|
onlinenewsreader.net
Posts: 328
Karma: 10143
Join Date: Dec 2009
Location: Phoenix, AZ & Victoria, BC
Device: Kindle 3, Kindle Fire, IPad3, iPhone4, Playbook, HTC Inspire
|
Macleans Magazine
Here is a recipe for Canada's Macleans Magazine. It is a weekly publication so the default setting for oldest_article is 7 days.
Code:
#!/usr/bin/env python
__license__ = 'GPL v3'
'''
macleans.ca
'''
import string, re
from calibre import strftime
from calibre.web.feeds.recipes import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup, Tag, NavigableString
from datetime import timedelta, datetime, date
class Macleans(BasicNewsRecipe):
title = u'Macleans Magazine'
__author__ = 'Nick Redding'
language = 'en_CA'
description = ('Macleans Magazine')
no_stylesheets = True
timefmt = ' [%b %d]'
# customization notes: delete sections you are not interested in
# set oldest_article to the maximum number of days back from today to include articles
sectionlist = [
['http://www2.macleans.ca/','Front Page'],
['http://www2.macleans.ca/category/canada/','Canada'],
['http://www2.macleans.ca/category/world-from-the-magazine/','World'],
['http://www2.macleans.ca/category/business','Business'],
['http://www2.macleans.ca/category/arts-culture/','Culture'],
['http://www2.macleans.ca/category/opinion','Opinion'],
['http://www2.macleans.ca/category/health-from-the-magazine/','Health'],
['http://www2.macleans.ca/category/environment-from-the-magazine/','Environment'],
['http://www2.macleans.ca/category/education/','On Campus'],
['http://www2.macleans.ca/category/travel-from-the-magazine/','Travel']
]
oldest_article = 7
# formatting for print version of articles
extra_css = '''h2{font-family:Times,serif; font-size:large;}
small {font-family:Times,serif; font-size:xx-small; list-style-type: none;}
'''
# tag handling for print version of articles
keep_only_tags = [dict(id='tw-print')]
remove_tags = [dict({'class':'postmetadata'})]
def get_browser(self):
br = BasicNewsRecipe.get_browser()
return br
def preprocess_html(self,soup):
for img_tag in soup.findAll('img'):
parent_tag = img_tag.parent
if parent_tag.name == 'a':
new_tag = Tag(soup,'p')
new_tag.insert(0,img_tag)
parent_tag.replaceWith(new_tag)
elif parent_tag.name == 'p':
if not self.tag_to_string(parent_tag) == '':
new_div = Tag(soup,'div')
new_tag = Tag(soup,'p')
new_tag.insert(0,img_tag)
parent_tag.replaceWith(new_div)
new_div.insert(0,new_tag)
new_div.insert(1,parent_tag)
return soup
def parse_index(self):
articles = {}
key = None
ans = []
def parse_index_page(page_url,page_title):
def decode_date(datestr):
dmysplit = datestr.strip().lower().split(',')
mdsplit = dmysplit[1].split()
m = ['january','february','march','april','may','june','july','august','september','october','november','december'].index(mdsplit[0])+1
d = int(mdsplit[1])
y = int(dmysplit[2].split()[0])
return date(y,m,d)
def article_title(tag):
atag = tag.find('a',href=True)
if not atag:
return ''
return self.tag_to_string(atag)
def article_url(tag):
atag = tag.find('a',href=True)
if not atag:
return ''
return atag['href']+'print/'
def article_description(tag):
for p_tag in tag.findAll('p'):
d = self.tag_to_string(p_tag,False)
if not d == '':
return d
return ''
def compound_h4_h3_title(tag):
if tag.h4:
if tag.h3:
return self.tag_to_string(tag.h4,False)+u'\u2014'+self.tag_to_string(tag.h3,False)
else:
return self.tag_to_string(tag.h4,False)
elif tag.h3:
return self.tag_to_string(tag.h3,False)
else:
return ''
def compound_h2_h4_title(tag):
if tag.h2:
if tag.h4:
return self.tag_to_string(tag.h2,False)+u'\u2014'+self.tag_to_string(tag.h4,False)
else:
return self.tag_to_string(tag.h2,False)
elif tag.h4:
return self.tag_to_string(tag.h4,False)
else:
return ''
def handle_article(header_tag, outer_tag):
if header_tag:
url = article_url(header_tag)
title = article_title(header_tag)
author_date_tag = outer_tag.h4
if author_date_tag:
author_date = self.tag_to_string(author_date_tag,False).split(' - ')
author = author_date[0].strip()
article_date = decode_date(author_date[1])
earliest_date = date.today() - timedelta(days=self.oldest_article)
if article_date < earliest_date:
self.log("Skipping article dated %s" % author_date[1])
else:
excerpt_div = outer_tag.find('div','excerpt')
if excerpt_div:
description = article_description(excerpt_div)
else:
description = ''
if not articles.has_key(page_title):
articles[page_title] = []
articles[page_title].append(dict(title=title,url=url,date=author_date[1],description=description,author=author,content=''))
def handle_category_article(cat, header_tag, outer_tag):
url = article_url(header_tag)
title = article_title(header_tag)
if not title == '':
title = cat+u'\u2014'+title
a_tag = outer_tag.find('span','authorLink')
if a_tag:
author = self.tag_to_string(a_tag,False)
a_tag.parent.extract()
else:
author = ''
description = article_description(outer_tag)
if not articles.has_key(page_title):
articles[page_title] = []
articles[page_title].append(dict(title=title,url=url,date='',description=description,author=author,content=''))
soup = self.index_to_soup(page_url)
if page_title == 'Front Page':
# special processing for the front page
top_stories = soup.find('div',{ "id" : "macleansFeatured" })
if top_stories:
for div_slide in top_stories.findAll('div','slide'):
url = article_url(div_slide)
div_title = div_slide.find('div','header')
if div_title:
title = self.tag_to_string(div_title,False)
else:
title = ''
description = article_description(div_slide)
if not articles.has_key(page_title):
articles[page_title] = []
articles[page_title].append(dict(title=title,url=url,date='',description=description,author='',content=''))
from_macleans = soup.find('div',{ "id" : "fromMacleans" })
if from_macleans:
for li_tag in from_macleans.findAll('li','fromMacleansArticle'):
title = compound_h4_h3_title(li_tag)
url = article_url(li_tag)
description = article_description(li_tag)
if not articles.has_key(page_title):
articles[page_title] = []
articles[page_title].append(dict(title=title,url=url,date='',description=description,author='',content=''))
blog_central = soup.find('div',{ "id" : "bloglist" })
if blog_central:
for li_tag in blog_central.findAll('li'):
title = compound_h2_h4_title(li_tag)
if li_tag.h4:
url = article_url(li_tag.h4)
if not articles.has_key(page_title):
articles[page_title] = []
articles[page_title].append(dict(title=title,url=url,date='',description='',author='',content=''))
# need_to_know = soup.find('div',{ "id" : "needToKnow" })
# if need_to_know:
# for div_tag in need_to_know('div',attrs={'class' : re.compile("^needToKnowArticle")}):
# title = compound_h4_h3_title(div_tag)
# url = article_url(div_tag)
# description = article_description(div_tag)
# if not articles.has_key(page_title):
# articles[page_title] = []
# articles[page_title].append(dict(title=title,url=url,date='',description=description,author='',content=''))
for news_category in soup.findAll('div','newsCategory'):
news_cat = self.tag_to_string(news_category.h4,False)
handle_category_article(news_cat, news_category.find('h2'), news_category.find('div'))
for news_item in news_category.findAll('li'):
handle_category_article(news_cat,news_item.h3,news_item)
return
# find the div containing the highlight article
div_post = soup.find('div','post')
if div_post:
h1_tag = div_post.h1
handle_article(h1_tag,div_post)
# find the divs containing the rest of the articles
div_other = div_post.find('div', { "id" : "categoryOtherPosts" })
if div_other:
for div_entry in div_other.findAll('div','entry'):
h2_tag = div_entry.h2
handle_article(h2_tag,div_entry)
for page_name,page_title in self.sectionlist:
parse_index_page(page_name,page_title)
ans.append(page_title)
ans = [(key, articles[key]) for key in ans if articles.has_key(key)]
return ans
|