mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
124 lines
4.4 KiB
Plaintext
124 lines
4.4 KiB
Plaintext
from calibre.web.feeds.news import BasicNewsRecipe
|
|
import re
|
|
|
|
|
|
def select_form(form):
|
|
return form.attrs.get('class', None) == 'user-login-form'
|
|
|
|
|
|
class ForeignAffairsRecipe(BasicNewsRecipe):
|
|
|
|
''' there are three modifications:
|
|
1) fetch issue cover
|
|
2) toggle ignore premium articles
|
|
3) extract proper section names, ie. "Comments", "Essay"
|
|
|
|
by Chen Wei, 2012-02-05
|
|
|
|
Additional modifications to support rebranded website
|
|
|
|
by anisotrope, 27 June 2015
|
|
'''
|
|
|
|
__license__ = 'GPL v3'
|
|
__author__ = 'Rick Shang, kwetal, anisotrope'
|
|
language = 'en'
|
|
version = 1.02
|
|
|
|
title = u'Foreign Affairs (Subcription)'
|
|
publisher = u'Council on Foreign Relations'
|
|
category = u'USA, Foreign Affairs'
|
|
description = u'The leading forum for serious discussion of American foreign policy and international affairs.'
|
|
|
|
no_stylesheets = True
|
|
remove_javascript = True
|
|
needs_subscription = True
|
|
|
|
INDEX = 'http://www.foreignaffairs.com'
|
|
FRONTPAGE = 'http://www.foreignaffairs.com/magazine'
|
|
|
|
remove_tags = [dict(name='svg')]
|
|
remove_tags_before = dict(name='div', attrs={'class': 'print-content'})
|
|
remove_tags_after = dict(name='div', attrs={'class': 'print-footer'})
|
|
|
|
extra_css = '''
|
|
body{font-family:verdana,arial,helvetica,geneva,sans-serif;}
|
|
div.print-footer {font-size: x-small; color: #696969;}
|
|
'''
|
|
|
|
conversion_options = {'comments': description, 'tags': category, 'language': 'en',
|
|
'publisher': publisher}
|
|
|
|
temp_files = []
|
|
|
|
def get_cover_url(self):
|
|
soup = self.index_to_soup(self.FRONTPAGE)
|
|
div = soup.find('div', attrs={'class':'magazine-hero__image image_auto_width'})
|
|
img_url = div.find('img')['src']
|
|
return img_url # The url includes the https:// as necessary
|
|
|
|
def get_print_url(self, url):
|
|
article_soup = self.index_to_soup(url.strip())
|
|
|
|
if article_soup is not None:
|
|
shortlink = article_soup.find('a', attrs={'class':re.compile(r'\bicon-print\b')})
|
|
if shortlink:
|
|
return shortlink['href']
|
|
else:
|
|
return url
|
|
else:
|
|
return url
|
|
|
|
def parse_index(self):
|
|
|
|
answer = []
|
|
soup = self.index_to_soup(self.FRONTPAGE)
|
|
# get dates
|
|
date = re.split('\s\|\s',self.tag_to_string(soup.head.title.string))[0]
|
|
self.title = "Foreign Affairs ({})".format(date)
|
|
self.timefmt = u' [%s]'%date
|
|
|
|
sec_start = soup.findAll('section', attrs={'class':re.compile(r'\bmagazine-list\b')})
|
|
for sec in sec_start:
|
|
articles = []
|
|
section = self.tag_to_string(sec.find('h1'))
|
|
for article_block in sec.findAll('article'):
|
|
if article_block.find('a') is not None:
|
|
title=self.tag_to_string(article_block.div.a.h2)
|
|
article_url = article_block.div.a['href']
|
|
url = self.get_print_url(article_url)
|
|
atr=article_block.findNext('p', attrs={'class': 'author'})
|
|
if atr is not None:
|
|
author=self.tag_to_string(atr)
|
|
else:
|
|
author=''
|
|
desc=article_block.findNext('div', attrs={'class': 'deck'})
|
|
if desc is not None:
|
|
description=self.tag_to_string(desc)
|
|
else:
|
|
description=''
|
|
articles.append({'title':title, 'date':None, 'url':url, 'description':description, 'author':author})
|
|
if articles:
|
|
answer.append((section, articles))
|
|
return answer
|
|
|
|
def preprocess_html(self, soup):
|
|
for img in soup.findAll('img', attrs={'src': True}):
|
|
if not img['src'].startswith('http'):
|
|
img['src'] = self.INDEX + img['src']
|
|
|
|
return soup
|
|
|
|
def get_browser(self):
|
|
br = BasicNewsRecipe.get_browser(self)
|
|
if self.username is not None and self.password is not None:
|
|
br.open('https://www.foreignaffairs.com/user?destination=user%3Fop%3Dlo')
|
|
br.select_form(predicate=select_form)
|
|
br.form['name'] = self.username
|
|
br.form['pass'] = self.password
|
|
br.submit()
|
|
return br
|
|
|
|
def cleanup(self):
|
|
self.browser.open('https://www.foreignaffairs.com/user/logout')
|