mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-08-11 09:13:57 -04:00
Fix #1008276 (New recipe for The Christian Science Monitor)
This commit is contained in:
Kovid Goyal
parent
71ea547f06
commit
acf009ad35
@ -1,152 +1,111 @@
|
||||
#!/usr/bin/env python
|
||||
__license__ = 'GPL v3'
|
||||
__author__ = 'Kovid Goyal and Sujata Raman, Lorenzo Vigentini'
|
||||
__copyright__ = '2009, Kovid Goyal and Sujata Raman'
|
||||
__version__ = 'v1.02'
|
||||
__date__ = '10, January 2010'
|
||||
__description__ = 'Providing context and clarity on national and international news, peoples and cultures'
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2012, Darko Miletic <darko.miletic at gmail.com>'
|
||||
'''
|
||||
www.csmonitor.com
|
||||
'''
|
||||
|
||||
'''csmonitor.com'''
|
||||
|
||||
import re
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
from calibre.ebooks.BeautifulSoup import BeautifulSoup
|
||||
|
||||
|
||||
class ChristianScienceMonitor(BasicNewsRecipe):
|
||||
|
||||
__author__ = 'Kovid Goyal'
|
||||
description = 'Providing context and clarity on national and international news, peoples and cultures'
|
||||
|
||||
cover_url = 'http://www.csmonitor.com/extension/csm_base/design/csm_design/images/csmlogo_179x46.gif'
|
||||
title = 'Christian Science Monitor'
|
||||
publisher = 'The Christian Science Monitor'
|
||||
category = 'News, politics, culture, economy, general interest'
|
||||
|
||||
language = 'en'
|
||||
encoding = 'utf-8'
|
||||
timefmt = '[%a, %d %b, %Y]'
|
||||
|
||||
oldest_article = 16
|
||||
max_articles_per_feed = 20
|
||||
class CSMonitor(BasicNewsRecipe):
|
||||
title = 'The Christian Science Monitor - daily'
|
||||
__author__ = 'Darko Miletic'
|
||||
description = 'The Christian Science Monitor is an international news organization that delivers thoughtful, global coverage via its website, weekly magazine, daily news briefing, and email newsletters.'
|
||||
publisher = 'The Christian Science Monitor'
|
||||
category = 'news, politics, USA'
|
||||
oldest_article = 2
|
||||
max_articles_per_feed = 200
|
||||
no_stylesheets = True
|
||||
encoding = 'utf8'
|
||||
use_embedded_content = False
|
||||
recursion = 10
|
||||
language = 'en'
|
||||
remove_empty_feeds = True
|
||||
publication_type = 'newspaper'
|
||||
masthead_url = 'http://www.csmonitor.com/extension/csm_base/design/csm_design/images/csmlogo_179x46.gif'
|
||||
extra_css = """
|
||||
body{font-family: Arial,Tahoma,Verdana,Helvetica,sans-serif }
|
||||
img{margin-bottom: 0.4em; display:block}
|
||||
.head {font-family: Georgia,"Times New Roman",Times,serif}
|
||||
.sByline,.caption{font-size: x-small}
|
||||
.hide{display: none}
|
||||
.sLoc{font-weight: bold}
|
||||
ul{list-style-type: none}
|
||||
"""
|
||||
|
||||
remove_javascript = True
|
||||
no_stylesheets = True
|
||||
requires_version = (0, 8, 39)
|
||||
conversion_options = {
|
||||
'comment' : description
|
||||
, 'tags' : category
|
||||
, 'publisher' : publisher
|
||||
, 'language' : language
|
||||
}
|
||||
|
||||
def preprocess_raw_html(self, raw, url):
|
||||
try:
|
||||
from html5lib import parse
|
||||
root = parse(raw, namespaceHTMLElements=False,
|
||||
treebuilder='lxml').getroot()
|
||||
from lxml import etree
|
||||
for tag in root.xpath(
|
||||
'//script|//style|//noscript|//meta|//link|//object'):
|
||||
tag.getparent().remove(tag)
|
||||
for elem in list(root.iterdescendants(tag=etree.Comment)):
|
||||
elem.getparent().remove(elem)
|
||||
ans = etree.tostring(root, encoding=unicode)
|
||||
ans = re.sub('.*<html', '<html', ans, flags=re.DOTALL)
|
||||
return ans
|
||||
except:
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
raise
|
||||
remove_tags = [
|
||||
dict(name=['meta','link','iframe','object','embed'])
|
||||
,dict(attrs={'class':['podStoryRel','bottom-rel','hide']})
|
||||
,dict(attrs={'id':['pgallerycarousel_enlarge','pgallerycarousel_related']})
|
||||
]
|
||||
keep_only_tags = [
|
||||
dict(name='h1', attrs={'class':'head'})
|
||||
,dict(name='h2', attrs={'class':'subhead'})
|
||||
,dict(attrs={'class':['sByline','podStoryGal','ui-body-header','sBody']})
|
||||
]
|
||||
remove_attributes=['xmlns:fb']
|
||||
|
||||
def index_to_soup(self, url):
|
||||
raw = BasicNewsRecipe.index_to_soup(self, url,
|
||||
raw=True).decode('utf-8')
|
||||
raw = self.preprocess_raw_html(raw, url)
|
||||
return BasicNewsRecipe.index_to_soup(self, raw)
|
||||
|
||||
def append_page(self, soup, appendtag, position):
|
||||
nav = soup.find('div',attrs={'class':'navigation'})
|
||||
if nav:
|
||||
pager = nav.findAll('a')
|
||||
for part in pager:
|
||||
if 'Next' in part:
|
||||
nexturl = ('http://www.csmonitor.com' +
|
||||
re.findall(r'href="(.*?)"', str(part))[0])
|
||||
soup2 = self.index_to_soup(nexturl)
|
||||
texttag = soup2.find('div',
|
||||
attrs={'class': re.compile('list-article-.*')})
|
||||
trash_c = soup2.findAll(attrs={'class': 'list-description'})
|
||||
trash_h = soup2.h1
|
||||
for tc in trash_c: tc.extract()
|
||||
trash_h.extract()
|
||||
|
||||
newpos = len(texttag.contents)
|
||||
self.append_page(soup2, texttag, newpos)
|
||||
texttag.extract()
|
||||
appendtag.insert(position, texttag)
|
||||
feeds = [
|
||||
(u'USA' , u'http://rss.csmonitor.com/feeds/usa' )
|
||||
,(u'World' , u'http://rss.csmonitor.com/feeds/world' )
|
||||
,(u'Politics' , u'http://rss.csmonitor.com/feeds/politics' )
|
||||
,(u'Business' , u'http://rss.csmonitor.com/feeds/wam' )
|
||||
,(u'Commentary' , u'http://rss.csmonitor.com/feeds/commentary' )
|
||||
,(u'Books' , u'http://rss.csmonitor.com/feeds/books' )
|
||||
,(u'Arts' , u'http://rss.csmonitor.com/feeds/arts' )
|
||||
,(u'Environment' , u'http://rss.csmonitor.com/feeds/environment')
|
||||
,(u'Innovation' , u'http://rss.csmonitor.com/feeds/scitech' )
|
||||
,(u'Living' , u'http://rss.csmonitor.com/feeds/living' )
|
||||
,(u'Science' , u'http://rss.csmonitor.com/feeds/science' )
|
||||
,(u'The Culture' , u'http://rss.csmonitor.com/feeds/theculture' )
|
||||
,(u'The Home Forum', u'http://rss.csmonitor.com/feeds/homeforum' )
|
||||
,(u'Articles' , u'http://rss.csmonitor.com/feeds/csarticles' )
|
||||
]
|
||||
|
||||
def append_page(self, soup):
|
||||
pager = soup.find('div', attrs={'class':'navigation'})
|
||||
if pager:
|
||||
nexttag = pager.find(attrs={'id':'next-button'})
|
||||
if nexttag:
|
||||
nurl = 'http://www.csmonitor.com' + nexttag['href']
|
||||
soup2 = self.index_to_soup(nurl)
|
||||
texttag = soup2.find(attrs={'class':'sBody'})
|
||||
if texttag:
|
||||
appendtag = soup.find(attrs={'class':'sBody'})
|
||||
for citem in texttag.findAll(attrs={'class':['podStoryRel','bottom-rel','hide']}):
|
||||
citem.extract()
|
||||
self.append_page(soup2)
|
||||
texttag.extract()
|
||||
pager.extract()
|
||||
appendtag.append(texttag)
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
PRINT_RE = re.compile(r'/layout/set/print/content/view/print/[0-9]*')
|
||||
html = str(soup)
|
||||
try:
|
||||
print_found = PRINT_RE.findall(html)
|
||||
except Exception:
|
||||
pass
|
||||
if print_found:
|
||||
print_url = 'http://www.csmonitor.com' + print_found[0]
|
||||
print_soup = self.index_to_soup(print_url)
|
||||
else:
|
||||
self.append_page(soup, soup.body, 3)
|
||||
|
||||
trash_a = soup.findAll(attrs={'class': re.compile('navigation.*')})
|
||||
trash_b = soup.findAll(attrs={'style': re.compile('.*')})
|
||||
trash_d = soup.findAll(attrs={'class': 'sByline'})
|
||||
for ta in trash_a: ta.extract()
|
||||
for tb in trash_b: tb.extract()
|
||||
for td in trash_d: td.extract()
|
||||
|
||||
print_soup = soup
|
||||
return print_soup
|
||||
|
||||
extra_css = '''
|
||||
h1{ color:#000000;font-family: Georgia,Times,"Times New Roman",serif; font-size: large}
|
||||
.sub{ color:#000000;font-family: Georgia,Times,"Times New Roman",serif; font-size: small;}
|
||||
.byline{ font-family:Arial,Helvetica,sans-serif ; color:#999999; font-size: x-small;}
|
||||
.postdate{color:#999999 ; font-family:Arial,Helvetica,sans-serif ; font-size: x-small; }
|
||||
h3{color:#999999 ; font-family:Arial,Helvetica,sans-serif ; font-size: x-small; }
|
||||
.photoCutline{ color:#333333 ; font-family:Arial,Helvetica,sans-serif ; font-size: x-small; }
|
||||
.photoCredit{ color:#999999 ; font-family:Arial,Helvetica,sans-serif ; font-size: x-small; }
|
||||
#story{font-family:Arial,Tahoma,Verdana,Helvetica,sans-serif ; font-size: small; }
|
||||
#main{font-family:Arial,Tahoma,Verdana,Helvetica,sans-serif ; font-size: small; }
|
||||
#photo-details{ font-family:Arial,Helvetica,sans-serif ; color:#999999; font-size: x-small;}
|
||||
span.name{color:#205B87;font-family: Georgia,Times,"Times New Roman",serif; font-size: x-small}
|
||||
p#dateline{color:#444444 ; font-family:Arial,Helvetica,sans-serif ; font-style:italic;} '''
|
||||
|
||||
feeds = [(u'Top Stories', u'http://rss.csmonitor.com/feeds/top'),
|
||||
(u'World' , u'http://rss.csmonitor.com/feeds/world'),
|
||||
(u'USA' , u'http://rss.csmonitor.com/feeds/usa'),
|
||||
(u'Commentary' , u'http://rss.csmonitor.com/feeds/commentary'),
|
||||
(u'Money' , u'http://rss.csmonitor.com/feeds/wam'),
|
||||
(u'Learning' , u'http://rss.csmonitor.com/feeds/learning'),
|
||||
(u'Living', u'http://rss.csmonitor.com/feeds/living'),
|
||||
(u'Innovation', u'http://rss.csmonitor.com/feeds/scitech'),
|
||||
(u'Gardening', u'http://rss.csmonitor.com/feeds/gardening'),
|
||||
(u'Environment',u'http://rss.csmonitor.com/feeds/environment'),
|
||||
(u'Arts', u'http://rss.csmonitor.com/feeds/arts'),
|
||||
(u'Books', u'http://rss.csmonitor.com/feeds/books'),
|
||||
(u'Home Forum' , u'http://rss.csmonitor.com/feeds/homeforum')
|
||||
]
|
||||
|
||||
keep_only_tags = [dict(name='div', attrs={'id':'mainColumn'}), ]
|
||||
|
||||
remove_tags = [
|
||||
dict(name='div', attrs={'id':['story-tools','videoPlayer','storyRelatedBottom','enlarge-photo','photo-paginate']}),
|
||||
dict(name=['div','a'], attrs={'class':
|
||||
['storyToolbar cfx','podStoryRel','spacer3',
|
||||
'divvy spacer7','comment','storyIncludeBottom',
|
||||
'hide', 'podBrdr']}),
|
||||
dict(name='ul', attrs={'class':[ 'centerliststories']}) ,
|
||||
dict(name='form', attrs={'id':[ 'commentform']}) ,
|
||||
dict(name='div', attrs={'class': ['ui-comments']})
|
||||
]
|
||||
|
||||
remove_tags_after = [ dict(name='div', attrs={'class':[ 'ad csmAd']}),
|
||||
dict(name='div', attrs={'class': [re.compile('navigation.*')]}),
|
||||
dict(name='div', attrs={'style': [re.compile('.*')]})
|
||||
]
|
||||
self.append_page(soup)
|
||||
pager = soup.find('div', attrs={'class':'navigation'})
|
||||
if pager:
|
||||
pager.extract()
|
||||
for item in soup.findAll('a'):
|
||||
limg = item.find('img')
|
||||
if item.string is not None:
|
||||
str = item.string
|
||||
item.replaceWith(str)
|
||||
else:
|
||||
if limg:
|
||||
item.name = 'div'
|
||||
item.attrs = []
|
||||
else:
|
||||
str = self.tag_to_string(item)
|
||||
item.replaceWith(str)
|
||||
for item in soup.findAll('img'):
|
||||
if 'scorecardresearch' in item['src']:
|
||||
item.extract()
|
||||
else:
|
||||
if not item.has_key('alt'):
|
||||
item['alt'] = 'image'
|
||||
return soup
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user