oss/miniflux-v2
oss/miniflux-v2
1
0
Fork 0
mirror of https://github.com/miniflux/v2.git synced 2025-06-27 16:36:00 +00:00
Code Wiki Activity

Improve content scraper

Browse source
This commit is contained in:
Frédéric Guillot 2017-12-13 21:30:40 -08:00
parent 827683ab59
commit c6d9eb3614
7 changed files with 39 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

6
reader/scraper/rules.go
View file

@ -7,10 +7,16 @@ package scraper
// List of predefined scraper rules (alphabetically sorted)
// domain => CSS selectors
var predefinedRules = map[string]string{
"github.com": "article.entry-content",
"igen.fr": "section.corps",
"lemonde.fr": "div#articleBody",
"lesjoiesducode.fr": ".blog-post-content img",
"linux.com": "div.content, div[property]",
"medium.com": ".section-content",
"opensource.com": "div[property]",
"osnews.com": "div.newscontent1",
"phoronix.com": "div.content",
"techcrunch.com": "div.article-entry",
"theregister.co.uk": "#body",
"wired.com": "main figure, article",
}