| 1 |
# -*- coding: utf-8 -*- |
| 2 |
from calibre.web.feeds.recipes import BasicNewsRecipe |
| 3 |
|
| 4 |
|
| 5 |
def classes(classes): |
| 6 |
q = frozenset(classes.split(' ')) |
| 7 |
return dict(attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)}) |
| 8 |
|
| 9 |
|
| 10 |
class NEJM(BasicNewsRecipe): |
| 11 |
title = 'New England Journal of Medicine' |
| 12 |
__author__ = 'Kovid Goyal' |
| 13 |
description = 'Medical news' |
| 14 |
timefmt = ' [%d %b, %Y]' |
| 15 |
needs_subscription = True |
| 16 |
language = 'en' |
| 17 |
|
| 18 |
no_stylesheets = True |
| 19 |
keep_only_tags = [dict(id='content')] |
| 20 |
remove_tags_after = dict(id='article_references') |
| 21 |
remove_attributes = ['width', 'height'] |
| 22 |
|
| 23 |
# TO LOGIN |
| 24 |
def get_browser(self): |
| 25 |
br = BasicNewsRecipe.get_browser(self) |
| 26 |
br.open('https://www.nejm.org/action/showLogin?uri=http%3A%2F%2Fwww.nejm.org%2F') |
| 27 |
br.select_form(name='frmLogin') |
| 28 |
br['login'] = self.username |
| 29 |
br['password'] = self.password |
| 30 |
response = br.submit() |
| 31 |
raw = response.read() |
| 32 |
if '>Sign Out<' not in raw: |
| 33 |
raise Exception('Login failed. Check your username and password') |
| 34 |
return br |
| 35 |
|
| 36 |
# TO GET ARTICLE TOC |
| 37 |
def nejm_get_index(self): |
| 38 |
return self.index_to_soup('https://www.nejm.org/toc/nejm/medical-journal') |
| 39 |
|
| 40 |
# To parse article toc |
| 41 |
def parse_index(self): |
| 42 |
soup = self.nejm_get_index() |
| 43 |
feeds = [] |
| 44 |
current_section = None |
| 45 |
articles = [] |
| 46 |
div = soup.find(**classes('pagefulltext')) |
| 47 |
for x in div.findAll(name=['h2', 'li']): |
| 48 |
if x.name == 'h2': |
| 49 |
if current_section and articles: |
| 50 |
feeds.append((current_section, articles)) |
| 51 |
current_section = self.tag_to_string(x).strip() |
| 52 |
articles = [] |
| 53 |
if current_section: |
| 54 |
self.log(current_section) |
| 55 |
else: |
| 56 |
a = x.find('a') |
| 57 |
if a is None: |
| 58 |
continue |
| 59 |
title = self.tag_to_string(a.find('strong')).strip() |
| 60 |
blurb = a.find(**classes('f-blurb')) |
| 61 |
desc = '' |
| 62 |
if blurb is not None: |
| 63 |
desc = self.tag_to_string(blurb) |
| 64 |
self.log('\t', title) |
| 65 |
articles.append({'title': title, 'url': 'https://www.nejm.org' + a['href'], 'description': desc}) |
| 66 |
|
| 67 |
if current_section and articles: |
| 68 |
feeds.append((current_section, articles)) |
| 69 |
|
| 70 |
return feeds |