denis/spiderss
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

add optional article scraping

Browse source
This commit is contained in:
Denis Lehmann 2020-04-16 01:43:12 +02:00
parent 2c27ab316c
commit a081019f51
3 changed files with 70 additions and 24 deletions
Download patch file Download diff file Expand all files Collapse all files

8
config.toml
View file

@ -4,17 +4,23 @@ base_directory = '/home/<user>/rss'
# Articles older than max_age (days) will be deleted and not be added
max_age = 30
# Date and time format as strftime to be included in the articles
datetime_format = '%d.%m.%Y %H:%M'
# Feeds
# The category can be empty (''). The feed fill then be stored in the base_directory.
# The category can also be a path, which will result in subdirectories (e.g. 'technology/hardware').
# The name can also be empty (''). feeds with the same category will then be stored in the same directory.
# The name can be empty, too (''). feeds with the same category will then be stored in the same directory.
# If scrape is set to true, the article content will be fetched from it's link. Otherwise the content of the RSS article is used.
[[feed]]
category = 'News'
name = 'Newssite'
url = 'https://example.org/feed'
scrape = false
[[feed]]
category = 'News'
name = 'Newssite 2'
url = 'https://example.org/feed'
scrape = true