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 The Economist

Browse Source
This commit is contained in:
Kovid Goyal 2022-06-20 18:46:55 +05:30
parent 86abf1122c
commit 06daad5c61
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
2 changed files with 6 additions and 26 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
recipes/economist.recipe
View File

@ -13,7 +13,6 @@ from collections import defaultdict
from calibre import replace_entities from calibre import replace_entities
from calibre.ebooks.BeautifulSoup import NavigableString, Tag from calibre.ebooks.BeautifulSoup import NavigableString, Tag
from calibre.utils.cleantext import clean_ascii_chars
from calibre.utils.date import parse_only_date from calibre.utils.date import parse_only_date
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
@ -255,18 +254,6 @@ class Economist(BasicNewsRecipe):
raw = etree.tostring(root, encoding='unicode') raw = etree.tostring(root, encoding='unicode')
return raw return raw
def populate_article_metadata(self, article, soup, first):
els = soup.findAll(name=['span', 'p'],
attrs={'class': ['flytitle-and-title__title', 'blog-post__rubric']})
result = []
for el in els[0:2]:
if el is not None and el.contents:
for descendant in el.contents:
if isinstance(descendant, NavigableString):
result.append(type(u'')(descendant))
article.summary = u'. '.join(result) + u'.'
article.text_summary = clean_ascii_chars(article.summary)
def publication_date(self): def publication_date(self):
if edition_date: if edition_date:
return parse_only_date(edition_date, as_utc=False) return parse_only_date(edition_date, as_utc=False)
@ -317,6 +304,9 @@ class Economist(BasicNewsRecipe):
if not section or not title or not url: if not section or not title or not url:
continue continue
desc = safe_dict(part, "print", "description") or '' desc = safe_dict(part, "print", "description") or ''
sub = safe_dict(part, "print", "subheadline") or ''
if sub and section != sub:
desc = sub + ' :: ' + desc
feeds_dict[section].append({"title": title, "url": url, "description": desc}) feeds_dict[section].append({"title": title, "url": url, "description": desc})
self.log(' ', title, url, '\n ', desc) self.log(' ', title, url, '\n ', desc)
return [(section, articles) for section, articles in feeds_dict.items()] return [(section, articles) for section, articles in feeds_dict.items()]

16
recipes/economist_free.recipe
View File

@ -13,7 +13,6 @@ from collections import defaultdict
from calibre import replace_entities from calibre import replace_entities
from calibre.ebooks.BeautifulSoup import NavigableString, Tag from calibre.ebooks.BeautifulSoup import NavigableString, Tag
from calibre.utils.cleantext import clean_ascii_chars
from calibre.utils.date import parse_only_date from calibre.utils.date import parse_only_date
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
@ -255,18 +254,6 @@ class Economist(BasicNewsRecipe):
raw = etree.tostring(root, encoding='unicode') raw = etree.tostring(root, encoding='unicode')
return raw return raw
def populate_article_metadata(self, article, soup, first):
els = soup.findAll(name=['span', 'p'],
attrs={'class': ['flytitle-and-title__title', 'blog-post__rubric']})
result = []
for el in els[0:2]:
if el is not None and el.contents:
for descendant in el.contents:
if isinstance(descendant, NavigableString):
result.append(type(u'')(descendant))
article.summary = u'. '.join(result) + u'.'
article.text_summary = clean_ascii_chars(article.summary)
def publication_date(self): def publication_date(self):
if edition_date: if edition_date:
return parse_only_date(edition_date, as_utc=False) return parse_only_date(edition_date, as_utc=False)
@ -317,6 +304,9 @@ class Economist(BasicNewsRecipe):
if not section or not title or not url: if not section or not title or not url:
continue continue
desc = safe_dict(part, "print", "description") or '' desc = safe_dict(part, "print", "description") or ''
sub = safe_dict(part, "print", "subheadline") or ''
if sub and section != sub:
desc = sub + ' :: ' + desc
feeds_dict[section].append({"title": title, "url": url, "description": desc}) feeds_dict[section].append({"title": title, "url": url, "description": desc})
self.log(' ', title, url, '\n ', desc) self.log(' ', title, url, '\n ', desc)
return [(section, articles) for section, articles in feeds_dict.items()] return [(section, articles) for section, articles in feeds_dict.items()]