Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-31 14:33:54 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update The New Yorker

Browse Source 
Fixes #1860959 [newyorker recipe no longer working](https://bugs.launchpad.net/calibre/+bug/1860959)
This commit is contained in:
Kovid Goyal 2020-01-27 15:04:47 +05:30
parent ae6aef1d4b
commit be8854e4ea
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 24 additions and 56 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

80
recipes/new_yorker.recipe
View File

@ -1,9 +1,8 @@
#!/usr/bin/env python2 #!/usr/bin/env python2
# vim:fileencoding=utf-8 # vim:fileencoding=utf-8
# License: GPLv3 Copyright: 2016, Kovid Goyal <kovid at kovidgoyal.net> # License: GPLv3 Copyright: 2016, Kovid Goyal <kovid at kovidgoyal.net>
from __future__ import absolute_import, division, print_function, unicode_literals
import json
import re
from collections import defaultdict from collections import defaultdict
from calibre import browser from calibre import browser
@ -32,8 +31,8 @@ def new_tag(soup, name, attrs=()):
class NewYorker(BasicNewsRecipe): class NewYorker(BasicNewsRecipe):
title = u'New Yorker Magazine' title = 'New Yorker Magazine'
description = u'Content from the New Yorker website' description = 'Content from the New Yorker website'
url_list = [] url_list = []
language = 'en' language = 'en'
@ -42,31 +41,33 @@ class NewYorker(BasicNewsRecipe):
timefmt = ' [%b %d]' timefmt = ' [%b %d]'
encoding = 'utf-8' encoding = 'utf-8'
extra_css = ''' extra_css = '''
.byline { font-size:xx-small; font-weight: bold;} .byline { font-size:xx-small; font-weight: bold;}
h3 { margin-bottom: 6px; } h3 { margin-bottom: 6px; }
.caption { font-size: xx-small; font-style: italic; font-weight: normal; } .caption { font-size: xx-small; font-style: italic; font-weight: normal; }
''' '''
keep_only_tags = [ keep_only_tags = [
dict(attrs={'class': lambda x: x and 'ArticleHeader__hed___' in x}),
dict(attrs={'class': lambda x: x and 'ArticleHeader__dek___' in x}),
dict(attrs={'class': lambda x: x and 'Byline__articleHeader___' in x}),
dict(attrs={'class': lambda x: x and 'ArticleLedeImage__container___' in x}),
dict(itemprop=['headline', 'alternativeHeadline']),
dict(name='h1'),
classes( classes(
'featured-image byline-and-date inset-mobile-crop-image hero-image-caption' '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'
), ),
dict(id=['articleBody', 'article-content']), ]
dict(attrs={'class': lambda x: x and 'ArticleDisclaimer__articleDisclaimer___' in x}),
dict(attrs={'class': lambda x: x and 'ArticleContributors__bio___' in x}), ]
remove_tags = [ remove_tags = [
classes('content-ad-wrapper social-hover background-image'), classes(
dict(id=['newsletter-signup']), 'social-icons'
dict(attrs={'class': lambda x: x and 'ImageEmbed__button___' in x}), ),
dict(attrs={'class': lambda x: x and 'ArticleLedeImage__button___' in x}), dict(childtypes='iframe'),
dict(name='links source'.split()), ] ]
remove_attributes = ['style'] remove_attributes = ['style']
def preprocess_html(self, soup):
for noscript in soup.findAll('noscript'):
noscript.name = 'div'
return soup
def parse_index(self): def parse_index(self):
soup = self.index_to_soup( soup = self.index_to_soup(
'https://www.newyorker.com/magazine?intcid=magazine') 'https://www.newyorker.com/magazine?intcid=magazine')
@ -115,39 +116,6 @@ class NewYorker(BasicNewsRecipe):
return [(k, stories[k]) for k in sorted(stories)] return [(k, stories[k]) for k in sorted(stories)]
def preprocess_raw_html(self, html, url):
self.featured_image = None
m = m = re.search(r'"featured_image".+?,"url":("https[^"]+")', html)
if m is not None:
self.featured_image = json.loads(m.group(1))
self.log('Found featured image in JSON at', url, ':', self.featured_image)
return html
def preprocess_html(self, soup):
body = soup.find('body')
if not body.find('h1'):
title = soup.find('meta', itemprop='name')
if title:
if self.featured_image:
img = new_tag(soup, 'img')
img['src'] = self.featured_image
div = new_tag(soup, 'div')
div.append(img)
body.insert(0, div)
h1 = new_tag(soup, 'h1')
h1.append(title.get('content'))
body.insert(0, h1)
for attr in 'srcset data-src-mobile'.split():
for img in soup.findAll('img'):
try:
ds = img[attr].split()[0]
del img[attr]
except KeyError:
continue
if ds:
img['src'] = ds
return soup
# The New Yorker changes the content it delivers based on cookies, so the # The New Yorker changes the content it delivers based on cookies, so the
# following ensures that we send no cookies # following ensures that we send no cookies
def get_browser(self, *args, **kwargs): def get_browser(self, *args, **kwargs):