From 37e21f78eeafada7ceb9fe448bde6fb9983f6a26 Mon Sep 17 00:00:00 2001
From: unkn0w7n <51942695+unkn0w7n@users.noreply.github.com>
Date: Sat, 26 Aug 2023 13:15:29 +0530
Subject: [PATCH 1/2] Update theeconomictimes_india_print_edition.recipe
---
.../theeconomictimes_india_print_edition.recipe | 17 ++++++++---------
1 file changed, 8 insertions(+), 9 deletions(-)
diff --git a/recipes/theeconomictimes_india_print_edition.recipe b/recipes/theeconomictimes_india_print_edition.recipe
index 35e358b7e9..c610386a3e 100644
--- a/recipes/theeconomictimes_india_print_edition.recipe
+++ b/recipes/theeconomictimes_india_print_edition.recipe
@@ -22,8 +22,9 @@ class TheEconomicTimes(BasicNewsRecipe):
masthead_url = 'https://upload.wikimedia.org/wikipedia/commons/9/98/The_Economic_Times_logo.svg'
ignore_duplicate_articles = {'title', 'url'}
extra_css = '''
- .summary {color:#404040; font-style:italic;}
- time{font-size:small;}
+ .artByline {font-size:small;}
+ .artImg, .imgBox {font-size:small; color:#202020; text-align:center;}
+ img {display:block; margin:0 auto;}
'''
def get_cover_url(self):
@@ -45,13 +46,14 @@ class TheEconomicTimes(BasicNewsRecipe):
keep_only_tags = [
dict(name='h1'),
classes(
- 'artByline artSyn artImg artText publisher publish_on slideshowPackage'
+ 'artByline pageContent'
),
]
remove_tags = [
+ dict(name='button'),
classes(
- 'story_title storyCollection shareBar sr_widget_free jsSrWidgetFree srwidgetfree_3'
- ' sr_paid jsSrWidgetPaid ar_wrp arwd_ld_chk adBox custom_ad mgid orn_free_r bold'
+ 'story_title storyCollection shareBar sr_widget_free jsSrWidgetFree srwidgetfree_3 showWhatsMsg artSyn'
+ ' sr_paid jsSrWidgetPaid ar_wrp arwd_ld_chk adBox custom_ad mgid orn_free_r bold primeSWrapper external_widget'
),
]
@@ -95,11 +97,8 @@ class TheEconomicTimes(BasicNewsRecipe):
return feeds
def preprocess_html(self, soup):
- h2 = soup.find(**classes('summary'))
- if h2:
- h2.name = 'p'
for image in soup.findAll('img', attrs={'src': True}):
image['src'] = image['src'].replace("width-300", "width-640")
for img in soup.findAll('img', attrs={'data-original': True}):
- img['src'] = img['data-original'].replace('photo', 'thumb').replace('quality-100', 'quality-100,width-600,resizemode-4')
+ img['src'] = img['data-original']
return soup
From 04638feeb9fa99a24e4d385d43e0f39d60d56113 Mon Sep 17 00:00:00 2001
From: unkn0w7n <51942695+unkn0w7n@users.noreply.github.com>
Date: Sat, 26 Aug 2023 13:17:01 +0530
Subject: [PATCH 2/2] Bloomberg
---
recipes/bloomberg-business-week.recipe | 7 ++++---
recipes/bloomberg.recipe | 7 ++++---
2 files changed, 8 insertions(+), 6 deletions(-)
diff --git a/recipes/bloomberg-business-week.recipe b/recipes/bloomberg-business-week.recipe
index 593a548bec..e9812e7157 100644
--- a/recipes/bloomberg-business-week.recipe
+++ b/recipes/bloomberg-business-week.recipe
@@ -176,15 +176,16 @@ class Bloomberg(BasicNewsRecipe):
caption = '' + data['lede']['alt'] + ''
if m:
- time.sleep(10)
+ time.sleep(5)
body = data['body']
else:
body = ''
body_data = data['body']['content']
for x in body_data:
- pause = random.choice((0.25, 0.5, 0.75, 1))
- time.sleep(pause)
body += get_contents(x)
+ pause = random.choice((4, 5, 6, 7, 8, 9))
+ self.log('Delay: ', pause, ' seconds')
+ time.sleep(pause)
return '' + cat + title + subhead + auth + lede + caption + '' + body + '
'
def preprocess_html(self, soup):
diff --git a/recipes/bloomberg.recipe b/recipes/bloomberg.recipe
index ac7e0f851e..b7ee45be05 100644
--- a/recipes/bloomberg.recipe
+++ b/recipes/bloomberg.recipe
@@ -170,15 +170,16 @@ class Bloomberg(BasicNewsRecipe):
caption = '' + data['lede']['alt'] + ''
if m:
- time.sleep(3)
+ time.sleep(5)
body = data['body']
elif m2:
body = ''
body_data = data['body']['content']
for x in body_data:
- pause = random.choice((0.25, 0.5, 0.75, 1))
- time.sleep(pause)
body += get_contents(x)
+ pause = random.choice((4, 5, 6, 7, 8, 9))
+ self.log('Delay: ', pause, ' seconds')
+ time.sleep(pause)
return '' + cat + title + subhead + auth + lede + caption + '' + body + '
'
def preprocess_html(self, soup):