forks/miniflux
1
0
Fork 0
Code Releases Activity

Add more scraper rules

Browse source
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

14
reader/scraper/rules.go
View file

@ -8,19 +8,33 @@ package scraper
// domain => CSS selectors // domain => CSS selectors
var predefinedRules = map[string]string{ var predefinedRules = map[string]string{
"cbc.ca": ".story-content", "cbc.ca": ".story-content",
"developpez.com": "div[itemprop=articleBody]",
"francetvinfo.fr": ".text",
"github.com": "article.entry-content", "github.com": "article.entry-content",
"heise.de": "div.article-content",
"igen.fr": "section.corps", "igen.fr": "section.corps",
"ing.dk": "section.body", "ing.dk": "section.body",
"lapresse.ca": ".amorce, .entry", "lapresse.ca": ".amorce, .entry",
"lemonde.fr": "div#articleBody", "lemonde.fr": "div#articleBody",
"lepoint.fr": ".art-text",
"lesjoiesducode.fr": ".blog-post-content img", "lesjoiesducode.fr": ".blog-post-content img",
"lesnumeriques.com": ".text",
"linux.com": "div.content, div[property]", "linux.com": "div.content, div[property]",
"medium.com": ".section-content", "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]", "opensource.com": "div[property]",
"osnews.com": "div.newscontent1", "osnews.com": "div.newscontent1",
"phoronix.com": "div.content", "phoronix.com": "div.content",
"pseudo-sciences.org": "#art_main",
"slate.fr": ".field-items",
"techcrunch.com": "div.article-entry", "techcrunch.com": "div.article-entry",
"theregister.co.uk": "#body", "theregister.co.uk": "#body",
"universfreebox.com": "#corps_corps",
"version2.dk": "section.body", "version2.dk": "section.body",
"wired.com": "main figure, article", "wired.com": "main figure, article",
"zeit.de": ".summary, .article-body",
"zdnet.com": "div.storyBody",
} }