Skip to content
Snippets Groups Projects
Commit 48aa0d07 authored by Frédéric Guillot's avatar Frédéric Guillot
Browse files

Add more scraper rules

parent 7d278d49
No related branches found
No related tags found
No related merge requests found
...@@ -7,20 +7,34 @@ package scraper ...@@ -7,20 +7,34 @@ package scraper
// List of predefined scraper rules (alphabetically sorted) // List of predefined scraper rules (alphabetically sorted)
// domain => CSS selectors // domain => CSS selectors
var predefinedRules = map[string]string{ var predefinedRules = map[string]string{
"cbc.ca": ".story-content", "cbc.ca": ".story-content",
"github.com": "article.entry-content", "developpez.com": "div[itemprop=articleBody]",
"igen.fr": "section.corps", "francetvinfo.fr": ".text",
"ing.dk": "section.body", "github.com": "article.entry-content",
"lapresse.ca": ".amorce, .entry", "heise.de": "div.article-content",
"lemonde.fr": "div#articleBody", "igen.fr": "section.corps",
"lesjoiesducode.fr": ".blog-post-content img", "ing.dk": "section.body",
"linux.com": "div.content, div[property]", "lapresse.ca": ".amorce, .entry",
"medium.com": ".section-content", "lemonde.fr": "div#articleBody",
"opensource.com": "div[property]", "lepoint.fr": ".art-text",
"osnews.com": "div.newscontent1", "lesjoiesducode.fr": ".blog-post-content img",
"phoronix.com": "div.content", "lesnumeriques.com": ".text",
"techcrunch.com": "div.article-entry", "linux.com": "div.content, div[property]",
"theregister.co.uk": "#body", "medium.com": ".section-content",
"version2.dk": "section.body", "mac4ever.com": "div[itemprop=articleBody]",
"wired.com": "main figure, article", "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",
} }
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment