calibre/recipes/new_yorker.recipe
Kovid Goyal 29cd8d64ea
Change shebangs to python from python2
Also remove a few other miscellaneous references to python2
2020-08-22 18:47:51 +05:30

133 lines
4.6 KiB
Python

#!/usr/bin/env python
# vim:fileencoding=utf-8
# License: GPLv3 Copyright: 2016, Kovid Goyal <kovid at kovidgoyal.net>
from __future__ import absolute_import, division, print_function, unicode_literals
from collections import defaultdict
from calibre import browser
from calibre.ebooks.BeautifulSoup import Tag
from calibre.web.feeds.news import BasicNewsRecipe
def classes(classes):
q = frozenset(classes.split(' '))
return dict(
attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)})
def absurl(x):
if x.startswith('/') and not x.startswith('//'):
x = 'https://www.newyorker.com' + x
return x
def new_tag(soup, name, attrs=()):
impl = getattr(soup, 'new_tag', None)
if impl is not None:
return impl(name, attrs=dict(attrs))
return Tag(soup, name, attrs=attrs or None)
class NewYorker(BasicNewsRecipe):
title = 'New Yorker Magazine'
description = 'Content from the New Yorker website'
url_list = []
language = 'en'
__author__ = 'Kovid Goyal'
no_stylesheets = True
timefmt = ' [%b %d]'
encoding = 'utf-8'
extra_css = '''
.byline { font-size:xx-small; font-weight: bold;}
h3 { margin-bottom: 6px; }
.caption { font-size: xx-small; font-style: italic; font-weight: normal; }
'''
keep_only_tags = [
classes(
'split-screen-content-header__dek split-screen-content-header__hed'
' content-header__dek content-header__hed content-header__publish-date content-header__lede-block'
' content-header__rubric--issue-date content-header__lead-asset'
' split-screen-content-header__publish-date split-screen-content-header__lede-block'
' article__body bylines featured-image byline-and-date inset-mobile-crop-image hero-image-caption'
),
]
remove_tags = [
classes(
'social-icons'
),
dict(childtypes='iframe'),
]
remove_attributes = ['style']
def preprocess_html(self, soup):
for noscript in soup.findAll('noscript'):
noscript.name = 'div'
return soup
def parse_index(self):
soup = self.index_to_soup(
'https://www.newyorker.com/magazine?intcid=magazine')
# soup = self.index_to_soup('file:///t/raw.html')
cover_soup = self.index_to_soup('https://www.newyorker.com/archive')
cover_img = cover_soup.find(
attrs={'class': lambda x: x and 'MagazineSection__cover___' in x})
if cover_img is not None:
cover_img = cover_img.find('img')
if cover_img is not None:
self.cover_url = cover_img.get('src')
try:
# the src original resolution w_280 was too low, replace w_280 with w_560
cover_url_width_index = self.cover_url.find("w_")
old_width = self.cover_url[cover_url_width_index:cover_url_width_index+5]
self.cover_url = self.cover_url.replace(old_width, "w_560")
except Exception:
self.log('Failed enlarging cover img, using the original one')
self.log('Found cover:', self.cover_url)
stories = defaultdict(list)
last_section = 'Unknown'
for story in soup.findAll(
attrs={'class': lambda x: x and 'River__riverItemContent___' in x}):
try:
section = self.tag_to_string(
story.find('a')['title']) or last_section
except KeyError:
section = last_section
last_section = section
h4 = story.find('h4')
title = self.tag_to_string(h4)
a = story.find('h4').parent
url = absurl(a['href'])
desc = ''
body = story.find(attrs={'class': 'River__dek___CayIg'})
if body is not None:
desc = body.contents[0]
self.log('Found article:', title)
self.log('\t' + url)
self.log('\t' + desc)
self.log('')
stories[section].append({
'title': title,
'url': url,
'description': desc})
return [(k, stories[k]) for k in sorted(stories)]
# The New Yorker changes the content it delivers based on cookies, so the
# following ensures that we send no cookies
def get_browser(self, *args, **kwargs):
return self
def clone_browser(self, *args, **kwargs):
return self.get_browser()
def open_novisit(self, *args, **kwargs):
br = browser()
return br.open_novisit(*args, **kwargs)
open = open_novisit