title = 'Masthead Image'
opf.guide.append(ref)
# Get cover
cpath = getattr(self, 'cover_path', None)
if cpath is None:
pf = open(os.path.join(dir, 'cover.jpg'), 'wb')
if self.default_cover(pf):
cpath = pf.name
if cpath is not None and os.access(cpath, os.R_OK):
opf.cover = cpath
manifest.append(cpath)
manifest = [os.path.join(dir, 'feed_%d'%i) for i in range(len(feeds))]
manifest.append(os.path.join(dir, 'index.html'))
manifest.append(os.path.join(dir, 'index.ncx'))
# Get masthead
mpath = getattr(self, 'masthead_path', None)
if mpath is not None and os.access(mpath, os.R_OK):
manifest.append(mpath)
# Get cover
cpath = getattr(self, 'cover_path', None)
if cpath is None:
pf = open(os.path.join(dir, 'cover.jpg'), 'wb')
if self.default_cover(pf):
cpath = pf.name
if cpath is not None and os.access(cpath, os.R_OK):
opf.cover = cpath
manifest.append(cpath)
opf.create_manifest_from_files_in(manifest)
for mani in opf.manifest:
if mani.path.endswith('.ncx'):
mani.id = 'ncx'
if mani.path.endswith('mastheadImage.jpg'):
mani.id = 'masthead-image'
entries = ['index.html']
toc = TOC(base_path=dir)
self.play_order_counter = 0
self.play_order_map = {}
# Get masthead
mpath = getattr(self, 'masthead_path', None)
if mpath is not None and os.access(mpath, os.R_OK):
manifest.append(mpath)
def feed_index(num, parent):
f = feeds[num]
for j, a in enumerate(f):
if getattr(a, 'downloaded', False):
adir = 'feed_%d/article_%d/'%(num, j)
auth = a.author
if not auth:
auth = None
desc = a.text_summary
if not desc:
desc = None
else:
desc = self.description_limiter(desc)
entries.append('%sindex.html'%adir)
po = self.play_order_map.get(entries[-1], None)
if po is None:
self.play_order_counter += 1
po = self.play_order_counter
parent.add_item('%sindex.html'%adir, None, a.title if a.title else _('Untitled Article'),
opf.create_manifest_from_files_in(manifest)
for mani in opf.manifest:
if mani.path.endswith('.ncx'):
mani.id = 'ncx'
if mani.path.endswith('mastheadImage.jpg'):
mani.id = 'masthead-image'
entries = ['index.html']
toc = TOC(base_path=dir)
self.play_order_counter = 0
self.play_order_map = {}
def feed_index(num, parent):
f = feeds[num]
for j, a in enumerate(f):
if getattr(a, 'downloaded', False):
adir = 'feed_%d/article_%d/'%(num, j)
auth = a.author
if not auth:
auth = None
desc = a.text_summary
if not desc:
desc = None
else:
desc = self.description_limiter(desc)
entries.append('%sindex.html'%adir)
po = self.play_order_map.get(entries[-1], None)
if po is None:
self.play_order_counter += 1
po = self.play_order_counter
parent.add_item('%sindex.html'%adir, None, a.title if a.title else _('Untitled Article'),
play_order=po, author=auth, description=desc)
last = os.path.join(self.output_dir, ('%sindex.html'%adir).replace('/', os.sep))
for sp in a.sub_pages:
prefix = os.path.commonprefix([opf_path, sp])
relp = sp[len(prefix):]
entries.append(relp.replace(os.sep, '/'))
last = sp
last = os.path.join(self.output_dir, ('%sindex.html'%adir).replace('/', os.sep))
for sp in a.sub_pages:
prefix = os.path.commonprefix([opf_path, sp])
relp = sp[len(prefix):]
entries.append(relp.replace(os.sep, '/'))
last = sp
if os.path.exists(last):
with open(last, 'rb') as fi:
src = fi.read().decode('utf-8')
soup = BeautifulSoup(src)
body = soup.find('body')
if body is not None:
prefix = '/'.join('..'for i in range(2*len(re.findall(r'link\d+', last))))
templ = self.navbar.generate(True, num, j, len(f),
if os.path.exists(last):
with open(last, 'rb') as fi:
src = fi.read().decode('utf-8')
soup = BeautifulSoup(src)
body = soup.find('body')
if body is not None:
prefix = '/'.join('..'for i in range(2*len(re.findall(r'link\d+', last))))
templ = self.navbar.generate(True, num, j, len(f),
not self.has_single_feed,
a.orig_url, self.publisher, prefix=prefix,
center=self.center_navbar)
elem = BeautifulSoup(templ.render(doctype='xhtml').decode('utf-8')).find('div')
body.insert(len(body.contents), elem)
with open(last, 'wb') as fi:
fi.write(unicode(soup).encode('utf-8'))
if len(feeds) == 0:
raise Exception('All feeds are empty, aborting.')
elem = BeautifulSoup(templ.render(doctype='xhtml').decode('utf-8')).find('div')
body.insert(len(body.contents), elem)
with open(last, 'wb') as fi:
fi.write(unicode(soup).encode('utf-8'))
if len(feeds) == 0:
raise Exception('All feeds are empty, aborting.')
if len(feeds) > 1:
for i, f in enumerate(feeds):
entries.append('feed_%d/index.html'%i)
po = self.play_order_map.get(entries[-1], None)
if po is None:
self.play_order_counter += 1
po = self.play_order_counter
auth = getattr(f, 'author', None)
if not auth:
auth = None
desc = getattr(f, 'description', None)
if not desc:
desc = None
feed_index(i, toc.add_item('feed_%d/index.html'%i, None,
if len(feeds) > 1:
for i, f in enumerate(feeds):
entries.append('feed_%d/index.html'%i)
po = self.play_order_map.get(entries[-1], None)
if po is None:
self.play_order_counter += 1
po = self.play_order_counter
auth = getattr(f, 'author', None)
if not auth:
auth = None
desc = getattr(f, 'description', None)
if not desc:
desc = None
feed_index(i, toc.add_item('feed_%d/index.html'%i, None,
f.title, play_order=po, description=desc, author=auth))
else:
entries.append('feed_%d/index.html'%0)
feed_index(0, toc)
else:
entries.append('feed_%d/index.html'%0)
feed_index(0, toc)
for i, p in enumerate(entries):
entries[i] = os.path.join(dir, p.replace('/', os.sep))
opf.create_spine(entries)
opf.set_toc(toc)
for i, p in enumerate(entries):
entries[i] = os.path.join(dir, p.replace('/', os.sep))
opf.create_spine(entries)
opf.set_toc(toc)
with nested(open(opf_path, 'wb'), open(ncx_path, 'wb')) as (opf_file, ncx_file):
opf.render(opf_file, ncx_file)
with nested(open(opf_path, 'wb'), open(ncx_path, 'wb')) as (opf_file, ncx_file):
opf.render(opf_file, ncx_file)

67
recipes/united_daily.recipe Normal file
View File

@ -0,0 +1,67 @@
# -*- coding: utf-8 -*-
__license__ = 'GPL v3'
from calibre.web.feeds.news import BasicNewsRecipe
class UnitedDaily(BasicNewsRecipe):
title = u'聯合新聞網'
oldest_article = 1
max_articles_per_feed = 100
feeds = [(u'焦點', u'http://udn.com/udnrss/focus.xml'),
(u'政治', u'http://udn.com/udnrss/politics.xml'),
(u'社會', u'http://udn.com/udnrss/social.xml'),
(u'生活', u'http://udn.com/udnrss/life.xml'),
(u'綜合', u'http://udn.com/udnrss/education.xml'),
(u'意見評論', u'http://udn.com/udnrss/opinion.xml'),
(u'大台北', u'http://udn.com/udnrss/local_taipei.xml'),
(u'桃竹苗', u'http://udn.com/udnrss/local_tyhcml.xml'),
(u'中彰投', u'http://udn.com/udnrss/local_tcchnt.xml'),
(u'雲嘉南', u'http://udn.com/udnrss/local_ylcytn.xml'),
(u'高屏離島', u'http://udn.com/udnrss/local_ksptisland.xml'),
(u'基宜花東', u'http://udn.com/udnrss/local_klilhltt.xml'),
(u'台灣百寶鄉', u'http://udn.com/udnrss/local_oddlyenough.xml'),
(u'兩岸要聞', u'http://udn.com/udnrss/mainland.xml'),
(u'國際焦點', u'http://udn.com/udnrss/international.xml'),
(u'台商經貿', u'http://udn.com/udnrss/financechina.xml'),
(u'國際財經', u'http://udn.com/udnrss/financeworld.xml'),
(u'財經焦點', u'http://udn.com/udnrss/financesfocus.xml'),
(u'股市要聞', u'http://udn.com/udnrss/stock.xml'),
(u'股市快訊', u'http://udn.com/udnrss/stklatest.xml'),
(u'稅務法務', u'http://udn.com/udnrss/tax.xml'),
(u'房市情報', u'http://udn.com/udnrss/houses.xml'),
(u'棒球', u'http://udn.com/udnrss/baseball.xml'),
(u'籃球', u'http://udn.com/udnrss/basketball.xml'),
(u'體壇動態', u'http://udn.com/udnrss/sportsfocus.xml'),
(u'熱門星聞', u'http://udn.com/udnrss/starsfocus.xml'),
(u'廣電港陸', u'http://udn.com/udnrss/tv.xml'),
(u'海外星球', u'http://udn.com/udnrss/starswestern.xml'),
(u'日韓星情', u'http://udn.com/udnrss/starsjk.xml'),
(u'電影世界', u'http://udn.com/udnrss/movie.xml'),
(u'流行音樂', u'http://udn.com/udnrss/music.xml'),
(u'觀點專題', u'http://udn.com/udnrss/starssubject.xml'),
(u'食樂指南', u'http://udn.com/udnrss/food.xml'),
(u'折扣好康', u'http://udn.com/udnrss/shopping.xml'),
(u'醫藥新聞', u'http://udn.com/udnrss/health.xml'),
(u'家婦繽紛', u'http://udn.com/udnrss/benfen.xml'),
(u'談星論命', u'http://udn.com/udnrss/astrology.xml'),
(u'文化副刊', u'http://udn.com/udnrss/reading.xml'),
]
extra_css = '''div[id='story_title'] {font-size:200%; font-weight:bold;}'''
__author__ = 'Eddie Lau'
__version__ = '1.0'
language = 'zh'
publisher = 'United Daily News Group'
description = 'United Daily (Taiwan)'
category = 'News, Chinese, Taiwan'
remove_javascript = True
use_embedded_content = False
no_stylesheets = True
encoding = 'big5'
conversion_options = {'linearize_tables':True}
masthead_url = 'http://udn.com/NEWS/2004/images/logo_udn.gif'
cover_url = 'http://udn.com/NEWS/2004/images/logo_udn.gif'
keep_only_tags = [dict(name='div', attrs={'id':['story_title','story_author', 'story']})]
remove_tags = [dict(name='div', attrs={'id':['mvouter']})]