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

Add date to articles in nyt todays papaer index

Browse Source
This commit is contained in:
Kovid Goyal 2018-02-13 07:40:58 +05:30
parent a385f0a2d9
commit 4e730dc862
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
2 changed files with 52 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
recipes/nytimes.recipe
View File

@ -4,8 +4,11 @@
from __future__ import absolute_import, division, print_function, unicode_literals from __future__ import absolute_import, division, print_function, unicode_literals
from calibre.web.feeds.news import BasicNewsRecipe import datetime
import re
from calibre.utils.date import strptime from calibre.utils.date import strptime
from calibre.web.feeds.news import BasicNewsRecipe
is_web_edition = True is_web_edition = True
# The sections to download when downloading the web edition, comment out # The sections to download when downloading the web edition, comment out
@ -36,6 +39,20 @@ web_sections = [
('Obituaries', 'obituaries'), ('Obituaries', 'obituaries'),
('Sunday Magazine', 'magazine') ('Sunday Magazine', 'magazine')
] ]
url_date_pat = re.compile(r'/(2\d\d\d)/(\d\d)/(\d\d)/')
def date_from_url(url):
m = url_date_pat.search(url)
if m is not None:
return datetime.date(*map(int, m.groups()))
def format_date(d):
try:
return d.strftime(' [%a, %d %b %Y]').decode('utf-8')
except Exception:
return d.strftime(' [%Y/%m/%d]').decode('utf-8')
def classes(classes): def classes(classes):
@ -71,7 +88,7 @@ class NewYorkTimes(BasicNewsRecipe):
dict(name='a', href=lambda x: x and '#story-continues-' in x), dict(name='a', href=lambda x: x and '#story-continues-' in x),
dict(name='a', href=lambda x: x and '#whats-next' in x), dict(name='a', href=lambda x: x and '#whats-next' in x),
dict(id=lambda x: x and 'sharetools-' in x), dict(id=lambda x: x and 'sharetools-' in x),
dict(id='newsletter-promo'.split()), dict(id='newsletter-promo supported-by-ad'.split()),
classes('story-print-citation'), classes('story-print-citation'),
] ]
@ -98,9 +115,14 @@ class NewYorkTimes(BasicNewsRecipe):
s = p.find(**classes('summary')) s = p.find(**classes('summary'))
if s is not None: if s is not None:
desc = self.tag_to_string(s) desc = self.tag_to_string(s)
self.log('\t', title, ': ', url) date = ''
d = date_from_url(url)
if d is not None:
date = format_date(d)
self.log('\t', title + date, ': ', url)
self.log('\t\t', desc) self.log('\t\t', desc)
yield {'title': title, 'url': url, 'description': desc} yield {'title': title, 'url': url, 'description': desc, 'date': date}
def parse_todays_page(self): def parse_todays_page(self):
soup = self.read_nyt_metadata() soup = self.read_nyt_metadata()

30
recipes/nytimes_sub.recipe
View File

@ -4,8 +4,11 @@
from __future__ import absolute_import, division, print_function, unicode_literals from __future__ import absolute_import, division, print_function, unicode_literals
from calibre.web.feeds.news import BasicNewsRecipe import datetime
import re
from calibre.utils.date import strptime from calibre.utils.date import strptime
from calibre.web.feeds.news import BasicNewsRecipe
is_web_edition = False is_web_edition = False
# The sections to download when downloading the web edition, comment out # The sections to download when downloading the web edition, comment out
@ -36,6 +39,20 @@ web_sections = [
('Obituaries', 'obituaries'), ('Obituaries', 'obituaries'),
('Sunday Magazine', 'magazine') ('Sunday Magazine', 'magazine')
] ]
url_date_pat = re.compile(r'/(2\d\d\d)/(\d\d)/(\d\d)/')
def date_from_url(url):
m = url_date_pat.search(url)
if m is not None:
return datetime.date(*map(int, m.groups()))
def format_date(d):
try:
return d.strftime(' [%a, %d %b %Y]').decode('utf-8')
except Exception:
return d.strftime(' [%Y/%m/%d]').decode('utf-8')
def classes(classes): def classes(classes):
@ -71,7 +88,7 @@ class NewYorkTimes(BasicNewsRecipe):
dict(name='a', href=lambda x: x and '#story-continues-' in x), dict(name='a', href=lambda x: x and '#story-continues-' in x),
dict(name='a', href=lambda x: x and '#whats-next' in x), dict(name='a', href=lambda x: x and '#whats-next' in x),
dict(id=lambda x: x and 'sharetools-' in x), dict(id=lambda x: x and 'sharetools-' in x),
dict(id='newsletter-promo'.split()), dict(id='newsletter-promo supported-by-ad'.split()),
classes('story-print-citation'), classes('story-print-citation'),
] ]
@ -98,9 +115,14 @@ class NewYorkTimes(BasicNewsRecipe):
s = p.find(**classes('summary')) s = p.find(**classes('summary'))
if s is not None: if s is not None:
desc = self.tag_to_string(s) desc = self.tag_to_string(s)
self.log('\t', title, ': ', url) date = ''
d = date_from_url(url)
if d is not None:
date = format_date(d)
self.log('\t', title + date, ': ', url)
self.log('\t\t', desc) self.log('\t\t', desc)
yield {'title': title, 'url': url, 'description': desc} yield {'title': title, 'url': url, 'description': desc, 'date': date}
def parse_todays_page(self): def parse_todays_page(self):
soup = self.read_nyt_metadata() soup = self.read_nyt_metadata()