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

...

Browse Source
This commit is contained in:
Kovid Goyal 2022-05-02 14:01:22 +05:30
parent 6eb871d823
commit 82027ad79c
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 24 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

37
recipes/caravan_magazine_hindi.recipe
View File

@ -11,8 +11,9 @@ from calibre.web.feeds.recipes import BasicNewsRecipe
def classes(classes):
q = frozenset(classes.split(' '))
return dict(attrs={
'class': lambda x: x and frozenset(x.split()).intersection(q)})
return dict(
attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)}
)
class CaravanMagazineHindi(BasicNewsRecipe):
@ -28,8 +29,8 @@ class CaravanMagazineHindi(BasicNewsRecipe):
no_stylesheets = True
keep_only_tags = [
classes('post-title short-desc author-details cover'),
dict(itemprop='articleBody'),
classes('post-title short-desc author-details cover'),
dict(itemprop='articleBody'),
]
remove_tags = [
@ -41,7 +42,11 @@ class CaravanMagazineHindi(BasicNewsRecipe):
br = BasicNewsRecipe.get_browser(self, *args, **kw)
if not self.username or not self.password:
return br
data = json.dumps({'email': self.username, 'name': '', 'password': self.password})
data = json.dumps({
'email': self.username,
'name': '',
'password': self.password
})
if not isinstance(data, bytes):
data = data.encode('utf-8')
rq = Request(
@ -70,16 +75,25 @@ class CaravanMagazineHindi(BasicNewsRecipe):
# find current issue cover
feeds = []
sections = soup.find(attrs={'class': lambda x: x and 'current-magazine-issue' in x.split()}).find(
attrs={'class': lambda x: x and 'sections' in x.split()})
for section in sections.findAll(attrs={'class': lambda x: x and 'section' in x.split()}):
sections = soup.find(
attrs={
'class': lambda x: x and 'current-magazine-issue' in x.split()
}
).find(attrs={'class': lambda x: x and 'sections' in x.split()})
for section in sections.findAll(
attrs={'class': lambda x: x and 'section' in x.split()}
):
a = section.find('a')
section_title = self.tag_to_string(a)
self.log('\nSection:', section_title)
articles = []
for article in section.findAll('article'):
details = article.find(attrs={'class': lambda x: x and 'details' in x.split()})
pre = details.find(attrs={'class': lambda x: x and 'pre-heading' in x.split()})
details = article.find(
attrs={'class': lambda x: x and 'details' in x.split()}
)
pre = details.find(
attrs={'class': lambda x: x and 'pre-heading' in x.split()}
)
if pre is not None:
pre.extract()
a = details.find('a')
@ -98,6 +112,3 @@ class CaravanMagazineHindi(BasicNewsRecipe):
for img in div.findAll('img'):
img['src'] = div['content']
return soup
calibre_most_common_ua = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.87 Safari/537.36'