1
0
Fork 0
miniflux/reader/scraper/rules.go
David Izquierdo 4fdef7b837 Add scrape and rewrite rules for webtoons
Although the only source I have for the rewrite rule is, in fact, https://github.com/miniflux/v2/pull/892, it does work when combined with add_dynamic_image and scraping the right element. I have not investigated further.

Works around https://github.com/miniflux/v2/issues/775 and https://github.com/miniflux/v2/issues/1871 (as in, gives us working webtoons feeds but referer spoofing would still be a nice tool to have).

Fixes https://github.com/miniflux/v2/issues/256.
2023-07-10 21:25:48 -07:00

57 lines
2.7 KiB
Go

// SPDX-FileCopyrightText: Copyright The Miniflux Authors. All rights reserved.
// SPDX-License-Identifier: Apache-2.0
package scraper // import "miniflux.app/reader/scraper"
// List of predefined scraper rules (alphabetically sorted)
// domain => CSS selectors
var predefinedRules = map[string]string{
"bbc.co.uk": "div.vxp-column--single, div.story-body__inner, ul.gallery-images__list",
"blog.cloudflare.com": "div.post-content",
"cbc.ca": ".story-content",
"darkreading.com": "#article-main:not(header)",
"developpez.com": "div[itemprop=articleBody]",
"dilbert.com": "span.comic-title-name, img.img-comic",
"explosm.net": "div#comic",
"financialsamurai.com": "article",
"francetvinfo.fr": ".text",
"github.com": "article.entry-content",
"heise.de": "header .article-content__lead, header .article-image, div.article-layout__content.article-content",
"igen.fr": "section.corps",
"ikiwiki.iki.fi": ".page.group",
"ilpost.it": ".entry-content",
"ing.dk": "section.body",
"lapresse.ca": ".amorce, .entry",
"lemonde.fr": "article",
"lepoint.fr": ".art-text",
"lesjoiesducode.fr": ".blog-post-content img",
"lesnumeriques.com": ".text",
"linux.com": "div.content, div[property]",
"mac4ever.com": "div[itemprop=articleBody]",
"monwindows.com": ".blog-post-body",
"npr.org": "#storytext",
"oneindia.com": ".io-article-body",
"opensource.com": "div[property]",
"openingsource.org": "article.suxing-popup-gallery",
"osnews.com": "div.newscontent1",
"phoronix.com": "div.content",
"pseudo-sciences.org": "#art_main",
"quantamagazine.org": ".outer--content, figure, script",
"raywenderlich.com": "article",
"royalroad.com": ".author-note-portlet,.chapter-content",
"slate.fr": ".field-items",
"smbc-comics.com": "div#cc-comicbody, div#aftercomic",
"swordscomic.com": "img#comic-image, div#info-frame.tab-content-area",
"techcrunch.com": "div.article-entry",
"theoatmeal.com": "div#comic",
"theregister.com": "#top-col-story h2, #body",
"theverge.com": "h2.inline:nth-child(2),h2.duet--article--dangerously-set-cms-markup,figure.w-full,div.duet--article--article-body-component",
"turnoff.us": "article.post-content",
"universfreebox.com": "#corps_corps",
"version2.dk": "section.body",
"wdwnt.com": "div.entry-content",
"webtoons.com": ".viewer_img",
"wired.com": "main figure, article",
"zeit.de": ".summary, .article-body",
"zdnet.com": "div.storyBody",
}