diff --git a/recipes/bloomberg-business-week.recipe b/recipes/bloomberg-business-week.recipe index aceb01b12b..7d07202200 100644 --- a/recipes/bloomberg-business-week.recipe +++ b/recipes/bloomberg-business-week.recipe @@ -1,10 +1,10 @@ import json import random import time +from collections import defaultdict from calibre.web.feeds.news import BasicNewsRecipe, classes, prefixed_classes from html5_parser import parse -from collections import defaultdict def get_contents(x): @@ -119,7 +119,6 @@ class Bloomberg(BasicNewsRecipe): if h3 and h3.text: sec = self.tag_to_string(h3) self.log(sec) - articles = [] a = div.find(**prefixed_classes('MagazinePageMagazineArchive_storyLink__')) url = a['href'] if url.startswith('http') is False: diff --git a/recipes/times_online.recipe b/recipes/times_online.recipe index d9ff6f72ce..b3a3315c33 100644 --- a/recipes/times_online.recipe +++ b/recipes/times_online.recipe @@ -1,7 +1,10 @@ from urllib.parse import quote + +from calibre.ebooks.BeautifulSoup import BeautifulSoup from calibre.scraper.simple import read_url from calibre.web.feeds.news import BasicNewsRecipe, prefixed_classes + def resize(x): if 'resize' in x: return x.split('&resize')[0] + '&resize=600' @@ -75,7 +78,7 @@ class times(BasicNewsRecipe): for a in soup.findAll('a', href=True): a['href'] = 'http' + a['href'].split('http')[-1] div = soup.findAll(attrs={'style': lambda x: x and x.startswith( - 'color:rgb(51, 51, 51);font-family:TimesDigitalW04-Regular' + 'color:rgb(51, 51, 51);font-family:TimesDigitalW04-Regular' )}) for p in div: p.name = 'p' @@ -101,7 +104,7 @@ class times(BasicNewsRecipe): feeds = [] when = oldest_article*24 - index = 'https://www.thetimes.com/' + index = 'https://www.thetimes.com/' sections = [ 'politics', 'world', 'uk/politics', 'uk/scotland', 'uk', 'comment', 'business-money', 'sport', 'life-style', 'culture', 'magazine', 'travel', 'sunday-times', 'edition', 'article'