Create dataset lihkg

[albertvillanova]

• uid: lihkg
• type: primary
• description:
  • name: LIHKG
  • description: Most Popular Hong Kong Forum
  • homepage: https://lihkg.com/category/1
  • validated: True
• languages:
  • language_names:
    • Chinese
    • Yue Chinese, Cantonese
  • language_comments: Cantonese
  • language_locations:
    • Eastern Asia
    • Hong Kong
  • validated: False
• custodian:
  • name: 許業珩
  • in_catalogue:
  • type: A private individual
  • location: Hong Kong
  • contact_name: 許業珩
  • contact_email:
  • contact_submitter: False
  • additional: https://lihkg.com/thread/1660096/page/1
  • validated: False
• availability:
  • procurement:
    • for_download: No - but the current owners/custodians have contact information for data queries
    • download_url:
    • download_email: https://t.me/lihkg_official
  • licensing:
    • has_licenses: Unclear
    • license_text:
    • license_properties:
    • license_list:
  • pii:
    • has_pii: Yes - text author name only
    • generic_pii_likely:
    • generic_pii_list:
    • numeric_pii_likely:
    • numeric_pii_list:
    • sensitive_pii_likely:
    • sensitive_pii_list:
    • no_pii_justification_class: general knowledge not written by or referring to private persons
    • no_pii_justification_text:
  • validated: False
• source_category:
  • category_type: website
  • category_web: forum
  • category_media:
  • validated: False
• media:
  • category:
    • text
    • image
  • text_format:
    • .HTML
  • audiovisual_format:
  • image_format:
    • .JPEG
  • database_format:
  • text_is_transcribed: No
  • instance_type: post
  • instance_count: 100K<n<1M
  • instance_size: 10<n<100
  • validated: False
• fname: lihkg.json