oss/miniflux-v2
oss/miniflux-v2
1
0
Fork 0
mirror of https://github.com/miniflux/v2.git synced 2025-08-11 17:51:01 +00:00
Code Wiki Activity

feat(readability): avoid removing elements with content class

Browse source
This commit is contained in:
Frédéric Guillot 2025-07-25 19:59:47 -07:00
parent 54abd0a736
commit 66b269e6cd
1 changed files with 9 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

18
internal/reader/readability/readability.go
View file

@ -18,9 +18,9 @@ import (
const defaultTagsToScore = "section,h2,h3,h4,h5,h6,p,td,pre,div" const defaultTagsToScore = "section,h2,h3,h4,h5,h6,p,td,pre,div"
var ( var (
strongCandidates = [...]string{"popupbody", "-ad", "g-plus"} strongCandidatesToRemove = [...]string{"popupbody", "-ad", "g-plus"}
maybeCandidate = [...]string{"and", "article", "body", "column", "main", "shadow"} maybeCandidateToRemove = [...]string{"and", "article", "body", "column", "main", "shadow", "content"}
unlikelyCandidate = [...]string{"banner", "breadcrumbs", "combx", "comment", "community", "cover-wrap", "disqus", "extra", "foot", "header", "legends", "menu", "modal", "related", "remark", "replies", "rss", "shoutbox", "sidebar", "skyscraper", "social", "sponsor", "supplemental", "ad-break", "agegate", "pagination", "pager", "popup", "yom-remote"} unlikelyCandidateToRemove = [...]string{"banner", "breadcrumbs", "combx", "comment", "community", "cover-wrap", "disqus", "extra", "foot", "header", "legends", "menu", "modal", "related", "remark", "replies", "rss", "shoutbox", "sidebar", "skyscraper", "social", "sponsor", "supplemental", "ad-break", "agegate", "pagination", "pager", "popup", "yom-remote"}
positiveKeywords = [...]string{"article", "blog", "body", "content", "entry", "h-entry", "hentry", "main", "page", "pagination", "post", "story", "text"} positiveKeywords = [...]string{"article", "blog", "body", "content", "entry", "h-entry", "hentry", "main", "page", "pagination", "post", "story", "text"}
negativeKeywords = [...]string{"author", "banner", "byline", "com-", "combx", "comment", "contact", "dateline", "foot", "hid", "masthead", "media", "meta", "modal", "outbrain", "promo", "related", "scroll", "share", "shopping", "shoutbox", "sidebar", "skyscraper", "sponsor", "tags", "tool", "widget", "writtenby"} negativeKeywords = [...]string{"author", "banner", "byline", "com-", "combx", "comment", "contact", "dateline", "foot", "hid", "masthead", "media", "meta", "modal", "outbrain", "promo", "related", "scroll", "share", "shopping", "shoutbox", "sidebar", "skyscraper", "sponsor", "tags", "tool", "widget", "writtenby"}
@ -185,17 +185,17 @@ func shouldRemoveCandidate(str string) bool {
str = strings.ToLower(str) str = strings.ToLower(str)
// Those candidates have no false-positives, no need to check against `maybeCandidate` // Those candidates have no false-positives, no need to check against `maybeCandidate`
for _, strongCandidate := range strongCandidates { for _, strongCandidateToRemove := range strongCandidatesToRemove {
if strings.Contains(str, strongCandidate) { if strings.Contains(str, strongCandidateToRemove) {
return true return true
} }
} }
for _, unlikelyCandidate := range unlikelyCandidate { for _, unlikelyCandidateToRemove := range unlikelyCandidateToRemove {
if strings.Contains(str, unlikelyCandidate) { if strings.Contains(str, unlikelyCandidateToRemove) {
// Do we have a false positive? // Do we have a false positive?
for _, maybe := range maybeCandidate { for _, maybeCandidateToRemove := range maybeCandidateToRemove {
if strings.Contains(str, maybe) { if strings.Contains(str, maybeCandidateToRemove) {
return false return false
} }
} }