calibre/recipes/nejm.recipe

75 lines
2.4 KiB
Plaintext

# -*- coding: utf-8 -*-
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 NEJM(BasicNewsRecipe):
title = 'New England Journal of Medicine'
__author__ = 'Kovid Goyal'
description = 'Medical news'
timefmt = ' [%d %b, %Y]'
needs_subscription = True
language = 'en'
no_stylesheets = True
keep_only_tags = [
dict(id='content')
]
remove_tags_after = dict(id='article_references')
remove_attributes = ['width', 'height']
# TO LOGIN
def get_browser(self):
br = BasicNewsRecipe.get_browser(self)
br.open('https://www.nejm.org/action/showLogin?uri=http%3A%2F%2Fwww.nejm.org%2F')
br.select_form(name='frmLogin')
br['login'] = self.username
br['password'] = self.password
response = br.submit()
raw = response.read()
if '>Sign Out<' not in raw:
raise Exception('Login failed. Check your username and password')
return br
# TO GET ARTICLE TOC
def nejm_get_index(self):
return self.index_to_soup('https://www.nejm.org/toc/nejm/medical-journal')
# To parse artice toc
def parse_index(self):
soup = self.nejm_get_index()
feeds = []
current_section = None
articles = []
div = soup.find(**classes('pagefulltext'))
for x in div.findAll(name=['h2', 'li']):
if x.name == 'h2':
if current_section and articles:
feeds.append((current_section, articles))
current_section = self.tag_to_string(x).strip()
articles = []
if current_section:
self.log(current_section)
else:
a = x.find('a')
if a is None:
continue
title = self.tag_to_string(a.find('strong')).strip()
blurb = a.find(**classes('f-blurb'))
desc = ''
if blurb is not None:
desc = self.tag_to_string(blurb)
self.log('\t', title)
articles.append({'title': title, 'url': 'https://www.nejm.org' + a['href'], 'description': desc})
if current_section and articles:
feeds.append((current_section, articles))
return feeds