aboutsummaryrefslogtreecommitdiffhomepage
path: root/reader/scraper
diff options
context:
space:
mode:
authorGravatar Frédéric Guillot <fred@miniflux.net>2018-01-04 19:32:24 -0800
committerGravatar Frédéric Guillot <fred@miniflux.net>2018-01-04 19:32:24 -0800
commit48aa0d07ef98fe5ebc1a762a876f140cb9528a6a (patch)
tree1264330bef4e65765695cd867641a8d666b256ab /reader/scraper
parent7d278d49f1da6b8dc8b31faf46d4127db5f7f711 (diff)
Add more scraper rules
Diffstat (limited to 'reader/scraper')
-rw-r--r--reader/scraper/rules.go46
1 files changed, 30 insertions, 16 deletions
diff --git a/reader/scraper/rules.go b/reader/scraper/rules.go
index 6fddd1e..f988c24 100644
--- a/reader/scraper/rules.go
+++ b/reader/scraper/rules.go
@@ -7,20 +7,34 @@ package scraper
// List of predefined scraper rules (alphabetically sorted)
// domain => CSS selectors
var predefinedRules = map[string]string{
- "cbc.ca": ".story-content",
- "github.com": "article.entry-content",
- "igen.fr": "section.corps",
- "ing.dk": "section.body",
- "lapresse.ca": ".amorce, .entry",
- "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",
- "version2.dk": "section.body",
- "wired.com": "main figure, article",
+ "cbc.ca": ".story-content",
+ "developpez.com": "div[itemprop=articleBody]",
+ "francetvinfo.fr": ".text",
+ "github.com": "article.entry-content",
+ "heise.de": "div.article-content",
+ "igen.fr": "section.corps",
+ "ing.dk": "section.body",
+ "lapresse.ca": ".amorce, .entry",
+ "lemonde.fr": "div#articleBody",
+ "lepoint.fr": ".art-text",
+ "lesjoiesducode.fr": ".blog-post-content img",
+ "lesnumeriques.com": ".text",
+ "linux.com": "div.content, div[property]",
+ "medium.com": ".section-content",
+ "mac4ever.com": "div[itemprop=articleBody]",
+ "monwindows.com": ".blog-post-body",
+ "npr.org": "#storytext",
+ "oneindia.com": ".io-article-body",
+ "opensource.com": "div[property]",
+ "osnews.com": "div.newscontent1",
+ "phoronix.com": "div.content",
+ "pseudo-sciences.org": "#art_main",
+ "slate.fr": ".field-items",
+ "techcrunch.com": "div.article-entry",
+ "theregister.co.uk": "#body",
+ "universfreebox.com": "#corps_corps",
+ "version2.dk": "section.body",
+ "wired.com": "main figure, article",
+ "zeit.de": ".summary, .article-body",
+ "zdnet.com": "div.storyBody",
}