extract-webpage 1.2.5

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (117) hide show
  1. package/README.md +212 -0
  2. package/dist/config/env.d.ts +6 -0
  3. package/dist/config/index.d.ts +23 -0
  4. package/dist/config/serverRegistry.d.ts +7 -0
  5. package/dist/config/types.d.ts +4 -0
  6. package/dist/extract-webpage.cjs.js +2 -0
  7. package/dist/extract-webpage.cjs.js.map +1 -0
  8. package/dist/extract-webpage.es.js +5 -0
  9. package/dist/extract-webpage.es.js.map +1 -0
  10. package/dist/html-to-cite/extract-author.d.ts +11 -0
  11. package/dist/html-to-cite/extract-cite.d.ts +33 -0
  12. package/dist/html-to-cite/extract-date/date-extractors.d.ts +40 -0
  13. package/dist/html-to-cite/extract-date/date-validators.d.ts +15 -0
  14. package/dist/html-to-cite/extract-date/extract-date-quick.d.ts +8 -0
  15. package/dist/html-to-cite/extract-date/extract-date.d.ts +26 -0
  16. package/dist/html-to-cite/extract-source.d.ts +7 -0
  17. package/dist/html-to-cite/extract-title.d.ts +11 -0
  18. package/dist/html-to-cite/human-names-recognize.d.ts +16 -0
  19. package/dist/html-to-cite/metadata-to-cite.d.ts +12 -0
  20. package/dist/html-to-cite/url-to-domain.d.ts +20 -0
  21. package/dist/html-to-content/extract-content/extract-content-mercury-utils.d.ts +27 -0
  22. package/dist/html-to-content/extract-content/extract-content-mercury.d.ts +61 -0
  23. package/dist/html-to-content/extract-content/extract-content-readability.d.ts +101 -0
  24. package/dist/html-to-content/html-to-basic-html.d.ts +36 -0
  25. package/dist/html-to-content/html-to-content.d.ts +51 -0
  26. package/dist/html-to-content/html-utils.d.ts +76 -0
  27. package/dist/index.d.ts +26 -0
  28. package/dist/search/index.d.ts +14 -0
  29. package/dist/search/meta-search-agent-reexport.d.ts +8 -0
  30. package/dist/search/public-searxng.d.ts +47 -0
  31. package/dist/search/search-web.d.ts +33 -0
  32. package/dist/search/tavily.d.ts +20 -0
  33. package/dist/search/url-to-html.d.ts +62 -0
  34. package/dist/seektopic/fold-keyphrases.d.ts +28 -0
  35. package/dist/seektopic/ngrams.d.ts +27 -0
  36. package/dist/seektopic/rank-sentences-keyphrases.d.ts +28 -0
  37. package/dist/seektopic/seektopic-keyphrases.d.ts +53 -0
  38. package/dist/seektopic/types.d.ts +86 -0
  39. package/dist/seektopic/vector-search.d.ts +89 -0
  40. package/dist/seektopic/weight-keyphrases.d.ts +22 -0
  41. package/dist/suggest-next-words/autocomplete-ai.d.ts +0 -0
  42. package/dist/suggest-next-words/autocomplete-search-engines.d.ts +64 -0
  43. package/dist/tokenize/suggest-complete-word.d.ts +48 -0
  44. package/dist/tokenize/text-to-chunks.d.ts +48 -0
  45. package/dist/tokenize/text-to-sentences.d.ts +35 -0
  46. package/dist/tokenize/text-to-topic-tokens.d.ts +51 -0
  47. package/dist/tokenize/word-is-ignored.d.ts +12 -0
  48. package/dist/tokenize/word-to-root-stem.d.ts +16 -0
  49. package/dist/url-to-content/docx-to-content.d.ts +22 -0
  50. package/dist/url-to-content/is-url-adult.d.ts +26 -0
  51. package/dist/url-to-content/url-to-content.d.ts +127 -0
  52. package/dist/url-to-content/url-to-html.d.ts +60 -0
  53. package/dist/url-to-content/youtube-helpers.d.ts +23 -0
  54. package/dist/url-to-content/youtube-to-text.d.ts +70 -0
  55. package/dist/utils/documents.d.ts +4 -0
  56. package/dist/utils/grab.d.ts +18 -0
  57. package/package.json +109 -0
  58. package/src/config/env.ts +8 -0
  59. package/src/config/index.ts +233 -0
  60. package/src/config/serverRegistry.ts +24 -0
  61. package/src/config/types.ts +17 -0
  62. package/src/fs-mock.js +22 -0
  63. package/src/global.d.ts +8 -0
  64. package/src/html-to-cite/extract-author.ts +125 -0
  65. package/src/html-to-cite/extract-cite.ts +97 -0
  66. package/src/html-to-cite/extract-date/date-extractors.ts +484 -0
  67. package/src/html-to-cite/extract-date/date-validators.ts +191 -0
  68. package/src/html-to-cite/extract-date/extract-date-quick.ts +184 -0
  69. package/src/html-to-cite/extract-date/extract-date.ts +1049 -0
  70. package/src/html-to-cite/extract-source.ts +30 -0
  71. package/src/html-to-cite/extract-title.ts +78 -0
  72. package/src/html-to-cite/human-names-92k.json +1 -0
  73. package/src/html-to-cite/human-names-recognize.ts +396 -0
  74. package/src/html-to-cite/metadata-to-cite.ts +73 -0
  75. package/src/html-to-cite/url-to-domain.ts +50 -0
  76. package/src/html-to-content/extract-content/extract-content-mercury-utils.ts +696 -0
  77. package/src/html-to-content/extract-content/extract-content-mercury.ts +830 -0
  78. package/src/html-to-content/extract-content/extract-content-readability.ts +432 -0
  79. package/src/html-to-content/extract-content/extract-selectors-per-domain.json +3453 -0
  80. package/src/html-to-content/html-to-basic-html.ts +282 -0
  81. package/src/html-to-content/html-to-content.ts +97 -0
  82. package/src/html-to-content/html-utils.ts +398 -0
  83. package/src/index.ts +29 -0
  84. package/src/search/__tests__/public-searxng.test.ts +529 -0
  85. package/src/search/index.ts +43 -0
  86. package/src/search/meta-search-agent-reexport.ts +38 -0
  87. package/src/search/public-searxng.ts +470 -0
  88. package/src/search/search-web.ts +668 -0
  89. package/src/search/tavily.ts +106 -0
  90. package/src/search/url-to-html.ts +278 -0
  91. package/src/seektopic/fold-keyphrases.ts +87 -0
  92. package/src/seektopic/ngrams.ts +64 -0
  93. package/src/seektopic/rank-sentences-keyphrases.ts +132 -0
  94. package/src/seektopic/seektopic-keyphrases.ts +279 -0
  95. package/src/seektopic/types.ts +92 -0
  96. package/src/seektopic/vector-search.ts +232 -0
  97. package/src/seektopic/weight-keyphrases.ts +59 -0
  98. package/src/suggest-next-words/autocomplete-ai.ts +38 -0
  99. package/src/suggest-next-words/autocomplete-search-engines.ts +435 -0
  100. package/src/tokenize/suggest-complete-word.ts +137 -0
  101. package/src/tokenize/text-to-chunks.ts +150 -0
  102. package/src/tokenize/text-to-sentences.ts +614 -0
  103. package/src/tokenize/text-to-topic-tokens.ts +175 -0
  104. package/src/tokenize/word-is-ignored.ts +53 -0
  105. package/src/tokenize/word-to-root-stem.ts +151 -0
  106. package/src/types.d.ts +130 -0
  107. package/src/url-to-content/.fuse_hidden003bd28a0000000d +332 -0
  108. package/src/url-to-content/__tests__/url-to-content.test.ts +368 -0
  109. package/src/url-to-content/__tests__/url-to-html.test.ts +301 -0
  110. package/src/url-to-content/docx-to-content.ts +702 -0
  111. package/src/url-to-content/is-url-adult.ts +318 -0
  112. package/src/url-to-content/url-to-content.ts +367 -0
  113. package/src/url-to-content/url-to-html.ts +436 -0
  114. package/src/url-to-content/youtube-helpers.ts +64 -0
  115. package/src/url-to-content/youtube-to-text.ts +468 -0
  116. package/src/utils/documents.ts +71 -0
  117. package/src/utils/grab.ts +51 -0

There are too many changes on this page to be displayed.


The amount of changes on this page would crash your brower.

You can still verify the content by downloading the package file manually.