calibre/recipes/caravan_magazine.recipe
2020-08-22 18:48:32 +05:30

101 lines
3.5 KiB
Python

#!/usr/bin/env python
# vim:fileencoding=utf-8
# License: GPLv3 Copyright: 2015, Kovid Goyal <kovid at kovidgoyal.net>
import json
from mechanize import Request
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)})
class CaravanMagazine(BasicNewsRecipe):
title = 'Caravan Magazine'
__author__ = 'Kovid Goyal, Gobelinus'
description = 'An Indian Journal of politics and culture'
language = 'en_IN'
timefmt = ' [%b, %Y]'
encoding = 'utf-8'
needs_subscription = 'optional'
no_stylesheets = True
keep_only_tags = [
classes('post-title short-desc author-details cover'),
dict(itemprop='articleBody'),
]
remove_tags = [
dict(name='meta'),
dict(attrs={'class': ['share-with']}),
]
def get_browser(self, *args, **kw):
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})
if not isinstance(data, bytes):
data = data.encode('utf-8')
rq = Request(
url='https://caravanmagazine.in/api/users/login',
data=data,
headers={
'Accept': 'application/json, text/plain, */*',
'Origin': 'https://caravanmagazine.in',
'Referer': 'https://caravanmagazine.in/',
'Content-type': 'application/json;charset=UTF-8',
},
method='POST'
)
res = br.open(rq).read()
res = res.decode('utf-8')
self.log('Login request response: {}'.format(res))
res = json.loads(res)
if res['code'] != 200 or res['message'] != "Login success":
raise ValueError('Login failed, check your username and password')
return br
# To parse artice toc
def parse_index(self):
base_url = 'https://www.caravanmagazine.in/'
soup = self.index_to_soup('{0}magazine'.format(base_url))
# 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()}):
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()})
if pre is not None:
pre.extract()
a = details.find('a')
url = base_url + a['href'].lstrip('/')
title = self.tag_to_string(a)
desc = self.tag_to_string(details.find('div'))
self.log('\t', title, url)
articles.append({'title': title, 'description': desc, 'url': url})
if articles:
feeds.append((section_title, articles))
return feeds
def preprocess_html(self, soup):
for div in soup.findAll(itemprop='image'):
for img in div.findAll('img'):
img['src'] = div['content']
return soup