Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Mediapart

Browse Source
This commit is contained in:
Kovid Goyal 2020-09-09 20:14:29 +05:30
parent a45c2fa5a3
commit 91f95e52fb
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 16 additions and 27 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

43
recipes/mediapart.recipe
View File

@ -14,10 +14,16 @@ from calibre.web.feeds import feeds_from_index
from datetime import date, timedelta from datetime import date, timedelta
def classes(classes):
q = frozenset(classes.split(' '))
return dict(attrs={
'class': lambda x: x and frozenset(x.split()).intersection(q)})
class Mediapart(BasicNewsRecipe): class Mediapart(BasicNewsRecipe):
title = 'Mediapart' title = 'Mediapart'
__author__ = 'Daniel Bonnery from a version by Mathieu Godlewski, Louis Gesbert' __author__ = 'Daniel Bonnery from a version by Mathieu Godlewski, Louis Gesbert'
description = 'Global news in french from news site Mediapart' description = 'Global news in French from news site Mediapart'
publication_type = 'newspaper' publication_type = 'newspaper'
language = 'fr' language = 'fr'
needs_subscription = True needs_subscription = True
@ -26,6 +32,15 @@ class Mediapart(BasicNewsRecipe):
use_embedded_content = False use_embedded_content = False
no_stylesheets = True no_stylesheets = True
keep_only_tags = [
dict(name='h1'),
dict(name='div', **classes('author')),
classes('introduction content-article')
]
remove_tags = [
classes('login-subscribe print-source_url')
]
cover_url = 'https://static.mediapart.fr/files/M%20Philips/logo-mediapart.png' cover_url = 'https://static.mediapart.fr/files/M%20Philips/logo-mediapart.png'
# -- # --
@ -116,8 +131,6 @@ class Mediapart(BasicNewsRecipe):
conversion_options = {'smarten_punctuation': True} conversion_options = {'smarten_punctuation': True}
remove_tags = [dict(name='div', attrs={'class': 'print-source_url'})]
# non-locale specific date parse (strptime("%d %b %Y",s) would work with # non-locale specific date parse (strptime("%d %b %Y",s) would work with
# french locale) # french locale)
def parse_french_date(self, date_str): def parse_french_date(self, date_str):
@ -127,21 +140,6 @@ class Mediapart(BasicNewsRecipe):
month=[None, 'janvier', 'février', 'mars', 'avril', 'mai', 'juin', 'juillet', month=[None, 'janvier', 'février', 'mars', 'avril', 'mai', 'juin', 'juillet',
'août', 'septembre', 'octobre', 'novembre', 'décembre'].index(date_arr[1])) 'août', 'septembre', 'octobre', 'novembre', 'décembre'].index(date_arr[1]))
def print_version(self, url):
soup = self.index_to_soup(url)
# Filter old articles
# article_date = self.parse_french_date(self.tag_to_string(soup.find('span', 'article-date')))
# if article_date < self.oldest_article_date:
# return None
tools = soup.find('li', {'class': 'print'})
link = tools.find('a', {'href': re.compile(r'\/print\/.*')})
# if link is None:
# print 'Error: print link not found'
# return None
return 'https://mediapart.fr' + link['href']
# -- Handle login # -- Handle login
def get_browser(self): def get_browser(self):
def is_form_login(form): def is_form_login(form):
@ -154,12 +152,3 @@ class Mediapart(BasicNewsRecipe):
br['password'] = self.password br['password'] = self.password
br.submit() br.submit()
return br return br
# This is a workaround articles with scribd content that include
# <body></body> tags _within_ the body
preprocess_regexps = [
(re.compile(r'(<body.*?>)(.*)</body>', re.IGNORECASE | re.DOTALL),
lambda match:
match.group(1) + re.sub(
re.compile(r'</?body>', re.IGNORECASE | re.DOTALL), '', match.group(2)) + '</body>')
]