Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update WSJ

Browse Source
This commit is contained in:
unkn0w7n 2024-06-26 18:54:39 +05:30
parent 62095818fa
commit e8d08955d6
2 changed files with 20 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
recipes/wsj.recipe
View File

@ -13,12 +13,16 @@ past_edition = None
def media_bucket(x): def media_bucket(x):
if x.get('type', '') == 'image': if x.get('type', '') == 'image':
return '<img src="{}"><div class="figc">{}</div>\n'.format( if x.get('subtype', '') == 'graphic':
x['manifest-url'], x['caption'] + '<i> ' + x['credit'] + '</i>' return '<br><img src="{}"><div class="figc">{}</div>\n'.format(
x['manifest-url'], x['caption'] + '<i> ' + x['credit'] + '</i>'
)
return '<br><img src="{}"><div class="figc">{}</div>\n'.format(
x['manifest-url'].split('?')[0] + '?width=600', x['caption'] + '<i> ' + x['credit'] + '</i>'
) )
if x.get('type', '') == 'video': if x.get('type', '') == 'video':
return '<a href="{}"><img src="{}"></a><div class="figc">{}</div>\n'.format( return '<br><a href="{}"><img src="{}"></a><div class="figc">{}</div>\n'.format(
x['share_link'], x['thumbnail_url'], x['caption'] + '<i> ' + x['credit'] + '</i>' x['share_link'], x['thumbnail_url'].split('?')[0] + '?width=600', x['caption'] + '<i> ' + x['credit'] + '</i>'
) )
return return
@ -90,7 +94,6 @@ class WSJ(BasicNewsRecipe):
m_itm = soup.findAll('panel', attrs={'class':'media-item'}) m_itm = soup.findAll('panel', attrs={'class':'media-item'})
if i_lst and m_itm: if i_lst and m_itm:
for x, y in list(zip_longest(m_itm, i_lst)): for x, y in list(zip_longest(m_itm, i_lst)):
x.name = 'p'
x.insert_after(BeautifulSoup(y, 'html.parser')) x.insert_after(BeautifulSoup(y, 'html.parser'))
return soup return soup
@ -141,9 +144,9 @@ class WSJ(BasicNewsRecipe):
break break
dt = datetime.fromisoformat(date[:-1]) + timedelta(seconds=time.timezone) dt = datetime.fromisoformat(date[:-1]) + timedelta(seconds=time.timezone)
dt = dt.strftime('%b %d, %Y') dt_ = dt.strftime('%b %d, %Y')
self.log('Downloading ', dt) self.log('Downloading ', dt_)
self.timefmt = ' [' + dt + ']' self.timefmt = ' [' + dt_ + ']'
feeds = [] feeds = []
@ -153,7 +156,7 @@ class WSJ(BasicNewsRecipe):
if '-pages_' in k: if '-pages_' in k:
section = k.split('-pages_')[0].replace('_', ' ') section = k.split('-pages_')[0].replace('_', ' ')
if 'MAGAZINE' in section: if 'MAGAZINE' in section:
if not datetime.now().strftime("%d") == 1: if not dt.strftime('%d') == 1:
continue continue
self.log('Loading Magazine section') self.log('Loading Magazine section')
self.log(section) self.log(section)

14
recipes/wsj_mag.recipe
View File

@ -9,16 +9,19 @@ from calibre.web.feeds.news import BasicNewsRecipe, classes
def media_bucket(x): def media_bucket(x):
if x.get('type', '') == 'image': if x.get('type', '') == 'image':
return '<img src="{}"><div class="figc">{}</div>\n'.format( if x.get('subtype', '') == 'graphic':
x['manifest-url'], x['caption'] + '<i> ' + x['credit'] + '</i>' return '<br><img src="{}"><div class="figc">{}</div>\n'.format(
x['manifest-url'], x['caption'] + '<i> ' + x['credit'] + '</i>'
)
return '<br><img src="{}"><div class="figc">{}</div>\n'.format(
x['manifest-url'].split('?')[0] + '?width=600', x['caption'] + '<i> ' + x['credit'] + '</i>'
) )
if x.get('type', '') == 'video': if x.get('type', '') == 'video':
return '<a href="{}"><img src="{}"></a><div class="figc">{}</div>\n'.format( return '<br><a href="{}"><img src="{}"></a><div class="figc">{}</div>\n'.format(
x['share_link'], x['thumbnail_url'], x['caption'] + '<i> ' + x['credit'] + '</i>' x['share_link'], x['thumbnail_url'].split('?')[0] + '?width=600', x['caption'] + '<i> ' + x['credit'] + '</i>'
) )
return return
class WSJ(BasicNewsRecipe): class WSJ(BasicNewsRecipe):
title = 'WSJ. Magazine' title = 'WSJ. Magazine'
__author__ = 'unkn0wn' __author__ = 'unkn0wn'
@ -87,7 +90,6 @@ class WSJ(BasicNewsRecipe):
m_itm = soup.findAll('panel', attrs={'class':'media-item'}) m_itm = soup.findAll('panel', attrs={'class':'media-item'})
if i_lst and m_itm: if i_lst and m_itm:
for x, y in list(zip_longest(m_itm, i_lst)): for x, y in list(zip_longest(m_itm, i_lst)):
x.name = 'p'
x.insert_after(BeautifulSoup(y, 'html.parser')) x.insert_after(BeautifulSoup(y, 'html.parser'))
return soup return soup