rules.go 2.9 KB

12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061
  1. // SPDX-FileCopyrightText: Copyright The Miniflux Authors. All rights reserved.
  2. // SPDX-License-Identifier: Apache-2.0
  3. package scraper // import "miniflux.app/v2/internal/reader/scraper"
  4. // List of predefined scraper rules (alphabetically sorted)
  5. // domain => CSS selectors
  6. var predefinedRules = map[string]string{
  7. "arstechnica.com": "div.post-content",
  8. "bbc.co.uk": "div.vxp-column--single, div.story-body__inner, ul.gallery-images__list",
  9. "bleepingcomputer.com": ".articleBody",
  10. "blog.cloudflare.com": "div.post-content",
  11. "cbc.ca": ".story-content",
  12. "darkreading.com": "div.ArticleBase-Body",
  13. "developpez.com": "div[itemprop=articleBody]",
  14. "dilbert.com": "span.comic-title-name, img.img-comic",
  15. "explosm.net": "div#comic",
  16. "financialsamurai.com": "article",
  17. "francetvinfo.fr": ".text",
  18. "github.com": "article.entry-content",
  19. "heise.de": "header .article-content__lead, header .article-image, div.article-layout__content.article-content",
  20. "igen.fr": "section.corps",
  21. "ikiwiki.iki.fi": ".page.group",
  22. "ilpost.it": ".entry-content",
  23. "ing.dk": "section.body",
  24. "lapresse.ca": ".amorce, .entry",
  25. "lemonde.fr": "article",
  26. "lepoint.fr": ".art-text",
  27. "lesjoiesducode.fr": ".blog-post-content img",
  28. "lesnumeriques.com": ".text",
  29. "linux.com": "div.content, div[property]",
  30. "mac4ever.com": "div[itemprop=articleBody]",
  31. "monwindows.com": ".blog-post-body",
  32. "npr.org": "#storytext",
  33. "oneindia.com": ".io-article-body",
  34. "opensource.com": "div[property]",
  35. "openingsource.org": "article.suxing-popup-gallery",
  36. "osnews.com": "div.newscontent1",
  37. "phoronix.com": "div.content",
  38. "pitchfork.com": "#main-content",
  39. "pseudo-sciences.org": "#art_main",
  40. "quantamagazine.org": ".outer--content, figure, script",
  41. "raywenderlich.com": "article",
  42. "royalroad.com": ".author-note-portlet,.chapter-content",
  43. "slate.fr": ".field-items",
  44. "smbc-comics.com": "div#cc-comicbody, div#aftercomic",
  45. "swordscomic.com": "img#comic-image, div#info-frame.tab-content-area",
  46. "techcrunch.com": "div.entry-content",
  47. "theoatmeal.com": "div#comic",
  48. "theregister.com": "#top-col-story h2, #body",
  49. "theverge.com": "h2.inline:nth-child(2),h2.duet--article--dangerously-set-cms-markup,figure.w-full,div.duet--article--article-body-component",
  50. "turnoff.us": "article.post-content",
  51. "universfreebox.com": "#corps_corps",
  52. "version2.dk": "section.body",
  53. "vnexpress.net": ".detail-new p.description, article.fck_detail",
  54. "wdwnt.com": "div.entry-content",
  55. "webtoons.com": ".viewer_img,p.author_text",
  56. "wired.com": "main figure, article",
  57. "zeit.de": ".summary, .article-body",
  58. "zdnet.com": "div.storyBody",
  59. }