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

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

Browse Source
This commit is contained in:
Kovid Goyal 2024-01-03 11:27:37 +05:30
commit f8f4f80fe4
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
2 changed files with 19 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
recipes/business_standard.recipe
View File

@ -13,7 +13,7 @@ class BusinessStandard(BasicNewsRecipe):
no_stylesheets = True
remove_javascript = True
remove_attributes = ['width', 'height', 'style']
remove_attributes = ['width', 'height', 'float', 'style']
def get_cover_url(self):
soup = self.index_to_soup('https://www.magzter.com/IN/Business-Standard-Private-Ltd/Business-Standard/Newspaper/')
@ -67,7 +67,7 @@ class BusinessStandard(BasicNewsRecipe):
def preprocess_raw_html(self, raw, *a):
root = parse(raw)
m = root.xpath('//script[@id="__NEXT_DATA__"]')
data = json.loads(m[0].text)
img_url = None
@ -75,7 +75,7 @@ class BusinessStandard(BasicNewsRecipe):
img_url = data['props']['pageProps']['articleSchema']['articleImageUrl']
art_url = 'https://www.business-standard.com' + data['props']['pageProps']['url']
data = data['props']['pageProps']['data']
title = '<h1 title="{}">'.format(art_url) + data['pageTitle'] + '</h1>'
@ -92,8 +92,11 @@ class BusinessStandard(BasicNewsRecipe):
date = (datetime.fromtimestamp(int(data['publishDate']))).strftime('%b %d, %Y | %I:%M %p')
if 'multiple_authors_name' in data:
auth = '<div><p class="auth">' + data['multiple_authors_name'] + ' | ' + data['placeName'] + ' | ' + date + '</p></div>'
authors = []
if 'articleMappedMultipleAuthors' in data:
for aut in data['articleMappedMultipleAuthors']:
authors.append(data['articleMappedMultipleAuthors'][str(aut)])
auth = '<div><p class="auth">' + ', '.join(authors) + ' | ' + data['placeName'] + ' | ' + date + '</p></div>'
if 'featuredImageObj' in data:
if 'url' in data['featuredImageObj']:

15
recipes/business_standard_print.recipe
View File

@ -23,7 +23,7 @@ class BusinessStandardPrint(BasicNewsRecipe):
no_stylesheets = True
remove_javascript = True
remove_attributes = ['width', 'height', 'style']
remove_attributes = ['width', 'height', 'float', 'style']
def __init__(self, *args, **kwargs):
BasicNewsRecipe.__init__(self, *args, **kwargs)
@ -43,6 +43,11 @@ class BusinessStandardPrint(BasicNewsRecipe):
.cap { font-size:small; text-align:center; }
'''
def get_cover_url(self):
soup = self.index_to_soup('https://www.magzter.com/IN/Business-Standard-Private-Ltd/Business-Standard/Newspaper/')
for citem in soup.findAll('meta', content=lambda s: s and s.endswith('view/3.jpg')):
return citem['content']
def parse_index(self):
if dt.weekday() == 6:
self.log.warn(
@ -58,7 +63,6 @@ class BusinessStandardPrint(BasicNewsRecipe):
for section in data:
if section == 'EpaperImage':
self.cover_url = data[section]['url']
continue
self.log(section)
articles = []
@ -100,8 +104,11 @@ class BusinessStandardPrint(BasicNewsRecipe):
date = (datetime.fromtimestamp(int(data['publishDate']))).strftime('%b %d, %Y | %I:%M %p')
if 'multiple_authors_name' in data:
auth = '<div><p class="auth">' + data['multiple_authors_name'] + ' | ' + data['placeName'] + ' | ' + date + '</p></div>'
authors = []
if 'articleMappedMultipleAuthors' in data:
for aut in data['articleMappedMultipleAuthors']:
authors.append(data['articleMappedMultipleAuthors'][str(aut)])
auth = '<div><p class="auth">' + ', '.join(authors) + ' | ' + data['placeName'] + ' | ' + date + '</p></div>'
if 'featuredImageObj' in data:
if 'url' in data['featuredImageObj']: