mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
129 lines
4.3 KiB
Plaintext
129 lines
4.3 KiB
Plaintext
# -*- coding: utf-8 -*-
|
|
|
|
import time
|
|
|
|
from calibre.web.feeds.recipes import BasicNewsRecipe
|
|
from calibre.ebooks.BeautifulSoup import BeautifulSoup
|
|
|
|
class JASN(BasicNewsRecipe):
|
|
title = u'Journal of the American Society of Nephrology'
|
|
language = 'en'
|
|
__author__ = 'Krittika Goyal'
|
|
oldest_article = 31 #days
|
|
max_articles_per_feed = 25
|
|
delay = 5
|
|
needs_subscription = True
|
|
|
|
INDEX = 'http://jasn.asnjournals.org/current.shtml'
|
|
no_stylesheets = True
|
|
remove_tags_before = dict(name='h2')
|
|
#remove_tags_after = dict(name='th', attrs={'align':'left'})
|
|
remove_tags = [
|
|
dict(name='iframe'),
|
|
#dict(name='div', attrs={'class':'related-articles'}),
|
|
dict(name='td', attrs={'id':['jasnFooter']}),
|
|
dict(name='table', attrs={'id':"jasnNavBar"}),
|
|
dict(name='table', attrs={'class':'content_box_outer_table'}),
|
|
dict(name='th', attrs={'align':'left'})
|
|
]
|
|
|
|
|
|
|
|
#TO LOGIN
|
|
def get_browser(self):
|
|
br = BasicNewsRecipe.get_browser()
|
|
self.kidney_toc_soup = BeautifulSoup(br.open(self.INDEX).read())
|
|
toc = self.kidney_toc_soup.find(id='tocTable')
|
|
t = toc.find(text=lambda x: x and '[Full Text]' in x)
|
|
a = t.findParent('a', href=True)
|
|
url = a.get('href')
|
|
if url.startswith('/'):
|
|
url = 'http://jasn.asnjournals.org'+url
|
|
br.open(url)
|
|
br.select_form(name='UserSignIn')
|
|
br['username'] = self.username
|
|
br['code'] = self.password
|
|
response = br.submit()
|
|
raw = response.read()
|
|
if 'Sign Out' not in raw:
|
|
raise ValueError('Failed to log in, is your account expired?')
|
|
return br
|
|
|
|
#feeds = [
|
|
#('JASN',
|
|
#'http://jasn.asnjournals.org/rss/current.xml'),
|
|
#]
|
|
|
|
|
|
#TO GET ARTICLE TOC
|
|
def jasn_get_index(self):
|
|
return self.index_to_soup('http://jasn.asnjournals.org/current.shtml')
|
|
|
|
# To parse artice toc
|
|
def parse_index(self):
|
|
parse_soup = self.jasn_get_index()
|
|
|
|
div = parse_soup.find(id='tocBody')
|
|
|
|
current_section = None
|
|
current_articles = []
|
|
feeds = []
|
|
for x in div.findAll(True):
|
|
if x.name == 'h2':
|
|
# Section heading found
|
|
if current_articles and current_section:
|
|
feeds.append((current_section, current_articles))
|
|
current_section = self.tag_to_string(x)
|
|
current_articles = []
|
|
self.log('\tFound section:', current_section)
|
|
if current_section is not None and x.name == 'strong':
|
|
title = self.tag_to_string(x)
|
|
a = x.parent.parent.find('a', href=lambda x: x and '/full/' in x)
|
|
if a is None:
|
|
continue
|
|
url = a.get('href', False)
|
|
if not url or not title:
|
|
continue
|
|
if url.startswith('/'):
|
|
url = 'http://jasn.asnjournals.org'+url
|
|
self.log('\t\tFound article:', title)
|
|
self.log('\t\t\t', url)
|
|
current_articles.append({'title': title, 'url':url,
|
|
'description':'', 'date':''})
|
|
|
|
if current_articles and current_section:
|
|
feeds.append((current_section, current_articles))
|
|
|
|
return feeds
|
|
|
|
|
|
|
|
def preprocess_html(self, soup):
|
|
for a in soup.findAll(text=lambda x: x and '[in this window]' in x):
|
|
a = a.findParent('a')
|
|
url = a.get('href', None)
|
|
if not url:
|
|
continue
|
|
if url.startswith('/'):
|
|
url = 'http://jasn.asnjournals.org'+url
|
|
img = isoup = None
|
|
try:
|
|
isoup = self.index_to_soup(url)
|
|
except:
|
|
time.sleep(5)
|
|
try:
|
|
isoup = self.index_to_soup(url)
|
|
except:
|
|
continue
|
|
img = isoup.find('img', src=lambda x: x and x.startswith('/content/'))
|
|
|
|
if img is not None:
|
|
img.extract()
|
|
table = a.findParent('table')
|
|
table.replaceWith(img)
|
|
return soup
|
|
|
|
|
|
|
|
|