10-07-2011, 08:32 AM
|
#1 |
|
Connoisseur
 Posts: 82
Karma: 10
Join Date: Oct 2010
Device: Kindle
|
Updated "Ming Pao - Hong Kong" recipe (2011/10/07)
Hi Kovid,
I've added a few extra features to my "Ming Pao - Hong Kong" recipe. Could you upload the below code to the next release of Calibre at your convenience? Thanks! Code:
__license__ = 'GPL v3'
__copyright__ = '2010-2011, Eddie Lau'
# Region - Hong Kong, Vancouver, Toronto
__Region__ = 'Hong Kong'
# Users of Kindle 3 with limited system-level CJK support
# please replace the following "True" with "False".
__MakePeriodical__ = True
# Turn below to True if your device supports display of CJK titles
__UseChineseTitle__ = False
# Set it to False if you want to skip images
__KeepImages__ = True
# (HK only) Turn below to True if you wish to use life.mingpao.com as the main article source
__UseLife__ = True
# (HK only) It is to disable the column section which is now a premium content
__InclCols__ = False
# (HK only) Turn below to True if you wish to parse articles in news.mingpao.com with their printer-friendly formats
__ParsePFF__ = False
# (HK only) Turn below to True if you wish hi-res images
__HiResImg__ = False
'''
Change Log:
2011/10/04: option to get hi-res photos for the articles
2011/09/21: fetching "column" section is made optional.
2011/09/18: parse "column" section stuff from source text file directly.
2011/09/07: disable "column" section as it is no longer offered free.
2011/06/26: add fetching Vancouver and Toronto versions of the paper, also provide captions for images using life.mingpao fetch source
provide options to remove all images in the file
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
View] make it the same title if generating a periodical, so past issue will be automatically put into "Past Issues"
folder in Kindle 3
2011/02/20: skip duplicated links in finance section, put photos which may extend a whole page to the back of the articles
clean up the indentation
2010/12/07: add entertainment section, use newspaper front page as ebook cover, suppress date display in section list
(to avoid wrong date display in case the user generates the ebook in a time zone different from HKT)
2010/11/22: add English section, remove eco-news section which is not updated daily, correct
ordering of articles
2010/11/12: add news image and eco-news section
2010/11/08: add parsing of finance section
2010/11/06: temporary work-around for Kindle device having no capability to display unicode
in section/article list.
2010/10/31: skip repeated articles in section pages
'''
import os, datetime, re, mechanize
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
# MAIN CLASS
class MPRecipe(BasicNewsRecipe):
if __Region__ == 'Hong Kong':
title = 'Ming Pao - Hong Kong'
description = 'Hong Kong Chinese Newspaper (http://news.mingpao.com)'
category = 'Chinese, News, Hong Kong'
extra_css = 'img {display: block; margin-left: auto; margin-right: auto; margin-top: 10px; margin-bottom: 10px; max-height:90%;} font>b {font-size:200%; font-weight:bold;} div[class=heading] {font-size:200%; font-weight:bold;} div[class=images] {font-size:50%;}'
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={'class':['heading']}), # for heading from txt
dict(attrs={'id':['newscontent']}), # entertainment and column page content
dict(attrs={'id':['newscontent01','newscontent02']}),
dict(attrs={'class':['content']}), # for content from txt
dict(attrs={'class':['photo']}),
dict(name='table', attrs={'width':['100%'], 'border':['0'], 'cellspacing':['5'], 'cellpadding':['0']}), # content in printed version of life.mingpao.com
dict(name='img', attrs={'width':['180'], 'alt':['按圖放大']}), # images for source from life.mingpao.com
dict(attrs={'class':['images']}) # for images from txt
]
if __KeepImages__:
remove_tags = [dict(name='style'),
dict(attrs={'id':['newscontent135']}), # for the finance page from mpfinance.com
dict(name='font', attrs={'size':['2'], 'color':['666666']}), # article date in life.mingpao.com article
#dict(name='table') # for content fetched from life.mingpao.com
]
else:
remove_tags = [dict(name='style'),
dict(attrs={'id':['newscontent135']}), # for the finance page from mpfinance.com
dict(name='font', attrs={'size':['2'], 'color':['666666']}), # article date in life.mingpao.com article
dict(name='img'),
#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),
lambda match: '</h1>'),
(re.compile(r'<p><a href=.+?</a></p>', re.DOTALL|re.IGNORECASE), # for entertainment page
lambda match: ''),
# skip <br> after title in life.mingpao.com fetched article
(re.compile(r"<div id='newscontent'><br>", re.DOTALL|re.IGNORECASE),
lambda match: "<div id='newscontent'>"),
(re.compile(r"<br><br></b>", re.DOTALL|re.IGNORECASE),
lambda match: "</b>")
]
elif __Region__ == 'Vancouver':
title = 'Ming Pao - Vancouver'
description = 'Vancouver Chinese Newspaper (http://www.mingpaovan.com)'
category = 'Chinese, News, Vancouver'
extra_css = 'img {display: block; margin-left: auto; margin-right: auto; margin-top: 10px; margin-bottom: 10px;} b>font {font-size:200%; font-weight:bold;}'
masthead_url = 'http://www.mingpaovan.com/image/mainlogo2_VAN2.gif'
keep_only_tags = [dict(name='table', attrs={'width':['450'], 'border':['0'], 'cellspacing':['0'], 'cellpadding':['1']}),
dict(name='table', attrs={'width':['450'], 'border':['0'], 'cellspacing':['3'], 'cellpadding':['3'], 'id':['tblContent3']}),
dict(name='table', attrs={'width':['180'], 'border':['0'], 'cellspacing':['0'], 'cellpadding':['0'], 'bgcolor':['F0F0F0']}),
]
if __KeepImages__:
remove_tags = [dict(name='img', attrs={'src':['../../../image/magnifier.gif']})] # the magnifier icon
else:
remove_tags = [dict(name='img')]
remove_attributes = ['width']
preprocess_regexps = [(re.compile(r' ', re.DOTALL|re.IGNORECASE),
lambda match: ''),
]
elif __Region__ == 'Toronto':
title = 'Ming Pao - Toronto'
description = 'Toronto Chinese Newspaper (http://www.mingpaotor.com)'
category = 'Chinese, News, Toronto'
extra_css = 'img {display: block; margin-left: auto; margin-right: auto; margin-top: 10px; margin-bottom: 10px;} b>font {font-size:200%; font-weight:bold;}'
masthead_url = 'http://www.mingpaotor.com/image/mainlogo2_TOR2.gif'
keep_only_tags = [dict(name='table', attrs={'width':['450'], 'border':['0'], 'cellspacing':['0'], 'cellpadding':['1']}),
dict(name='table', attrs={'width':['450'], 'border':['0'], 'cellspacing':['3'], 'cellpadding':['3'], 'id':['tblContent3']}),
dict(name='table', attrs={'width':['180'], 'border':['0'], 'cellspacing':['0'], 'cellpadding':['0'], 'bgcolor':['F0F0F0']}),
]
if __KeepImages__:
remove_tags = [dict(name='img', attrs={'src':['../../../image/magnifier.gif']})] # the magnifier icon
else:
remove_tags = [dict(name='img')]
remove_attributes = ['width']
preprocess_regexps = [(re.compile(r' ', re.DOTALL|re.IGNORECASE),
lambda match: ''),
]
oldest_article = 1
max_articles_per_feed = 100
__author__ = 'Eddie Lau'
publisher = 'MingPao'
remove_javascript = True
use_embedded_content = False
no_stylesheets = True
language = 'zh'
encoding = 'Big5-HKSCS'
recursions = 0
conversion_options = {'linearize_tables':True}
timefmt = ''
def get_dtlocal(self):
dt_utc = datetime.datetime.utcnow()
if __Region__ == 'Hong Kong':
# convert UTC to local hk time - at HKT 5.30am, all news are available
dt_local = dt_utc + datetime.timedelta(8.0/24) - datetime.timedelta(5.5/24)
# dt_local = dt_utc.astimezone(pytz.timezone('Asia/Hong_Kong')) - datetime.timedelta(5.5/24)
elif __Region__ == 'Vancouver':
# convert UTC to local Vancouver time - at PST time 5.30am, all news are available
dt_local = dt_utc + datetime.timedelta(-8.0/24) - datetime.timedelta(5.5/24)
#dt_local = dt_utc.astimezone(pytz.timezone('America/Vancouver')) - datetime.timedelta(5.5/24)
elif __Region__ == 'Toronto':
# convert UTC to local Toronto time - at EST time 8.30am, all news are available
dt_local = dt_utc + datetime.timedelta(-5.0/24) - datetime.timedelta(8.5/24)
#dt_local = dt_utc.astimezone(pytz.timezone('America/Toronto')) - datetime.timedelta(8.5/24)
return dt_local
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_fetchday(self):
return self.get_dtlocal().strftime("%d")
def get_cover_url(self):
if __Region__ == 'Hong Kong':
cover = 'http://news.mingpao.com/' + self.get_fetchdate() + '/' + self.get_fetchdate() + '_' + self.get_fetchday() + 'gacov.jpg'
elif __Region__ == 'Vancouver':
cover = 'http://www.mingpaovan.com/ftp/News/' + self.get_fetchdate() + '/' + self.get_fetchday() + 'pgva1s.jpg'
elif __Region__ == 'Toronto':
cover = 'http://www.mingpaotor.com/ftp/News/' + self.get_fetchdate() + '/' + self.get_fetchday() + 'pgtas.jpg'
br = BasicNewsRecipe.get_browser()
try:
br.open(cover)
except:
cover = None
return cover
def parse_index(self):
feeds = []
dateStr = self.get_fetchdate()
if __Region__ == 'Hong Kong':
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')
]:
articles = self.parse_section2(url, keystr)
if articles:
feeds.append((title, articles))
if __InclCols__ == True:
# parse column section articles directly from .txt files
for title, url, keystr in [(u'\u5c08\u6b04 Columns', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=ncolumn', 'ncl')
]:
articles = self.parse_section2_txt(url, keystr)
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))
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'),
(u'\u793e\u8a55/\u7b46\u9663 Editorial', 'http://news.mingpao.com/' + dateStr + '/mrindex.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))
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 - 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, keystr in [(u'\u7d93\u6fdf Finance', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalea', 'nal')]:
articles = self.parse_section2(url, keystr)
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 - 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, keystr in [(u'\u5f71\u8996 Film/TV', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr + '&Category=nalma', 'nal')
]:
articles = self.parse_section2(url, keystr)
if articles:
feeds.append((title, articles))
if __InclCols__ == True:
# parse column section articles directly from .txt files
for title, url, keystr in [(u'\u5c08\u6b04 Columns', 'http://life.mingpao.com/cfm/dailynews2.cfm?Issue=' + dateStr +'&Category=ncolumn', 'ncl')
]:
articles = self.parse_section2_txt(url, keystr)
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))
elif __Region__ == 'Vancouver':
for title, url in [(u'\u8981\u805e Headline', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VAindex.htm'),
(u'\u52a0\u570b Canada', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VBindex.htm'),
(u'\u793e\u5340 Local', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VDindex.htm'),
(u'\u6e2f\u805e Hong Kong', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/HK-VGindex.htm'),
(u'\u570b\u969b World', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VTindex.htm'),
(u'\u4e2d\u570b China', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VCindex.htm'),
(u'\u7d93\u6fdf Economics', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VEindex.htm'),
(u'\u9ad4\u80b2 Sports', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/VSindex.htm'),
(u'\u5f71\u8996 Film/TV', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/HK-MAindex.htm'),
(u'\u526f\u520a Supplements', 'http://www.mingpaovan.com/htm/News/' + dateStr + '/WWindex.htm'),]:
articles = self.parse_section3(url, 'http://www.mingpaovan.com/')
if articles:
feeds.append((title, articles))
elif __Region__ == 'Toronto':
for title, url in [(u'\u8981\u805e Headline', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/TAindex.htm'),
(u'\u52a0\u570b Canada', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/TDindex.htm'),
(u'\u793e\u5340 Local', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/TFindex.htm'),
(u'\u4e2d\u570b China', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/TCAindex.htm'),
(u'\u570b\u969b World', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/TTAindex.htm'),
(u'\u6e2f\u805e Hong Kong', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/HK-GAindex.htm'),
(u'\u7d93\u6fdf Economics', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/THindex.htm'),
(u'\u9ad4\u80b2 Sports', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/TSindex.htm'),
(u'\u5f71\u8996 Film/TV', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/HK-MAindex.htm'),
(u'\u526f\u520a Supplements', 'http://www.mingpaotor.com/htm/News/' + dateStr + '/WWindex.htm'),]:
articles = self.parse_section3(url, 'http://www.mingpaotor.com/')
if articles:
feeds.append((title, articles))
return feeds
# 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
# replace the url to the print-friendly version
if __ParsePFF__ == True:
if url.rfind('Redirect') <> -1:
url = re.sub(dateStr + '.*' + dateStr, dateStr, url)
url = re.sub('%2F.*%2F', '/', url)
title = title.replace(u'\u6536\u8cbb\u5167\u5bb9', '')
url = url.replace('%2Etxt', '_print.htm')
url = url.replace('%5F', '_')
else:
url = url.replace('.htm', '_print.htm')
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 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):
url = url.replace('dailynews3.cfm', 'dailynews3a.cfm') # use printed version of the article
current_articles.append({'title': title, 'url': url, 'description': ''})
included_urls.append(url)
current_articles.reverse()
return current_articles
# parse from text file of life.mingpao.com
def parse_section2_txt(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):
url = url.replace('cfm/dailynews3.cfm?File=', 'ftp/Life3/') # use printed version of the article
current_articles.append({'title': title, 'url': url, 'description': ''})
included_urls.append(url)
current_articles.reverse()
return current_articles
# parse from www.mingpaovan.com
def parse_section3(self, url, baseUrl):
self.get_fetchdate()
soup = self.index_to_soup(url)
divs = soup.findAll(attrs={'class': ['ListContentLargeLink']})
current_articles = []
included_urls = []
divs.reverse()
for i in divs:
title = self.tag_to_string(i)
urlstr = i.get('href', False)
urlstr = baseUrl + '/' + urlstr.replace('../../../', '')
if urlstr not in included_urls:
current_articles.append({'title': title, 'url': urlstr, 'description': '', 'date': ''})
included_urls.append(urlstr)
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
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_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_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
# preprocess those .txt and javascript based files
def preprocess_raw_html(self, raw_html, url):
#raw_html = raw_html.replace(u'<p>\u3010', u'\u3010')
if __HiResImg__ == True:
# TODO: add a _ in front of an image url
if url.rfind('news.mingpao.com') > -1:
imglist = re.findall('src="?.*?jpg"', raw_html)
br = mechanize.Browser()
br.set_handle_redirect(False)
for img in imglist:
gifimg = img.replace('jpg"', 'gif"')
try:
br.open_novisit(url + "/../" + gifimg[5:len(gifimg)-1])
raw_html = raw_html.replace(img, gifimg)
except:
# find the location of the first _
pos = img.find('_')
if pos > -1:
# if found, insert _ after the first _
newimg = img[0:pos] + '_' + img[pos:]
raw_html = raw_html.replace(img, newimg)
else:
# if not found, insert _ after "
raw_html = raw_html.replace(img[1:], '"_' + img[1:])
elif url.rfind('life.mingpao.com') > -1:
imglist = re.findall('src=\'?.*?jpg\'', raw_html)
br = mechanize.Browser()
br.set_handle_redirect(False)
#print 'Img list: ', imglist, '\n'
for img in imglist:
gifimg = img.replace('jpg\'', 'gif\'')
try:
#print 'Original: ', url
#print 'To append: ', "/../" + gifimg[5:len(gifimg)-1]
gifurl = re.sub(r'dailynews.*txt', '', url)
#print 'newurl: ', gifurl + gifimg[5:len(gifimg)-1]
br.open_novisit(gifurl + gifimg[5:len(gifimg)-1])
#print 'URL: ', url + "/../" + gifimg[5:len(gifimg)-1]
#br.open_novisit(url + "/../" + gifimg[5:len(gifimg)-1])
raw_html = raw_html.replace(img, gifimg)
except:
#print 'GIF not found'
pos = img.rfind('/')
newimg = img[0:pos+1] + '_' + img[pos+1:]
#print 'newimg: ', newimg
raw_html = raw_html.replace(img, newimg)
if url.rfind('ftp') == -1 and url.rfind('_print.htm') == -1:
return raw_html
else:
if url.rfind('_print.htm') <> -1:
# javascript based file
splitter = re.compile(r'\n')
new_raw_html = '<html><head><title>Untitled</title></head>'
new_raw_html = new_raw_html + '<body>'
for item in splitter.split(raw_html):
if item.startswith('var heading1 ='):
heading = item.replace('var heading1 = \'', '')
heading = heading.replace('\'', '')
heading = heading.replace(';', '')
new_raw_html = new_raw_html + '<div class="heading">' + heading
if item.startswith('var heading2 ='):
heading = item.replace('var heading2 = \'', '')
heading = heading.replace('\'', '')
heading = heading.replace(';', '')
if heading <> '':
new_raw_html = new_raw_html + '<br>' + heading + '</div>'
else:
new_raw_html = new_raw_html + '</div>'
if item.startswith('var content ='):
content = item.replace("var content = ", '')
content = content.replace('\'', '')
content = content.replace(';', '')
new_raw_html = new_raw_html + '<div class="content">' + content + '</div>'
if item.startswith('var photocontent ='):
photo = item.replace('var photocontent = \'', '')
photo = photo.replace('\'', '')
photo = photo.replace(';', '')
photo = photo.replace('<tr>', '')
photo = photo.replace('<td>', '')
photo = photo.replace('</tr>', '')
photo = photo.replace('</td>', '<br>')
photo = photo.replace('class="photo"', '')
new_raw_html = new_raw_html + '<div class="images">' + photo + '</div>'
return new_raw_html + '</body></html>'
else:
# .txt based file
splitter = re.compile(r'\n') # Match non-digits
new_raw_html = '<html><head><title>Untitled</title></head><body><div class="images">'
next_is_img_txt = False
title_started = False
met_article_start_char = False
for item in splitter.split(raw_html):
if item.startswith(u'\u3010'):
met_article_start_char = True
new_raw_html = new_raw_html + '</div><div class="content"><p>' + item + '<p>\n'
else:
if next_is_img_txt == False:
if item.startswith('='):
next_is_img_txt = True
new_raw_html += '<img src="' + str(item)[1:].strip() + '.jpg" /><p>\n'
else:
if met_article_start_char == False:
if title_started == False:
new_raw_html = new_raw_html + '</div><div class="heading">' + item + '\n'
title_started = True
else:
new_raw_html = new_raw_html + item + '\n'
else:
new_raw_html = new_raw_html + item + '<p>\n'
else:
next_is_img_txt = False
new_raw_html = new_raw_html + item + '\n'
return new_raw_html + '</div></body></html>'
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 create_opf(self, feeds, dir=None):
if dir is None:
dir = self.output_dir
if __UseChineseTitle__ == True:
if __Region__ == 'Hong Kong':
title = u'\u660e\u5831 (\u9999\u6e2f)'
elif __Region__ == 'Vancouver':
title = u'\u660e\u5831 (\u6eab\u54e5\u83ef)'
elif __Region__ == 'Toronto':
title = u'\u660e\u5831 (\u591a\u502b\u591a)'
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)
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 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)
# Get masthead
mpath = getattr(self, 'masthead_path', None)
if mpath is not None and os.access(mpath, os.R_OK):
manifest.append(mpath)
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
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.')
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)
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)
|
|
|
 |
«
Previous Thread
|
Next Thread
»
|
Similar Threads
|
||||
| Thread | Thread Starter | Forum | Replies | Last Post |
| [Updated recipe] Ming Pao (明報) - Hong Kong (2011/09/21) | tylau0 | Recipes | 0 | 09-21-2011 07:13 AM |
| [Updated recipe] Ming Pao (明報) - Hong Kong (2011/09/20) | tylau0 | Recipes | 1 | 09-20-2011 06:56 PM |
| [Updated recipe] Ming Pao (明報) - Hong Kong (2011/06/26) | tylau0 | Recipes | 3 | 06-28-2011 12:17 PM |
| Updated Recipe: Ming Pao - Hong Kong (2011/03/08) | tylau0 | Recipes | 0 | 03-08-2011 07:25 PM |
| [Updated recipe] Ming Pao (明報) - Hong Kong (2011/02/28) | tylau0 | Recipes | 0 | 02-28-2011 07:57 AM |
All times are GMT -4. The time now is 03:45 AM.