Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-08-11 09:13:57 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update The Atlantic

Browse Source
This commit is contained in:
Kovid Goyal 2016-05-04 15:54:30 +05:30
parent db47669c10
commit db09bafd9e
1 changed files with 17 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
recipes/atlantic.recipe
View File

@ -5,9 +5,14 @@ __copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
''' '''
theatlantic.com theatlantic.com
''' '''
import re import html5lib
from lxml import html
from calibre.web.feeds.news import BasicNewsRecipe 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)})
class TheAtlantic(BasicNewsRecipe): class TheAtlantic(BasicNewsRecipe):
title = 'The Atlantic' title = 'The Atlantic'
@ -18,7 +23,7 @@ class TheAtlantic(BasicNewsRecipe):
encoding = 'utf-8' encoding = 'utf-8'
keep_only_tags = [ keep_only_tags = [
{'attrs':{'class':['article-header', 'article-body', 'article-magazine', 'metadata', 'article-cover-content']}}, classes('article-header article-body article-magazine metadata article-cover-content lead-img'),
] ]
remove_tags = [ remove_tags = [
{'name': ['meta', 'link', 'noscript']}, {'name': ['meta', 'link', 'noscript']},
@ -26,12 +31,18 @@ class TheAtlantic(BasicNewsRecipe):
{'attrs':{'class':lambda x: x and 'article-tools' in x}}, {'attrs':{'class':lambda x: x and 'article-tools' in x}},
{'src':lambda x:x and 'spotxchange.com' in x}, {'src':lambda x:x and 'spotxchange.com' in x},
] ]
remove_tags_after = classes('article-body')
no_stylesheets = True no_stylesheets = True
remove_attributes = ['style'] remove_attributes = ['style']
preprocess_regexps = [
(re.compile(r'<script\b.+?</script>', re.DOTALL), lambda m: ''), def get_browser(self):
(re.compile(r'^.*<html', re.DOTALL|re.IGNORECASE), lambda m: '<html'), br = BasicNewsRecipe.get_browser(self)
] br.set_cookie('inEuropeanUnion', '0', '.theatlantic.com')
return br
def preprocess_raw_html(self, raw, url):
return html.tostring(html5lib.parse(raw, treebuilder='lxml', namespaceHTMLElements=False), method='html', encoding=unicode)
def print_version(self, url): def print_version(self, url):
return url + '?single_page=true' return url + '?single_page=true'