rssto/crates/crawler/config.toml

74 lines
2 KiB
TOML

# Rescan feed channels time, in seconds
update = 900
# Database connection setup
# * see crates/mysql/database
[mysql]
host = "localhost"
port = 3306
username = ""
password = ""
database = "rssto"
# Content sources (unlimited)
[[channel]]
# 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]]
# 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"