8000 [pull] main from miniflux:main by pull[bot] · Pull Request #277 · abcdlsj/miniflux · GitHub
[go: up one dir, main page]

Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions internal/reader/rewrite/content_rewrite_rules.go
Original file line number Diff line number Diff line change
Expand Up @@ -10,6 +10,7 @@ package rewrite // import "miniflux.app/v2/internal/reader/rewrite"
var predefinedRules = map[string]string{
"abstrusegoose.com": "add_image_title",
"amazingsuperpowers.com": "add_image_title",
"bleepingcomputer.com": `add_dynamic_image, remove(".ia_ad, .cz-related-article-wrapp, div[align]")`,
"blog.cloudflare.com": `add_image_title,remove("figure.kg-image-card figure.kg-image + img")`,
"cowbirdsinlove.com": "add_image_title",
"drawingboardcomic.com": "add_image_title",
Expand Down
12 changes: 8 additions & 4 deletions internal/reader/sanitizer/sanitizer.go
Original file line number Diff line number Diff line change
Expand Up @@ -253,6 +253,10 @@ func SanitizeHTML(baseURL, rawHTML string, sanitizerOptions *SanitizerOptions) s

buffer.WriteString(token.String())
case html.StartTagToken:
if len(blockedStack) != 0 {
continue
}

parentTag = tagNam 10BC8 e

if isPixelTracker(tagName, token.Attr) {
Expand All @@ -264,7 +268,7 @@ func SanitizeHTML(baseURL, rawHTML string, sanitizerOptions *SanitizerOptions) s
continue
}

if len(blockedStack) == 0 && isValidTag(tagName) {
if isAllowedTag(tagName) {
attrNames, htmlAttributes := sanitizeAttributes(parsedBaseUrl, tagName, token.Attr, sanitizerOptions)
if hasRequiredAttributes(tagName, attrNames) {
if len(attrNames) > 0 {
Expand All @@ -280,7 +284,7 @@ func SanitizeHTML(baseURL, rawHTML string, sanitizerOptions *SanitizerOptions) s
}
case html.EndTagToken:
if len(blockedStack) == 0 {
if isValidTag(tagName) && slices.Contains(tagStack, tagName) {
if isAllowedTag(tagName) && slices.Contains(tagStack, tagName) {
buffer.WriteString("</" + tagName + ">")
}
} else {
Expand All @@ -292,7 +296,7 @@ func SanitizeHTML(baseURL, rawHTML string, sanitizerOptions *SanitizerOptions) s
if isPixelTracker(tagName, token.Attr) {
continue
}
if len(blockedStack) == 0 && isValidTag(tagName) {
if len(blockedStack) == 0 && isAllowedTag(tagName) {
attrNames, htmlAttributes := sanitizeAttributes(parsedBaseUrl, tagName, token.Attr, sanitizerOptions)
if hasRequiredAttributes(tagName, attrNames) {
if len(attrNames) > 0 {
Expand Down Expand Up @@ -440,7 +444,7 @@ func getExtraAttributes(tagName string, isYouTubeEmbed bool, sanitizerOptions *S
}
}

func isValidTag(tagName string) bool {
func isAllowedTag(tagName string) bool {
_, ok := allowedHTMLTagsAndAttributes[tagName]
return ok
}
Expand Down
1 change: 1 addition & 0 deletions internal/reader/scraper/rules.go
Original file line number Diff line number Diff line change
Expand Up @@ -8,6 +8,7 @@ package scraper // import "miniflux.app/v2/internal/reader/scraper"
var predefinedRules = map[string]string{
"arstechnica.com": "div.post-content",
"bbc.co.uk": "div.vxp-column--single, div.story-body__inner, ul.gallery-images__list",
"bleepingcomputer.com": ".articleBody",
"blog.cloudflare.com": "div.post-content",
"cbc.ca": ".story-content",
"darkreading.com": "div.ArticleBase-Body",
Expand Down
Loading
0