mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
74 lines
3.0 KiB
Plaintext
74 lines
3.0 KiB
Plaintext
import re
|
|
from calibre.web.feeds.recipes import BasicNewsRecipe
|
|
from collections import OrderedDict
|
|
|
|
class BusinessWeekMagazine(BasicNewsRecipe):
|
|
|
|
title = 'Business Week Magazine'
|
|
__author__ = 'Rick Shang, Armin Geller' # AGE Upd 2014-01-18
|
|
|
|
description = 'A renowned business publication. Business news, trends and profiles of successful businesspeople.'
|
|
language = 'en'
|
|
category = 'news'
|
|
encoding = 'UTF-8'
|
|
keep_only_tags = [
|
|
dict(name='div', attrs={'id':['content']}), # AGE 2014-01-18
|
|
]
|
|
remove_tags = [dict(name='hr'),
|
|
dict(name='a', attrs={'class':'sub_sales'}),
|
|
dict(name='div', attrs={'class':'fieldset'}),
|
|
dict(name='div', attrs={'id':'taboola_wrapper'})] # AGE 2014-01-18
|
|
no_javascript = True
|
|
no_stylesheets = True
|
|
|
|
cover_url = 'http://images.businessweek.com/mz/covers/current_120x160.jpg'
|
|
|
|
def parse_index(self):
|
|
# Go to the issue
|
|
soup = self.index_to_soup('http://www.businessweek.com/magazine/news/articles/business_news.htm')
|
|
|
|
# Find date
|
|
mag=soup.find('h2',text='Magazine')
|
|
dates=self.tag_to_string(mag.findNext('h3'))
|
|
self.timefmt = u' [%s]'%dates
|
|
|
|
# Go to the main body
|
|
div0 = soup.find('div', attrs={'class':'column left'})
|
|
section_title = ''
|
|
feeds = OrderedDict()
|
|
for div in div0.findAll('a', attrs={'class': None}):
|
|
articles = []
|
|
section_title = self.tag_to_string(div.findPrevious('h3')).strip()
|
|
title=self.tag_to_string(div).strip()
|
|
url=div['href']
|
|
soup0 = self.index_to_soup(url)
|
|
urlprint=soup0.find('a', attrs={'href':re.compile('.*printer.*')})
|
|
if urlprint is not None:
|
|
url=urlprint['href']
|
|
articles.append({'title':title, 'url':url, 'description':'', 'date':''})
|
|
|
|
if articles:
|
|
if section_title not in feeds:
|
|
feeds[section_title] = []
|
|
feeds[section_title] += articles
|
|
div1 = soup.find('div', attrs={'class':'column center'})
|
|
section_title = ''
|
|
for div in div1.findAll('a'):
|
|
articles = []
|
|
desc=self.tag_to_string(div.findNext('p')).strip()
|
|
section_title = self.tag_to_string(div.findPrevious('h3')).strip()
|
|
title=self.tag_to_string(div).strip()
|
|
url=div['href']
|
|
soup0 = self.index_to_soup(url)
|
|
urlprint=soup0.find('a', attrs={'href':re.compile('.*printer.*')})
|
|
if urlprint is not None:
|
|
url=urlprint['href']
|
|
articles.append({'title':title, 'url':url, 'description':desc, 'date':''})
|
|
if articles:
|
|
if section_title not in feeds:
|
|
feeds[section_title] = []
|
|
feeds[section_title] += articles
|
|
|
|
ans = [(key, val) for key, val in feeds.iteritems()]
|
|
return ans
|