Bloomberg

This commit is contained in:
unkn0w7n 2024-07-20 09:47:42 +05:30
parent 365b80bd24
commit 115a287c21
2 changed files with 19 additions and 4 deletions

View File

@ -5,9 +5,6 @@ from datetime import datetime
from calibre.ebooks.BeautifulSoup import BeautifulSoup
from calibre.web.feeds.news import BasicNewsRecipe, classes
# https://www.bloomberg.com/magazine/businessweek/24_12
# Set past_edition to edition id, which is '24_12'.
past_edition = None
def get_contents(x):
if x == '':
@ -60,6 +57,13 @@ class Bloomberg(BasicNewsRecipe):
)
remove_empty_feeds = True
recipe_specific_options = {
'date': {
'short': 'The ID of the edition to download (YY_XX format)',
'long': 'For example, 24_17\nHint: Edition ID can be found at the end of its URL'
}
}
remove_tags = [
dict(name=['button', 'svg', 'meta']),
dict(name='div', attrs={'id':['bb-that', 'bb-nav']}),
@ -82,6 +86,7 @@ class Bloomberg(BasicNewsRecipe):
inx = 'https://cdn-mobapi.bloomberg.com'
sec = self.index_to_soup(inx + '/wssmobile/v1/bw/news/list?limit=1', raw=True)
id = json.loads(sec)['magazines'][0]['id']
past_edition = self.recipe_specific_options.get('date')
if past_edition:
id = past_edition
edit = self.index_to_soup(inx + '/wssmobile/v1/bw/news/week/' + id, raw=True)

View File

@ -55,7 +55,7 @@ class Bloomberg(BasicNewsRecipe):
'Bloomberg delivers business and markets news, data, analysis, and video'
' to the world, featuring stories from Businessweek and Bloomberg News.'
)
oldest_article = 1 # days
oldest_article = 1.2 # days
resolve_internal_links = True
remove_empty_feeds = True
cover_url = 'https://assets.bwbx.io/images/users/iqjWHBFdfxIU/ivUxvlPidC3M/v0/600x-1.jpg'
@ -78,7 +78,17 @@ class Bloomberg(BasicNewsRecipe):
.news-figure-credit {font-size:small; text-align:center; color:#202020;}
'''
recipe_specific_options = {
'days': {
'short': 'Oldest article to download from this news source. In days ',
'long': 'For example, 0.5, gives you articles for the past 12 hours'
}
}
def parse_index(self):
d = self.recipe_specific_options.get('days')
if d:
self.oldest_article = d
inx = 'https://cdn-mobapi.bloomberg.com'
sec = self.index_to_soup(inx + '/wssmobile/v1/navigation/bloomberg_app/search-v2', raw=True)
sec_data = json.loads(sec)['searchNav']