fix kyiv post recipe fiters

This commit is contained in:
Wes Bradley 2023-10-03 10:06:39 -05:00
parent 503d0e0113
commit 7d08dc4955
3 changed files with 27 additions and 12 deletions

View File

@ -16,14 +16,19 @@ class KyivPost(BasicNewsRecipe):
remove_javascript = True
auto_cleanup = False
oldest_article = 7
max_articles_per_feed = 10
max_articles_per_feed = 20
remove_tags_before = dict(name='article', attrs={'class': 'article'})
remove_tags_before = dict(attrs={'class': 'single-article'})
remove_tags_after = dict(name='article', attrs={'class': 'article'})
remove_tags_after = dict(attrs={'class': 'post-author-block'})
remove_tags = [
dict(name='div', attrs={'class': 'entry-footer hide_post_header'})
dict(attrs={'class': 'post-label-and-topic'}),
dict(attrs={'class': 'sidebar-start'}),
dict(attrs={'class': 'correction'}),
dict(attrs={'id': 'correction'}),
dict(attrs={'class': 'ad_between_paragraphs'}),
dict(attrs={'id': 'insert-post-by-topic'})
]
feeds = [(

View File

@ -16,14 +16,19 @@ class KyivPost(BasicNewsRecipe):
remove_javascript = True
auto_cleanup = False
oldest_article = 7
max_articles_per_feed = 10
max_articles_per_feed = 20
remove_tags_before = dict(name='article', attrs={'class': 'article'})
remove_tags_before = dict(attrs={'class': 'single-article'})
remove_tags_after = dict(name='article', attrs={'class': 'article'})
remove_tags_after = dict(attrs={'class': 'post-author-block'})
remove_tags = [
dict(name='div', attrs={'class': 'entry-footer hide_post_header'})
dict(attrs={'class': 'post-label-and-topic'}),
dict(attrs={'class': 'sidebar-start'}),
dict(attrs={'class': 'correction'}),
dict(attrs={'id': 'correction'}),
dict(attrs={'class': 'ad_between_paragraphs'}),
dict(attrs={'id': 'insert-post-by-topic'})
]
feeds = [('News', 'https://www.kyivpost.com/feed')]

View File

@ -16,14 +16,19 @@ class KyivPost(BasicNewsRecipe):
remove_javascript = True
auto_cleanup = False
oldest_article = 7
max_articles_per_feed = 10
max_articles_per_feed = 20
remove_tags_before = dict(name='article', attrs={'class': 'article'})
remove_tags_before = dict(attrs={'class': 'single-article'})
remove_tags_after = dict(name='article', attrs={'class': 'article'})
remove_tags_after = dict(attrs={'class': 'post-author-block'})
remove_tags = [
dict(name='div', attrs={'class': 'entry-footer hide_post_header'})
dict(attrs={'class': 'post-label-and-topic'}),
dict(attrs={'class': 'sidebar-start'}),
dict(attrs={'class': 'correction'}),
dict(attrs={'id': 'correction'}),
dict(attrs={'class': 'ad_between_paragraphs'}),
dict(attrs={'id': 'insert-post-by-topic'})
]
feeds = [