rules.go 2.2 KB

12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849
  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. "dilbert.com": "span.comic-title-name, img.img-comic",
  13. "financialsamurai.com": "article",
  14. "francetvinfo.fr": ".text",
  15. "github.com": "article.entry-content",
  16. "heise.de": "header .article-content__lead, header .article-image, div.article-layout__content.article-content",
  17. "igen.fr": "section.corps",
  18. "ikiwiki.iki.fi": ".page.group",
  19. "ing.dk": "section.body",
  20. "lapresse.ca": ".amorce, .entry",
  21. "lemonde.fr": "article",
  22. "lepoint.fr": ".art-text",
  23. "lesjoiesducode.fr": ".blog-post-content img",
  24. "lesnumeriques.com": ".text",
  25. "linux.com": "div.content, div[property]",
  26. "mac4ever.com": "div[itemprop=articleBody]",
  27. "monwindows.com": ".blog-post-body",
  28. "npr.org": "#storytext",
  29. "oneindia.com": ".io-article-body",
  30. "opensource.com": "div[property]",
  31. "osnews.com": "div.newscontent1",
  32. "phoronix.com": "div.content",
  33. "pseudo-sciences.org": "#art_main",
  34. "raywenderlich.com": "article",
  35. "slate.fr": ".field-items",
  36. "techcrunch.com": "div.article-entry",
  37. "theoatmeal.com": "div#comic",
  38. "theregister.com": "#top-col-story h2, #body",
  39. "turnoff.us": "article.post-content",
  40. "universfreebox.com": "#corps_corps",
  41. "version2.dk": "section.body",
  42. "wdwnt.com": "div.entry-content",
  43. "wired.com": "main figure, article",
  44. "zeit.de": ".summary, .article-body",
  45. "zdnet.com": "div.storyBody",
  46. "openingsource.org": "article.suxing-popup-gallery",
  47. }