rdelaage
/
miniflux-v2
mirror of https://github.com/miniflux/v2.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Add more scraper rules

This commit is contained in:
Frédéric Guillot 2018-01-04 19:32:24 -08:00
parent 7d278d49f1
commit 48aa0d07ef
1 changed files with 30 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

46
reader/scraper/rules.go
View File

@ -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",
}