Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-06-23 15:30:45 -04:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' of https://github.com/unkn0w7n/calibre

Browse Source
This commit is contained in:
Kovid Goyal 2023-08-27 07:58:32 +05:30
commit fd25c117c5
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
3 changed files with 16 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
recipes/bloomberg-business-week.recipe
View File

@ -176,15 +176,16 @@ class Bloomberg(BasicNewsRecipe):
caption = '<span class="cap">' + data['lede']['alt'] + '</span>'
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 '<html><body>' + cat + title + subhead + auth + lede + caption + '<div>' + body + '</div></body></html>'
def preprocess_html(self, soup):

7
recipes/bloomberg.recipe
View File

@ -170,15 +170,16 @@ class Bloomberg(BasicNewsRecipe):
caption = '<span class="cap">' + data['lede']['alt'] + '</span>'
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 '<html><body>' + cat + title + subhead + auth + lede + caption + '<div>' + body + '</div></body></html>'
def preprocess_html(self, soup):

17
recipes/theeconomictimes_india_print_edition.recipe
View File

@ -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