From 365b80bd24f339c735ae1b5a01fe82153e73541e Mon Sep 17 00:00:00 2001 From: unkn0w7n <51942695+unkn0w7n@users.noreply.github.com> Date: Sat, 20 Jul 2024 09:47:15 +0530 Subject: [PATCH 1/2] Update hindu.recipe international edition as the default --- recipes/hindu.recipe | 47 ++++++++++++++++---------------------------- 1 file changed, 17 insertions(+), 30 deletions(-) diff --git a/recipes/hindu.recipe b/recipes/hindu.recipe index 616e123cdd..cb285f743b 100644 --- a/recipes/hindu.recipe +++ b/recipes/hindu.recipe @@ -60,10 +60,13 @@ class TheHindu(BasicNewsRecipe): return soup def parse_index(self): - mag_url = None + local_edition = self.recipe_specific_options.get('location') if local_edition: local_edition = 'th_' + local_edition + else: + local_edition = 'th_international' + past_edition = self.recipe_specific_options.get('date') dt = date.today() @@ -71,36 +74,20 @@ class TheHindu(BasicNewsRecipe): year, month, day = (int(x) for x in past_edition.split('-')) dt = date(year, month, day) - is_monday = dt.weekday() == 0 - is_friday = dt.weekday() == 4 - is_saturday = dt.weekday() == 5 - is_sunday = dt.weekday() == 6 + today = dt.strftime('%Y-%m-%d') + self.log('Downloading The Hindu, ' + local_edition[3:] + ' edition, ' + today) + url = absurl('/todays-paper/' + today + '/' + local_edition + '/') - if local_edition or past_edition: - if local_edition is None: - local_edition = 'th_chennai' - today = date.today().strftime('%Y-%m-%d') - if past_edition: - today = past_edition - self.log('Downloading past edition of', local_edition + ' from ' + today) - url = absurl('/todays-paper/' + today + '/' + local_edition + '/') - if is_monday: - mag_url = url + '?supplement=' + local_edition + '-epbs' - if is_saturday: - mag_url = url + '?supplement=' + local_edition + '-mp' - if is_sunday: - mag_url = url + '?supplement=' + local_edition + '-sm' - else: - url = 'https://www.thehindu.com/todays-paper/' - if is_monday: - mag_url = url + '?supplement=th_chennai-epbs' - if is_friday: - mag_url = url + '?supplement=th_chennai-fr' - if is_saturday: - mag_url = url + '?supplement=th_chennai-mp' - if is_sunday: - mag_url = url + '?supplement=th_chennai-sm' + mag_url = None + if dt.weekday() == 0: + mag_url = url + '?supplement=' + local_edition + '-epbs' + if dt.weekday() == 4: + mag_url = url + '?supplement=' + local_edition + '-fr' + if dt.weekday() == 5: + mag_url = url + '?supplement=' + local_edition + '-mp' + if dt.weekday() == 6: + mag_url = url + '?supplement=' + local_edition + '-sm' raw = self.index_to_soup(url, raw=True) soup = self.index_to_soup(raw) @@ -139,7 +126,7 @@ class TheHindu(BasicNewsRecipe): title = item['articleheadline'] url = absurl(item['href']) desc = 'Page no.' + item['pageno'] + ' | ' + item['teaser_text'] or '' - self.log('\t', title, '\n\t\t', url) + self.log(' ', title, '\n\t', url) feeds_dict[section].append({"title": title, "url": url, "description": desc}) return [(section, articles) for section, articles in feeds_dict.items()] else: From 115a287c2129247bae16eb44e1fcd921fa5d7fc8 Mon Sep 17 00:00:00 2001 From: unkn0w7n <51942695+unkn0w7n@users.noreply.github.com> Date: Sat, 20 Jul 2024 09:47:42 +0530 Subject: [PATCH 2/2] Bloomberg --- recipes/bloomberg-business-week.recipe | 11 ++++++++--- recipes/bloomberg.recipe | 12 +++++++++++- 2 files changed, 19 insertions(+), 4 deletions(-) diff --git a/recipes/bloomberg-business-week.recipe b/recipes/bloomberg-business-week.recipe index 3d94f6868a..5cf8d4d5b0 100644 --- a/recipes/bloomberg-business-week.recipe +++ b/recipes/bloomberg-business-week.recipe @@ -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) diff --git a/recipes/bloomberg.recipe b/recipes/bloomberg.recipe index 3a9557570b..f34278ab9c 100644 --- a/recipes/bloomberg.recipe +++ b/recipes/bloomberg.recipe @@ -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']