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

Merge branch 'lemonde-may2022' of https://github.com/aimylios/calibre

Browse Source
This commit is contained in:
Kovid Goyal 2022-05-30 07:06:51 +05:30
commit a5338869d4
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
2 changed files with 52 additions and 28 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
recipes/le_monde.recipe
View File

@ -9,16 +9,11 @@ __copyright__ = '2012'
lemonde.fr
'''
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.web.feeds.news import BasicNewsRecipe, classes
from datetime import date
import re
def classes(classes):
q = frozenset(classes.split(' '))
return dict(attrs={
'class': lambda x: x and frozenset(x.split()).intersection(q)})
class LeMonde(BasicNewsRecipe):
title = 'Le Monde'
__author__ = 'veezh'
@ -93,19 +88,34 @@ class LeMonde(BasicNewsRecipe):
def get_browser(self):
br = BasicNewsRecipe.get_browser(self)
if self.username is not None and self.password is not None:
br.open('https://secure.lemonde.fr/sfuser/connexion')
br.select_form(nr=0)
br['email'] = self.username
br['password'] = self.password
br.submit()
try:
br.open('https://secure.lemonde.fr/sfuser/connexion')
br.select_form(nr=0)
br['email'] = self.username
br['password'] = self.password
br.submit()
except Exception as e:
self.log('Login failed with error:', str(e))
return br
def get_cover_url(self):
# today's date is a reasonable guess for the ID of the cover
cover_id = date.today().strftime('%Y%m%d')
soup = self.index_to_soup('https://www.lemonde.fr/')
a = soup.find('a', {'id': 'jelec_link', 'style': True})
if a and a['style']:
url = a['style'].split('/')
if len(url) > 5 and url[3].isdigit():
# overwrite guess if actual cover ID was found
cover_id = url[3]
return 'https://www.lemonde.fr/thumbnail/journal/' + cover_id + '/1000/1490'
def get_article_url(self, article):
url = BasicNewsRecipe.get_article_url(self, article)
# skip articles without relevant content (e.g., videos)
for el in 'blog chat live podcasts portfolio video visuel'.split():
if '/' + el + '/' in url:
self.log(url)
self.log('Skipping URL', url)
self.abort_article()
return url

44
recipes/le_monde_sub.recipe
View File

@ -9,16 +9,11 @@ __license__ = 'GPL v3'
lemonde.fr
'''
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.web.feeds.news import BasicNewsRecipe, classes
from datetime import date
import re
def classes(classes):
q = frozenset(classes.split(' '))
return dict(attrs={
'class': lambda x: x and frozenset(x.split()).intersection(q)})
class LeMondeNumerique(BasicNewsRecipe):
title = 'Le Monde: Édition abonnés'
__author__ = 'Sylvain Durand'
@ -90,13 +85,29 @@ class LeMondeNumerique(BasicNewsRecipe):
def get_browser(self):
br = BasicNewsRecipe.get_browser(self)
br.open('https://secure.lemonde.fr/sfuser/connexion')
br.select_form(nr=0)
br['email'] = self.username
br['password'] = self.password
br.submit()
if self.username is not None and self.password is not None:
try:
br.open('https://secure.lemonde.fr/sfuser/connexion')
br.select_form(nr=0)
br['email'] = self.username
br['password'] = self.password
br.submit()
except Exception as e:
self.log('Login failed with error:', str(e))
return br
def get_cover_url(self):
# today's date is a reasonable guess for the ID of the cover
cover_id = date.today().strftime('%Y%m%d')
soup = self.index_to_soup('https://www.lemonde.fr/')
a = soup.find('a', {'id': 'jelec_link', 'style': True})
if a and a['style']:
url = a['style'].split('/')
if len(url) > 5 and url[3].isdigit():
# overwrite guess if actual cover ID was found
cover_id = url[3]
return 'https://www.lemonde.fr/thumbnail/journal/' + cover_id + '/1000/1490'
def parse_index(self):
ans = []
for x in self.lm_sections:
@ -111,14 +122,17 @@ class LeMondeNumerique(BasicNewsRecipe):
soup = self.index_to_soup(url)
for article in soup.find_all('section', {'class': 'teaser'}):
# extract URL
a = article.find('a', {'class': 'teaser__link'})
a = article.find('a', {'class': 'teaser__link', 'href': True})
if a is None:
continue
url = a['href']
# skip articles without relevant content (e.g., videos)
for el in 'blog chat live podcasts portfolio video visuel'.split():
for el in 'blog chat live newsletters podcasts portfolio video visuel'.split():
if '/' + el + '/' in url:
continue
url = None
break
if url is None:
continue
# extract title
h3 = article.find('h3', {'class': 'teaser__title'})
if h3 is None: