from calibre.web.feeds.news import BasicNewsRecipe, classes
from calibre import browser
import json
import re
class Bloomberg(BasicNewsRecipe):
title = u'Bloomberg Businessweek'
language = 'en'
__author__ = 'unkn0wn'
no_stylesheets = True
use_embedded_content = False
remove_attributes = ['style', 'height', 'width']
ignore_duplicate_articles = {'url'}
resolve_internal_links = True
masthead_url = 'https://assets.bwbx.io/s3/javelin/public/hub/images/BW-Logo-Black-cc9035fbb3.svg'
extra_css = '''
#auth {font-size:small;}
#subhead {font-style:italic; color:#404040;}
.news-figure-caption-text, #cap {font-size:small; text-align:center;}
.news-figure-credit {font-size:small; text-align:center; color:#202020;}
'''
def get_browser(self):
br = browser()
br.set_handle_redirect(False)
return br
def parse_index(self):
soup = self.index_to_soup('https://www.bloomberg.com/businessweek')
bw = soup.find('a', href=lambda x: x and x.startswith('/magazine/businessweek/'))
edition = 'https://www.bloomberg.com' + bw['href']
self.log('Downloading ', edition)
self.cover_url = bw.find('img')['src'].replace('25x19', '600x800')
soup = self.index_to_soup(edition)
timefmt = soup.find(**classes('section-front-header-module__title'))
if timefmt:
self.timefmt = ' [' + (self.tag_to_string(timefmt).replace('Issue', '')).strip() + ']'
feeds = []
for div in soup.findAll('div', attrs={'class':'story-list-module__info'}):
h3 = div.find('h3', attrs={'class':'story-list-module__title'})
sec = self.tag_to_string(h3)
self.log(sec)
articles = []
for art in div.findAll('article'):
a = art.find('a', **classes('story-list-story__info__headline-link'))
url = 'https://www.bloomberg.com' + a['href']
title = self.tag_to_string(a)
desc = ''
sum = art.find(**classes('story-list-story__info__summary'))
if sum:
desc = self.tag_to_string(sum).strip()
by = art.find(**classes('story-list-story__info__byline'))
if by:
desc = self.tag_to_string(by).strip() + ' | ' + desc
articles.append({'title': title, 'url': url, 'description': desc})
self.log('\t', title, '\n\t', desc, '\n\t\t', url)
if articles:
feeds.append((sec, articles))
return feeds
def preprocess_raw_html(self, raw, *a):
m = re.search('data-component-props="ArticleBody">', raw)
if not m:
m = re.search('data-component-props="FeatureBody">', raw)
raw = raw[m.start():]
raw = raw.split('>', 1)[1]
data = json.JSONDecoder().raw_decode(raw)[0]
data = data['story']
title = '' + data['headline'] + '
'
subhead = lede = auth = caption = ''
if data['summary']:
subhead = '' + data['summary'] + '
'
if data['authors']:
if len(data['authors']) != 0:
auth = '' + data['authors'][0]['name'] + ', ' + data['publishedAt'] + '
'
if data['ledeAttachment']:
if data['ledeAttachment']['alt']:
caption = '' + data['ledeAttachment']['alt'] + ''
try:
lede = '
'.format(data['ledeAttachment']['url'].replace('\\', ''))
except:
if 'baseUrl' in data['ledeAttachment']:
lede = '
'.format(data['ledeAttachment']['baseUrl'].replace('\\', ''))
body = data['body'].replace('\\n', '').replace('\\','')
html = '
' + title + subhead + auth + lede + caption + '' + body
return html
def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'data-native-src':True}):
img['src'] = img['data-native-src']
return soup