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 Outlook Business Magazine

Browse Source
This commit is contained in:
Kovid Goyal 2022-08-14 10:28:47 +05:30
parent d380be1e1e
commit 8fcb834e4d
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 49 additions and 41 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

90
recipes/outlook_business_magazine.recipe
View File

@ -18,53 +18,61 @@ class outlook(BasicNewsRecipe):
remove_attributes = ['height', 'width', 'style']
ignore_duplicate_articles = {'url'}
masthead_url = 'https://imgnew.outlookindia.com/uploadimage/library/free_files/jpg/logo_2022_04_30_092331.jpg'
resolve_internal_links = True
keep_only_tags = [classes('__story_detail')]
remove_tags = [
classes(
'social_sharing_article left_trending left-sticky __tag_links next_prev_stories downarrow uparrow more_from_author_links next prev'
)
]
extra_css = '.author{font-size:small;}'
def parse_index(self):
soup = self.index_to_soup('https://business.outlookindia.com')
a = soup.find('a', href=lambda x: x and x.startswith('/magazine/issue/'))
url = a['href']
self.log('Downloading issue:', url)
soup = self.index_to_soup('https://business.outlookindia.com' + url)
cover = soup.find(**classes('listingPage_lead_story'))
self.cover_url = cover.find('img', attrs={'src': True})['src']
soup = self.index_to_soup('https://www.outlookbusiness.com/magazine/')
div = soup.find('div', attrs={'class': 'SplWapper'})
url = div.find('a', href=True)['href']
self.cover_url = div.find('img', srcset=True)['srcset']
self.timefmt = '[' + self.tag_to_string(div.find('h6')) + ']'
soup = self.index_to_soup('https://www.outlookbusiness.com' + url)
ans = []
for h3 in soup.findAll(['h3', 'h4'],
attrs={'class': 'tk-kepler-std-condensed-subhead'}):
a = h3.find('a', href=lambda x: x)
url = a['href']
title = self.tag_to_string(a)
desc = ''
p = h3.find_next_sibling('p')
if p:
desc = self.tag_to_string(p)
self.log('\t', title)
self.log('\t', desc)
self.log('\t\t', url)
ans.append({'title': title, 'url': url, 'description': desc})
for section in soup.findAll(**classes('category-banner-content')):
p = section.find(
'p',
attrs={'class': lambda x: x and x.startswith('styled__Content')}
)
desc = self.tag_to_string(p)
head = section.find(
'p',
attrs={'class': lambda x: x and x.startswith('styled__Heading')}
)
title = self.tag_to_string(head)
a = p.findParent('a', href=True)['href']
if a.startswith('/'):
url = 'https://www.outlookbusiness.com' + a
self.log('\t', title, '\n\t', desc, '\n\t\t', url)
ans.append({'title': title, 'description': desc, 'url': url})
return [('Articles', ans)]
def preprocess_raw_html(self, raw, *a):
return raw
m = re.search('<!-- NewsArticle Schema -->.*?script.*?>', raw, flags=re.DOTALL)
raw = raw[m.end():].lstrip()
m = re.search('id="__NEXT_DATA__" type="application/json">', raw)
raw = raw[m.start():]
raw = raw.split('>', 1)[1]
data = json.JSONDecoder().raw_decode(raw)[0]
title = data['headline']
body = data['articleBody']
body = body.replace('\r\n', '<p>')
author = ' and '.join(x['name'] for x in data['author'])
image = desc = ''
if data.get('image'):
image = '<p><img src="{}">'.format(data['image']['url'])
if data.get('description'):
desc = '<h2>' + data['description'] + '</h2>'
html = '<html><body><h1>' + title + '</h1>' + desc + '<h3>' + author + '</h3>' + image + '<p>' + body
data = data['props']['initialState']['dashboard']['ARTICLE_POST_DETAIL_API'][
'data']['article_data']
title = data['title']
body = data['description']
cat = desc = image = author = ''
if 'category_name' in data:
try:
cat = data['category_name']
except Exception:
cat = ''
if 'excerpt' in data:
desc = '<h4>' + data['excerpt'] + '</h4>'
if 'author' in data:
try:
author = data['author'][0]['name']
except Exception:
author = ''
if 'images' in data:
try:
image = '<p><img src="{}">'.format(data['images'][0]['image'])
except Exception:
image = ''
html = '<html><body>' + cat + '<h1>' + title + '</h1>' + desc + '<div class="author">' + author + '</div>' + image + body
return html