rules.go 1.9 KB

12345678910111213141516171819202122232425262728293031323334353637383940414243
  1. // Copyright 2017 Frédéric Guillot. All rights reserved.
  2. // Use of this source code is governed by the Apache 2.0
  3. // license that can be found in the LICENSE file.
  4. package scraper // import "miniflux.app/reader/scraper"
  5. // List of predefined scraper rules (alphabetically sorted)
  6. // domain => CSS selectors
  7. var predefinedRules = map[string]string{
  8. "bbc.co.uk": "div.vxp-column--single, div.story-body__inner, ul.gallery-images__list",
  9. "cbc.ca": ".story-content",
  10. "darkreading.com": "#article-main:not(header)",
  11. "developpez.com": "div[itemprop=articleBody]",
  12. "francetvinfo.fr": ".text",
  13. "github.com": "article.entry-content",
  14. "heise.de": "header .article-content__lead, header .article-image, div.article-layout__content.article-content",
  15. "igen.fr": "section.corps",
  16. "ing.dk": "section.body",
  17. "lapresse.ca": ".amorce, .entry",
  18. "lemonde.fr": "article",
  19. "lepoint.fr": ".art-text",
  20. "lesjoiesducode.fr": ".blog-post-content img",
  21. "lesnumeriques.com": ".text",
  22. "linux.com": "div.content, div[property]",
  23. "medium.com": ".section-content",
  24. "mac4ever.com": "div[itemprop=articleBody]",
  25. "monwindows.com": ".blog-post-body",
  26. "npr.org": "#storytext",
  27. "oneindia.com": ".io-article-body",
  28. "opensource.com": "div[property]",
  29. "osnews.com": "div.newscontent1",
  30. "phoronix.com": "div.content",
  31. "pseudo-sciences.org": "#art_main",
  32. "slate.fr": ".field-items",
  33. "techcrunch.com": "div.article-entry",
  34. "theregister.co.uk": "#body",
  35. "universfreebox.com": "#corps_corps",
  36. "version2.dk": "section.body",
  37. "wired.com": "main figure, article",
  38. "zeit.de": ".summary, .article-body",
  39. "zdnet.com": "div.storyBody",
  40. "openingsource.org": "article.suxing-popup-gallery",
  41. }