YGGverse/rssto
1
0
Fork 0
mirror of https://github.com/YGGverse/rssto.git synced 2026-03-31 17:15:29 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

implement allowed_tags config option, format config, update documentation comments

Browse source
This commit is contained in:
yggverse 2026-01-10 22:48:45 +02:00
parent 89cd7cb9cf
commit b34d7cdcdd
3 changed files with 110 additions and 54 deletions
Download patch file Download diff file Expand all files Collapse all files

84
crates/crawler/config.toml
View file

@ -4,29 +4,71 @@ update = 900
# Database connection setup
# * see crates/mysql/database
[mysql]
host = "localhost"
port = 3306
username = ""
password = ""
database = "rssto"
host = "localhost"
port = 3306
username = ""
password = ""
database = "rssto"
# Content sources (unlimited)
[[channel]]
url = "https://"
items_limit = 20
persist_item_title = true
persist_item_description = true
# optional:
# content_title_selector = "h1"
# content_description_selector = "article"
# persist_images_selector = "img"
# RSS feed source
url = "https://1"
# Limit latest channel items to crawl (unlimited by default)
items_limit = 20
# Save Channel item title in the database (currently not in use)
persist_item_title = true
#Save Channel item description in the database (currently not in use)
persist_item_description = true
# Allowed tags
# * empty to strip all tags (default)
allowed_tags = []
# Scrape title by CSS selector
# * None to use Channel item title if exists or fail to continue
# content_title_selector = "h1"
# Scrape description by CSS selector
# * None to use Channel item description if exists or fail to continue
# content_description_selector = "article"
# Preload content images locally if `Some`
# * currently stored in the database
# persist_images_selector = "img"
[[channel]]
url = "https://"
items_limit = 20
persist_item_title = true
persist_item_description = true
# optional:
# content_title_selector = "h1"
# content_description_selector = "article"
# persist_images_selector = "img"
# RSS feed source
url = "https://2"
# Limit latest channel items to crawl (unlimited by default)
items_limit = 20
# Save Channel item title in the database (currently not in use)
persist_item_title = true
#Save Channel item description in the database (currently not in use)
persist_item_description = true
# Allowed tags
# * empty to strip all tags (default)
allowed_tags = []
# Scrape title by CSS selector
# * None to use Channel item title if exists or fail to continue
# content_title_selector = "h1"
# Scrape description by CSS selector
# * None to use Channel item description if exists or fail to continue
# content_description_selector = "article"
# Preload content images locally if `Some`
# * currently stored in the database
# persist_images_selector = "img"