← back to Paul Conrad Archive

data/exports/summary.json

1035 lines

{
 "total_canonical_item_level": 380,
 "total_box_range_slots": 8628,
 "total_folder_records": 69,
 "total_source_records": 17795,
 "total_source_records_live": 8799,
 "total_repositories_with_records": 15,
 "total_sources_registered": 52,
 "earliest_item": [
  "1950-01-01..1963-12-31",
  "Reporter riding a worn burro backwards",
  "cat:obit-burro-denver"
 ],
 "earliest_item_exact": [
  "1967-01-27",
  "Apollo 1 tragedy \u2014 'I thought you knew, I've been aboard on every flight'",
  "cat:obit-apollo1-1967"
 ],
 "latest_item": [
  "2008-01-01..2008-12-31",
  "Sarah Palin with the slain Republican elephant",
  "cat:obit-palin-2008"
 ],
 "latest_item_exact": [
  "2003-12-25",
  "I'll be home for Christmas....",
  "lat:lat-home-for-christmas-2003"
 ],
 "earliest_any": [
  "1950-01-01"
 ],
 "latest_any": [
  "2008-12-31"
 ],
 "auto_linked_duplicates": 20,
 "possible_duplicates_for_review": 12,
 "contained_in_candidates": 554,
 "canonical_with_public_image_link": 79,
 "canonical_requiring_archive_access": 8900,
 "archive_access_items": 207,
 "local_images_stored": 0,
 "source_rows_by_acquisition_method": {
  "seed_direct": 8692,
  "direct_html": 8660,
  "seed_via_reader_bypass": 272,
  "secondary_citation": 102,
  "direct_api": 69
 },
 "item_level_pending_direct_verification": 207,
 "item_level_secondary_citation_only": 76,
 "years_with_no_item_records": [
  1945,
  1946,
  1947,
  1948,
  1949,
  1950,
  1951,
  1952,
  1953,
  1954,
  1955,
  1956,
  1960,
  1966,
  1981,
  1995,
  1996,
  1998,
  1999,
  2002,
  2005,
  2006,
  2007,
  2009,
  2010
 ],
 "years_with_no_records_at_all": [
  1945,
  1946,
  1947,
  1948,
  1949,
  1950,
  1951,
  1952,
  1953,
  1954,
  1955,
  1956,
  2005,
  2006,
  2007,
  2009,
  2010
 ],
 "per_source": [
  {
   "source_id": "billy_ireland_dc",
   "name": "Ohio State Billy Ireland \u2014 Digital Collections catalog JSON (library.osu.edu/dc)",
   "repository": null,
   "classification": "PUBLIC_HTML",
   "status": "failed",
   "rows": 0,
   "item": 0,
   "folder": 0,
   "box_range": 0,
   "public_image": 0,
   "archive": 0,
   "pages": null,
   "errors": null,
   "notes": "not measured \u2014 endpoint timed out / errored after retries (HTTP 504 at https://library.osu.edu/dc/catalog.json?q=%22paul+conrad%22&per_page=100)",
   "url": "https://library.osu.edu/dc/catalog.json",
   "access_notes": null
  },
  {
   "source_id": "calisphere",
   "name": "Calisphere (UC Libraries)",
   "repository": null,
   "classification": "REQUIRES_PERMISSION",
   "status": "blocked",
   "rows": 0,
   "item": 0,
   "folder": 0,
   "box_range": 0,
   "public_image": 0,
   "archive": 0,
   "pages": null,
   "errors": null,
   "notes": "AWS WAF JS challenge for non-browser clients; probe: robots.txt unreadable (HTTP 401/403 or WAF challenge) \u2014 treated as disallowed: https://calisphere.org/search/?q=%22paul+conrad%22",
   "url": "https://calisphere.org/search/?q=%22paul+conrad%22",
   "access_notes": null
  },
  {
   "source_id": "cdnc",
   "name": "California Digital Newspaper Collection (cdnc.ucr.edu, Veridian)",
   "repository": null,
   "classification": "REQUIRES_PERMISSION",
   "status": "blocked",
   "rows": 0,
   "item": 0,
   "folder": 0,
   "box_range": 0,
   "public_image": 0,
   "archive": 0,
   "pages": null,
   "errors": null,
   "notes": "robots.txt 'User-agent: * Disallow: /' (only archive.org_bot/bingbot allowed, and even they may not query) (robots.txt disallows https://cdnc.ucr.edu/?a=q&txq=%22Paul+Conrad%22)",
   "url": "https://cdnc.ucr.edu/?a=q&txq=%22Paul+Conrad%22",
   "access_notes": null
  },
  {
   "source_id": "chronicling_america",
   "name": "Chronicling America (loc.gov, digitized newspapers to 1963)",
   "repository": null,
   "classification": "PUBLIC_API",
   "status": "worked",
   "rows": 0,
   "item": 0,
   "folder": 0,
   "box_range": 0,
   "public_image": 0,
   "archive": 0,
   "pages": null,
   "errors": null,
   "notes": "q=\"paul conrad\" 1946-1963: 23 page hit(s); Conrad drew for the Denver Post (not in Chronicling America) and was syndicated only from 1964 -> 0 records; hits: 1949-11-19 Image 2 of Kodiak mirror (Kodiak, Alaska), Novembe; 1954-10-25 Image 32 of Evening star (Washington, D.C.), Octob; 1960-12-22 Image 5 of Westside enterprise (Goodyear, Ariz.), ; 1959-06-19 Image 4 of El sol (Phoenix, Ariz.), June 19, 1959; 1951-11-29 Image 46 of Evening star (Washington, D.C.), Novem; 1952-08-05 Image 2 of Le messager (Lewiston, Me.), August 5, ; 1951-12-23 Image 64 of Evening star (Washington, D.C.), Decem; 1963-10-24 Image 21 of Evening star (Washington, D.C.), Octob; 1962-12-07 Image 1 of Washington Journal (Washington, D.C.), ; 1957-04-05 Image 4 of The Harlem news (Harlem, Mont.), April ",
   "url": "https://www.loc.gov/collections/chronicling-america/",
   "access_notes": null
  },
  {
   "source_id": "colorado_newspapers",
   "name": "Colorado Historic Newspapers (Veridian)",
   "repository": null,
   "classification": "REQUIRES_PERMISSION",
   "status": "blocked",
   "rows": 0,
   "item": 0,
   "folder": 0,
   "box_range": 0,
   "public_image": 0,
   "archive": 0,
   "pages": null,
   "errors": null,
   "notes": "robots.txt 'User-agent: * Disallow: /' (Veridian default); Denver Post 1950-64 not reachable (robots.txt disallows https://www.coloradohistoricnewspapers.org/?a=q&txq=%22Paul+Conrad%22)",
   "url": "https://www.coloradohistoricnewspapers.org/?a=q&txq=%22Paul+Conrad%22",
   "access_notes": null
  },
  {
   "source_id": "daily_iowan",
   "name": "The Daily Iowan digital archive (University of Iowa Libraries)",
   "repository": "University of Iowa Libraries",
   "classification": "PUBLIC_HTML",
   "status": "partial",
   "rows": 0,
   "item": 0,
   "folder": 0,
   "box_range": 0,
   "public_image": 0,
   "archive": 0,
   "pages": 15,
   "errors": 0,
   "notes": "issue PDFs listed 1945-1950: {1945: 306, 1946: 308, 1947: 308, 1948: 308, 1949: 307, 1950: 308} (total 1845); full list -> data/exports/daily_iowan_issues_1945_1950.csv; no PDF downloaded; text-layer probe: NO separate text layer exposed [di1947-07-01.txt=HTTP 404; di1947-07-01.xml=HTTP 404; di1947-07-01.hocr=HTTP 404; di1947-07-01.html=HTTP 404; di1949-07-01.txt=HTTP 404; di1949-07-01.xml=HTTP 404; di1949-07-01.hocr=HTTP 404; di1949-07-01.html=HTTP 404; DI/1948/ listing=blocked (HTTP 403 (access denied) at https://dailyiowan.lib.uiowa.edu/DI/1948/); search/=Google CSE embed (cse.google.com robots Disallow: / -> not used); digital.lib.uiowa.edu=robots unreadable/disallowed (403) -> not crawled]; not in Chronicling America (loc.gov Iowa titles 1946-1950 exclude it) and no Internet Archive run (checked 2026-09-24); 0 cartoon records added: no permitted text layer; OCR of scans is out of bounds",
   "url": "https://dailyiowan.lib.uiowa.edu/",
   "access_notes": "Issue-level PDFs only, public (robots allows /). No separate text/OCR layer is exposed: no .txt/ALTO/hOCR sidecars, search is a Google CSE embed (cse.google.com robots Disallow: /), Iowa Digital Library host 403s even robots.txt. Any OCR text lives only inside the PDFs, which this project may not download. Conrad's student cartoons need manual page review \u2014 issue list in data/exports/daily_iowan_issues_1945_1950.csv."
  },
  {
   "source_id": "denver_post",
   "name": "Denver Post archive (newspapers.com / NewsBank)",
   "repository": "Denver Post",
   "classification": "PAYWALLED",
   "status": "not_attempted",
   "rows": 0,
   "item": 0,
   "folder": 0,
   "box_range": 0,
   "public_image": 0,
   "archive": 0,
   "pages": 0,
   "errors": 0,
   "notes": "paywalled \u2014 not crawled; 7 item records elsewhere are attributed to the Denver Post",
   "url": "https://denverpost.newspapers.com/",
   "access_notes": "Denver Post 1950-1964 pages via subscription databases or Denver Public Library microfilm."
  },
  {
   "source_id": "discovery",
   "name": "Discovery pass (DPLA, Smithsonian, probes)",
   "repository": "multiple",
   "classification": "PUBLIC_API",
   "status": "worked",
   "rows": 0,
   "item": 0,
   "folder": 0,
   "box_range": 0,
   "public_image": 0,
   "archive": 0,
   "pages": 8,
   "errors": 3,
   "notes": "non-cartoon references: DPLA non-image ref (sound): Paul Conrad cartoons and drawings; DeWain Valentine: New York; Ken Price \"Happy's Curious\" || DPLA non-image ref (sound): Paul Conrad cartoons and drawings; DeWain Valentine: New York; Ken Price \"Happy's Curious\" || SI SIL library record: Pro and Conrad / Paul Conrad || SI SIL library record: Cartoon America : comic art in the Library of Congress / [edited by] Harry Katz || SI SIL library record: Cartoon America : comic art in the Library of Congress / [edited by] Harry Katz || SI SIL library record: Pro and Conrad / Paul Conrad",
   "url": "https://api.dp.la/v2/items",
   "access_notes": null
  },
  {
   "source_id": "dpla",
   "name": "Digital Public Library of America (API)",
   "repository": null,
   "classification": "PUBLIC_API",
   "status": "worked",
   "rows": 4,
   "item": 4,
   "folder": 0,
   "box_range": 0,
   "public_image": 4,
   "archive": 0,
   "pages": null,
   "errors": null,
   "notes": "kept 9 Conrad-cartoon records; providers={'History Colorado': 3, 'National Portrait Gallery': 6}",
   "url": "https://dp.la/",
   "access_notes": null
  },
  {
   "source_id": "empire_adc",
   "name": "Empire Archival Discovery Cooperative",
   "repository": null,
   "classification": "REQUIRES_PERMISSION",
   "status": "blocked",
   "rows": 0,
   "item": 0,
   "folder": 0,
   "box_range": 0,
   "public_image": 0,
   "archive": 0,
   "pages": null,
   "errors": null,
   "notes": "AWS WAF JS challenge; probe: robots.txt unreadable (HTTP 401/403 or WAF challenge) \u2014 treated as disallowed: https://empireadc.org/search/catalog/nsyu_2642890",
   "url": "https://empireadc.org/search/catalog/nsyu_2642890",
   "access_notes": null
  },
  {
   "source_id": "google_news_archive",
   "name": "Google News Archive (news.google.com/newspapers)",
   "repository": null,
   "classification": "REQUIRES_PERMISSION",
   "status": "blocked",
   "rows": 0,
   "item": 0,
   "folder": 0,
   "box_range": 0,
   "public_image": 0,
   "archive": 0,
   "pages": null,
   "errors": null,
   "notes": "robots.txt disallows /newspapers for generic agents (robots.txt disallows https://news.google.com/newspapers?nid=conrad)",
   "url": "https://news.google.com/newspapers?nid=conrad",
   "access_notes": null
  },
  {
   "source_id": "hathitrust",
   "name": "HathiTrust catalog",
   "repository": null,
   "classification": "REQUIRES_PERMISSION",
   "status": "blocked",
   "rows": 0,
   "item": 0,
   "folder": 0,
   "box_range": 0,
   "public_image": 0,
   "archive": 0,
   "pages": null,
   "errors": null,
   "notes": "robots.txt unreadable (403); treated as disallowed; probe: robots.txt disallows https://catalog.hathitrust.org/Search/Home?lookfor=%22Conrad%2C+Paul%2C+1924-2010%22",
   "url": "https://catalog.hathitrust.org/Search/Home?lookfor=%22Conrad%2C+Paul%2C+1924-2010%22",
   "access_notes": null
  },
  {
   "source_id": "huntington",
   "name": "Huntington Library \u2014 Paul Conrad Papers (EAD finding aid)",
   "repository": "Huntington Library",
   "classification": "PHYSICAL_ARCHIVE",
   "status": "worked",
   "rows": 8628,
   "item": 0,
   "folder": 0,
   "box_range": 8628,
   "public_image": 0,
   "archive": 8628,
   "pages": 1,
   "errors": 2,
   "notes": "EAD: 2844 components, 288 boxes, 206 original-drawing boxes; typo repairs: ['box 111: 4890-49152 -> 4890-4912', 'box 137: 5791-5834 -> 5791-5833']; https://catalog.huntington.org/record=b1768021: robots.txt disallows https://catalog.huntington.org/record=b1768021; https://www.huntington.org/verso/volunteering-decipher-paul-conrad: HTTP 429 at https://www.huntington.org/verso/volunteering-decipher-paul-conrad",
   "url": "https://cinco-prd.s3.amazonaws.com/media/ead/conrad.xml",
   "access_notes": "Originals viewable in the Huntington reading room (reader credentials required). Public EAD lists box-level CON ranges only; the Huntington's internal item database is not public."
  },
  {
   "source_id": "huntington_exhibits",
   "name": "The Huntington \u2014 exhibition / collection web pages",
   "repository": null,
   "classification": "PUBLIC_HTML",
   "status": "blocked",
   "rows": 0,
   "item": 0,
   "folder": 0,
   "box_range": 0,
   "public_image": 0,
   "archive": 0,
   "pages": null,
   "errors": null,
   "notes": "probe: HTTP 429 at https://www.huntington.org/collections/lib-msscon-1-12360",
   "url": "https://www.huntington.org/collections/lib-msscon-1-12360",
   "access_notes": null
  },
  {
   "source_id": "ia_fulltext",
   "name": "Internet Archive full-text search \u2014 printed Conrad cartoon appearances (newspapers, anthologies)",
   "repository": "Internet Archive",
   "classification": "PUBLIC_API",
   "status": null,
   "rows": 0,
   "item": 0,
   "folder": 0,
   "box_range": 0,
   "public_image": 0,
   "archive": 0,
   "pages": 0,
   "errors": 0,
   "notes": null,
   "url": "https://archive.org/search?query=%22Paul+Conrad%22&sin=TXT",
   "access_notes": "OCR full-text search (page-level). Records = pages carrying a Conrad credit line. Page images are hotlinked from iiif.archive.org only for openly served items; lending-library books: no image."
  },
  {
   "source_id": "internet_archive",
   "name": "Internet Archive (books metadata)",
   "repository": "Internet Archive",
   "classification": "PUBLIC_API",
   "status": "worked",
   "rows": 0,
   "item": 0,
   "folder": 0,
   "box_range": 0,
   "public_image": 0,
   "archive": 0,
   "pages": 11,
   "errors": 0,
   "notes": "excluded name-authority conflations: ['11301329bsb (Neue Kinderklapper; Funke, Conrad Paul)', 'gottistmeinheil0000conr (Gott ist mein Heil!; Conrad, Paul, 1865-1927)', 'larryboyfibfrom00poth (Larryboy and the Fib from outer space; Poth, Karen Conrad, Paul, 1924-2010)', 'slavebug0000conr (The slave bug; Conrad, Paul)', 'thiswaytothrivin0000conr (This way to a thriving church; Conrad, Paul, H)']",
   "url": "https://archive.org/details/paulconraddrawin0000conr",
   "access_notes": "Book scans are lending-library (CDL) items; metadata only, not borrowed."
  },
  {
   "source_id": "invaluable",
   "name": "Invaluable \u2014 auction results for Paul Conrad originals",
   "repository": null,
   "classification": "PUBLIC_HTML",
   "status": "worked",
   "rows": 9,
   "item": 9,
   "folder": 0,
   "box_range": 0,
   "public_image": 9,
   "archive": 0,
   "pages": null,
   "errors": null,
   "notes": "records=9; image URLs recorded=9",
   "url": "https://www.invaluable.com/artist/paul-conrad-saveb5g89x/sold-at-auction-prices/",
   "access_notes": null
  },
  {
   "source_id": "latimes",
   "name": "Los Angeles Times \u2014 free latimes.com galleries/articles (historical archive paywalled)",
   "repository": "Los Angeles Times",
   "classification": "PUBLIC_HTML",
   "status": "partial",
   "rows": 27,
   "item": 27,
   "folder": 0,
   "box_range": 0,
   "public_image": 26,
   "archive": 0,
   "pages": 503,
   "errors": 0,
   "notes": "sitemaps scanned=501 (1985-2026); pages with a 'paul-conrad' slug=17; gallery slides saved=26 (from 1 gallery page(s)); quote-verified article citations=1; historical archive paywalled \u2014 not crawled; 345 item records overall are attributed to the LA Times; pre-2000 la-xpm slugs are opaque, so older articles about single cartoons are undiscoverable without the robots-disallowed /search",
   "url": "https://www.latimes.com/",
   "access_notes": "Historical page archive (ProQuest / latimes.newspapers.com) is paywalled and NOT crawled. Free, robots-permitted latimes.com pages found via the site's own sitemaps are parsed; images are recorded as URLs only. Robots re-audit 2026-09-25: the photogallery Disallow applies only to Googlebot-News, not to '*' (our UA) \u2014 gallery permitted."
  },
  {
   "source_id": "lbj_artifacts",
   "name": "LBJ Library eMuseum (lbj.artifacts.archives.gov) \u2014 ~11 Conrad originals 1964-68",
   "repository": null,
   "classification": "REQUIRES_PERMISSION",
   "status": "blocked",
   "rows": 0,
   "item": 0,
   "folder": 0,
   "box_range": 0,
   "public_image": 0,
   "archive": 0,
   "pages": null,
   "errors": null,
   "notes": "robots.txt allows /people/ and /objects/ (Crawl-delay 30, Disallow /assets/) but the site answers HTTP 403 to this crawler's descriptive UA; a browser UA is NOT substituted (that would be a bypass) (HTTP 403 (access denied) at https://lbj.artifacts.archives.gov/people/14908/paul-conrad/objects)",
   "url": "https://lbj.artifacts.archives.gov/people/14908/paul-conrad/objects",
   "access_notes": null
  },
  {
   "source_id": "lbj_library",
   "name": "LBJ Presidential Library",
   "repository": null,
   "classification": "PHYSICAL_ARCHIVE",
   "status": "not_attempted",
   "rows": 0,
   "item": 0,
   "folder": 0,
   "box_range": 0,
   "public_image": 0,
   "archive": 0,
   "pages": null,
   "errors": null,
   "notes": "UNVERIFIED lead.",
   "url": "https://www.lbjlibrary.org/",
   "access_notes": null
  },
  {
   "source_id": "loc",
   "name": "Library of Congress \u2014 Prints & Photographs (JSON API)",
   "repository": "Library of Congress",
   "classification": "PUBLIC_API",
   "status": "worked",
   "rows": 65,
   "item": 61,
   "folder": 4,
   "box_range": 0,
   "public_image": 17,
   "archive": 0,
   "pages": 75,
   "errors": 0,
   "notes": "robots.txt: /photos/=allow, /manuscripts/=allow, /books/=allow, /maps/=allow, /collections/cartoon-drawings/=allow, /item/1/=allow, /pictures/item/1/=allow, /search/=DISALLOW, /pictures/search/=DISALLOW, /pictures/related/=DISALLOW; format endpoints (Conrad hits): /photos/ {'fa': 'contributor:conrad, paul'}=17; /photos/ {'q': 'paul conrad editorial cartoon'}=16; /photos/ {'q': 'conrad, paul, 1924-2010'}=17; /photos/ {'q': 'conrad, paul'}=17; /manuscripts/ {'fa': 'contributor:conrad, paul'}=0; /manuscripts/ {'q': 'paul conrad cartoons'}=0; /books/ {'fa': 'contributor:conrad, paul'}=0; /maps/ {'fa': 'contributor:conrad, paul'}=0; /collections/cartoon-drawings/ {'fa': 'contributor:conrad, paul'}=10; /collections/cartoon-drawings/ {'q': 'conrad'}=10; neighbour-LCCN probing (+/-5, cap 300): {'requests': 0, 'conrad': 0, 'other': 0, 'missing': 0, 'error': 0, 'cached_skip': 158, 'cumulative_probed_ids': {'other': 126, 'missing': 4, 'total': 130}}; new Conrad ids from probing: none; group 2010632868: {'call_number': 'Unprocessed in PR 13 CN 1983:004 [P&P]', 'digitized_resources': 0, 'resource_files': 0, 'declared_components': '83 prints', 'child_item_links': [], 'neighbors_link_disallowed': True, 'components_addressable': False, 'why': \"no child item records, no digitized component files; the only component path is the 'neighbors' link under /pictures/related/, which robots.txt disallows\"}; group 2010634752: {'call_number': 'Unprocessed in PR 13 CN 1999:086 [P&P]', 'digitized_resources': 0, 'resource_files': 0, 'declared_components': '21 drawings', 'child_item_links': [], 'neighbors_link_disallowed': True, 'components_addressable': False, 'why': \"no child item records, no digitized component files; the only component path is the 'neighbors' link under /pictures/related/, which robots.txt disallows\"}; group 2010634813: {'call_number': 'Unprocessed in PR 13 CN 2000:046 [P&P]', 'digitized_resources': 0, 'resource_files': 0, 'declared_components': '7 drawings', 'child_item_links': [], 'neighbors_link_disallowed': True, 'components_addressable': False, 'why': \"no child item records, no digitized component files; the only component path is the 'neighbors' link under /pictures/related/, which robots.txt disallows\"}; group 2010635027: {'call_number': 'Unprocessed in PR 13 CN 2003:069 [P&P]', 'digitized_resources': 0, 'resource_files': 0, 'declared_components': '24 drawings', 'child_item_links': [], 'neighbors_link_disallowed': True, 'components_addressable': False, 'why': \"no child item records, no digitized component files; the only component path is the 'neighbors' link under /pictures/related/, which robots.txt disallows\"}; LOC book records by Conrad: 1; format endpoints found 17 Conrad ids; verified 65 Conrad item JSON records; /search, /pictures/search, /pictures/related are robots-disallowed (not paged)",
   "url": "https://www.loc.gov/photos/?fa=contributor:conrad,%20paul&fo=json",
   "access_notes": "Item records online; many Conrad drawings are digitized but flagged 'May be restricted: Copyright ... Los Angeles Times' \u2014 view at loc.gov (link-out), reproduction needs permission."
  },
  {
   "source_id": "loc_lcib",
   "name": "LOC Information Bulletin (Oct 1999) \u2014 Conrad gift article",
   "repository": null,
   "classification": "PUBLIC_HTML",
   "status": "worked",
   "rows": 0,
   "item": 0,
   "folder": 0,
   "box_range": 0,
   "public_image": 0,
   "archive": 0,
   "pages": null,
   "errors": null,
   "notes": "context article about Conrad's gift of drawings to LOC; probe: HTTP 200",
   "url": "https://www.loc.gov/loc/lcib/9910/conrad.html",
   "access_notes": null
  },
  {
   "source_id": "nara_artifacts",
   "name": "JFK Library eMuseum (jfk.artifacts.archives.gov) \u2014 2 Denver Post originals 1961-63",
   "repository": null,
   "classification": "REQUIRES_PERMISSION",
   "status": "blocked",
   "rows": 0,
   "item": 0,
   "folder": 0,
   "box_range": 0,
   "public_image": 0,
   "archive": 0,
   "pages": null,
   "errors": null,
   "notes": "robots.txt allows /people/ and /objects/ (Crawl-delay 30, Disallow /assets/) but the site answers HTTP 403 to this crawler's descriptive UA; a browser UA is NOT substituted (that would be a bypass) (HTTP 403 (access denied) at https://jfk.artifacts.archives.gov/people/6554/paul-conrad-denver-post/objects)",
   "url": "https://jfk.artifacts.archives.gov/people/6554/paul-conrad-denver-post/objects",
   "access_notes": null
  },
  {
   "source_id": "newspaper_probes",
   "name": "Digitized-newspaper / museum archive probes",
   "repository": null,
   "classification": "PUBLIC_HTML",
   "status": "worked",
   "rows": 0,
   "item": 0,
   "folder": 0,
   "box_range": 0,
   "public_image": 0,
   "archive": 0,
   "pages": 1,
   "errors": 0,
   "notes": "probes: cdnc=blocked, colorado_newspapers=blocked, chronicling_america=worked, nara_artifacts=blocked, lbj_artifacts=blocked, billy_ireland_dc=failed, stanford_daily=blocked, truthdig_api=blocked, google_news_archive=blocked",
   "url": "https://www.loc.gov/collections/chronicling-america/",
   "access_notes": "Reachability probes only; each probed archive is registered as its own source."
  },
  {
   "source_id": "nixon_foundation",
   "name": "Richard Nixon Foundation (site search 'conrad')",
   "repository": null,
   "classification": "PUBLIC_HTML",
   "status": "worked",
   "rows": 0,
   "item": 0,
   "folder": 0,
   "box_range": 0,
   "public_image": 0,
   "archive": 0,
   "pages": null,
   "errors": null,
   "notes": "HTTP 200; 'conrad' mentions=2; no page naming a specific dated Conrad cartoon found -> 0 item records",
   "url": "https://www.nixonfoundation.org/?s=conrad",
   "access_notes": null
  },
  {
   "source_id": "nixon_library",
   "name": "Richard Nixon Presidential Library (site search 'conrad')",
   "repository": null,
   "classification": "PUBLIC_HTML",
   "status": "worked",
   "rows": 0,
   "item": 0,
   "folder": 0,
   "box_range": 0,
   "public_image": 0,
   "archive": 0,
   "pages": null,
   "errors": null,
   "notes": "HTTP 200; 'conrad' mentions=0; no page naming a specific dated Conrad cartoon found -> 0 item records",
   "url": "https://www.nixonlibrary.gov/search?keys=conrad",
   "access_notes": null
  },
  {
   "source_id": "nytimes_obit",
   "name": "New York Times obituary, 5 Sep 2010",
   "repository": null,
   "classification": "REQUIRES_PERMISSION",
   "status": "blocked",
   "rows": 0,
   "item": 0,
   "folder": 0,
   "box_range": 0,
   "public_image": 0,
   "archive": 0,
   "pages": null,
   "errors": null,
   "notes": "live page WAF-blocked; its Wayback copy is deliberately NOT used (would bypass the block) (WAF/JS challenge (HTTP 403) at https://www.nytimes.com/2010/09/05/us/politics/05conrad.html)",
   "url": "https://www.nytimes.com/2010/09/05/us/politics/05conrad.html",
   "access_notes": null
  },
  {
   "source_id": "oac",
   "name": "Online Archive of California (Huntington finding aid host)",
   "repository": "Huntington Library",
   "classification": "PUBLIC_HTML",
   "status": "worked",
   "rows": 0,
   "item": 0,
   "folder": 0,
   "box_range": 0,
   "public_image": 0,
   "archive": 0,
   "pages": 1,
   "errors": 0,
   "notes": "OAC collection page parsed: 272.41 Linear Feet (285 boxes, 1 folder)",
   "url": "https://oac.cdlib.org/findaid/ark:/13030/c8z03dxd/",
   "access_notes": "Finding aid only; no digitized Conrad items. Crawl-delay 5 honoured."
  },
  {
   "source_id": "ohio_state",
   "name": "Ohio State University \u2014 Billy Ireland Cartoon Library & Museum",
   "repository": "Ohio State University",
   "classification": "REQUIRES_PERMISSION",
   "status": "blocked",
   "rows": 0,
   "item": 0,
   "folder": 0,
   "box_range": 0,
   "public_image": 0,
   "archive": 0,
   "pages": 0,
   "errors": 1,
   "notes": "blocked: robots.txt unreadable (HTTP 401/403 or WAF challenge) \u2014 treated as disallowed: https://osucartoons.pastperfectonline.com/",
   "url": "https://osucartoons.pastperfectonline.com/",
   "access_notes": "Holds Conrad material (per OSU catalog references) but the online collections database refuses automated access (HTTP 403). Request a metadata export from the Billy Ireland reference desk."
  },
  {
   "source_id": "pc_gallery",
   "name": "Political Cartoon Gallery (dealer, London) \u2014 Conrad originals for sale",
   "repository": null,
   "classification": "PUBLIC_HTML",
   "status": "worked",
   "rows": 8,
   "item": 8,
   "folder": 0,
   "box_range": 0,
   "public_image": 8,
   "archive": 0,
   "pages": null,
   "errors": null,
   "notes": "records=8; image URLs recorded=8",
   "url": "https://www.original-political-cartoon.com/cartoon-gallery/artists/conrad-paul-1924-2010/",
   "access_notes": null
  },
  {
   "source_id": "pophistorydig",
   "name": "The Pop History Dig \u2014 'Paul Conrad, cartoonist' article (blog reprints)",
   "repository": null,
   "classification": "PUBLIC_HTML",
   "status": "worked",
   "rows": 8,
   "item": 8,
   "folder": 0,
   "box_range": 0,
   "public_image": 8,
   "archive": 0,
   "pages": null,
   "errors": null,
   "notes": "records=8; image URLs recorded=8",
   "url": "https://pophistorydig.com/topics/paul-conrad-cartoonist/",
   "access_notes": null
  },
  {
   "source_id": "pulitzer",
   "name": "Pulitzer Prizes (1964, 1971, 1984)",
   "repository": null,
   "classification": "PUBLIC_HTML",
   "status": "worked",
   "rows": 0,
   "item": 0,
   "folder": 0,
   "box_range": 0,
   "public_image": 0,
   "archive": 0,
   "pages": null,
   "errors": null,
   "notes": "prize citations name no single cartoon (year-of-work awards) -> 0 item records; 1964: Paul Conrad of The Denver Post For his editorial cartooning during the past year | 1971: Paul Conrad of Los Angeles Times For his editorial cartooning during 1970. | 1984: Paul Conrad of Los Angeles Times",
   "url": "https://www.pulitzer.org/winners/paul-conrad",
   "access_notes": null
  },
  {
   "source_id": "reagan_library",
   "name": "Ronald Reagan Presidential Library",
   "repository": null,
   "classification": "PHYSICAL_ARCHIVE",
   "status": "not_attempted",
   "rows": 0,
   "item": 0,
   "folder": 0,
   "box_range": 0,
   "public_image": 0,
   "archive": 0,
   "pages": null,
   "errors": null,
   "notes": "UNVERIFIED lead.",
   "url": "https://www.reaganlibrary.gov/",
   "access_notes": null
  },
  {
   "source_id": "secondary_web",
   "name": "Secondary citations \u2014 verified quotes (Wikipedia, LA Times obit, LOC bulletin, PBS gallery, NCR)",
   "repository": "Secondary citation",
   "classification": "PUBLIC_HTML",
   "status": "worked",
   "rows": 43,
   "item": 43,
   "folder": 0,
   "box_range": 0,
   "public_image": 0,
   "archive": 0,
   "pages": 43,
   "errors": 0,
   "notes": "verified citations saved per site: PBS Independent Lens (Wayback)=29, Los Angeles Times obituary=6, Wikipedia=2, Library of Congress Information Bulletin=2, Canyon News=1, Washington Report on Middle East Affairs=1, Associated Press obituary=1, National Catholic Reporter=1",
   "url": "https://en.wikipedia.org/wiki/Paul_Conrad",
   "access_notes": "Each record cites a fetched page and carries a verbatim <=200-char quote; saved only if the quote is on the page. Wayback used only for retired pages whose origin robots.txt allows the path."
  },
  {
   "source_id": "seed",
   "name": "Seed corpus (TK-12179, read-only)",
   "repository": "multiple",
   "classification": "METADATA_ONLY",
   "status": "worked",
   "rows": 0,
   "item": 0,
   "folder": 0,
   "box_range": 0,
   "public_image": 0,
   "archive": 0,
   "pages": 142,
   "errors": 0,
   "notes": "huntington_repairs=[{'box': '111', 'was': '4890-49152', 'now': '4890-4912'}, {'box': '137', 'was': '5791-5834', 'now': '5791-5833'}]",
   "url": "/Users/macstudio3/Projects/paul-conrad-cartoons/research",
   "access_notes": "Local cached metadata built by paul-conrad-cartoons/scripts/build-corpus.mjs; read-only."
  },
  {
   "source_id": "seed_catalog",
   "name": "Seed: hand-built secondary-source catalog (data/cartoons.json)",
   "repository": "Secondary citation",
   "classification": "METADATA_ONLY",
   "status": "seed_only",
   "rows": 32,
   "item": 32,
   "folder": 0,
   "box_range": 0,
   "public_image": 0,
   "archive": 0,
   "pages": null,
   "errors": null,
   "notes": null,
   "url": "/Users/macstudio3/Projects/paul-conrad-cartoons/data/cartoons.json",
   "access_notes": "seed cache; provenance recorded per row"
  },
  {
   "source_id": "seed_huntington",
   "name": "Seed: Huntington EAD slots (corpus.json)",
   "repository": "Huntington Library",
   "classification": "PHYSICAL_ARCHIVE",
   "status": "seed_only",
   "rows": 8628,
   "item": 0,
   "folder": 0,
   "box_range": 8628,
   "public_image": 0,
   "archive": 8628,
   "pages": null,
   "errors": null,
   "notes": null,
   "url": "https://oac.cdlib.org/findaid/ark:/13030/c8z03dxd/",
   "access_notes": "seed cache; provenance recorded per row"
  },
  {
   "source_id": "seed_loc",
   "name": "Seed: LOC P&P search cache (raw/loc-page-1.json)",
   "repository": "Library of Congress",
   "classification": "PUBLIC_API",
   "status": "seed_only",
   "rows": 64,
   "item": 61,
   "folder": 3,
   "box_range": 0,
   "public_image": 17,
   "archive": 0,
   "pages": null,
   "errors": null,
   "notes": null,
   "url": "https://www.loc.gov/pictures/search/?q=Conrad%2C%20Paul",
   "access_notes": "seed cache; provenance recorded per row"
  },
  {
   "source_id": "seed_syracuse",
   "name": "Seed: Syracuse finding-aid cache (raw/syr.html, syr.md)",
   "repository": "Syracuse University",
   "classification": "PHYSICAL_ARCHIVE",
   "status": "seed_only",
   "rows": 65,
   "item": 0,
   "folder": 65,
   "box_range": 0,
   "public_image": 0,
   "archive": 65,
   "pages": null,
   "errors": null,
   "notes": null,
   "url": "https://library.syracuse.edu/digital/guides/c/conrad_p.htm",
   "access_notes": "seed cache; provenance recorded per row"
  },
  {
   "source_id": "seed_wichita",
   "name": "Seed: Wichita State ArchivesSpace cache (raw/wsu/*.md via r.jina.ai)",
   "repository": "Wichita State University",
   "classification": "PHYSICAL_ARCHIVE",
   "status": "seed_only",
   "rows": 207,
   "item": 207,
   "folder": 0,
   "box_range": 0,
   "public_image": 0,
   "archive": 207,
   "pages": null,
   "errors": null,
   "notes": null,
   "url": "https://archivesspace.wichita.edu/repositories/3/resources/166",
   "access_notes": "seed cache; provenance recorded per row"
  },
  {
   "source_id": "smithsonian",
   "name": "Smithsonian Open Access API",
   "repository": null,
   "classification": "PUBLIC_API",
   "status": "worked",
   "rows": 0,
   "item": 0,
   "folder": 0,
   "box_range": 0,
   "public_image": 0,
   "archive": 0,
   "pages": null,
   "errors": null,
   "notes": "kept 0 records; units={'SIL': 4}",
   "url": "https://api.si.edu/openaccess/",
   "access_notes": null
  },
  {
   "source_id": "stanford_daily",
   "name": "Stanford Daily archive search API (ran Conrad from 1964-09-28 / 1976-11-15)",
   "repository": null,
   "classification": "REQUIRES_PERMISSION",
   "status": "blocked",
   "rows": 0,
   "item": 0,
   "folder": 0,
   "box_range": 0,
   "public_image": 0,
   "archive": 0,
   "pages": null,
   "errors": null,
   "notes": "the API host's robots.txt answers 403 -> treated as disallowed (conservative rule) (robots.txt unreadable (HTTP 401/403 or WAF challenge) \u2014 treated as disallowed: https://ehabp6fuc5.execute-api.us-east-1.amazonaws.com/prod?q=%22Paul+Conrad%22&size=50)",
   "url": "https://ehabp6fuc5.execute-api.us-east-1.amazonaws.com/prod",
   "access_notes": null
  },
  {
   "source_id": "syracuse",
   "name": "Syracuse University Special Collections \u2014 Paul Conrad Cartoons",
   "repository": "Syracuse University",
   "classification": "PHYSICAL_ARCHIVE",
   "status": "blocked",
   "rows": 0,
   "item": 0,
   "folder": 0,
   "box_range": 0,
   "public_image": 0,
   "archive": 0,
   "pages": 0,
   "errors": 2,
   "notes": "blocked: https://library.syracuse.edu/digital/guides/c/conrad_p.htm (WAF/JS challenge (HTTP 202) at https://library.syracuse.edu/digital/guides/c/conrad_p.htm); blocked: https://empireadc.org/search/catalog/nsyu_2642890 (robots.txt unreadable (HTTP 401/403 or WAF challenge) \u2014 treated as disallowed: https://empireadc.org/search/catalog/nsyu_2642890); using seed cache (seed_syracuse) for the 65 folder records",
   "url": "https://library.syracuse.edu/digital/guides/c/conrad_p.htm",
   "access_notes": "Reading-room access at SCRC. Finding aid is folder-level (65 folders, 388 index headings)."
  },
  {
   "source_id": "syracuse_exhibit",
   "name": "Syracuse University Libraries \u2014 'Cartoonists' web exhibit, Paul Conrad page",
   "repository": null,
   "classification": "PUBLIC_HTML",
   "status": "worked",
   "rows": 5,
   "item": 5,
   "folder": 0,
   "box_range": 0,
   "public_image": 5,
   "archive": 0,
   "pages": null,
   "errors": null,
   "notes": "records=5; image URLs recorded=5",
   "url": "https://library.syracuse.edu/extsites/cartoonists/conrad.php",
   "access_notes": null
  },
  {
   "source_id": "truthdig",
   "name": "Truthdig \u2014 Paul Conrad cartoons (2000s syndicated)",
   "repository": null,
   "classification": "PUBLIC_HTML",
   "status": "worked",
   "rows": 2,
   "item": 2,
   "folder": 0,
   "box_range": 0,
   "public_image": 2,
   "archive": 0,
   "pages": null,
   "errors": null,
   "notes": "records=2; image URLs recorded=2",
   "url": "https://www.truthdig.com/author/paul_conrad/",
   "access_notes": null
  },
  {
   "source_id": "truthdig_api",
   "name": "Truthdig WordPress REST API (cartoons search)",
   "repository": null,
   "classification": "REQUIRES_PERMISSION",
   "status": "blocked",
   "rows": 0,
   "item": 0,
   "folder": 0,
   "box_range": 0,
   "public_image": 0,
   "archive": 0,
   "pages": null,
   "errors": null,
   "notes": "robots.txt disallows /wp-json/ (the author page /author/paul_conrad/ is used instead, see truthdig) (robots.txt disallows https://www.truthdig.com/wp-json/wp/v2/cartoons?search=conrad&per_page=100)",
   "url": "https://www.truthdig.com/wp-json/wp/v2/cartoons",
   "access_notes": null
  },
  {
   "source_id": "washpost_obit",
   "name": "Washington Post obituary, 6 Sep 2010",
   "repository": null,
   "classification": "REQUIRES_PERMISSION",
   "status": "blocked",
   "rows": 0,
   "item": 0,
   "folder": 0,
   "box_range": 0,
   "public_image": 0,
   "archive": 0,
   "pages": null,
   "errors": null,
   "notes": "robots.txt disallows; its Wayback copy is deliberately NOT used (would bypass robots) (robots.txt disallows http://www.washingtonpost.com/wp-dyn/content/article/2010/09/05/AR2010090503410_pf.html)",
   "url": "http://www.washingtonpost.com/wp-dyn/content/article/2010/09/05/AR2010090503410_pf.html",
   "access_notes": null
  },
  {
   "source_id": "web_images",
   "name": "Public web pages showing Conrad cartoons (exhibit, dealer, auction, blog, magazine)",
   "repository": null,
   "classification": "PUBLIC_HTML",
   "status": "worked",
   "rows": 0,
   "item": 0,
   "folder": 0,
   "box_range": 0,
   "public_image": 0,
   "archive": 0,
   "pages": 16,
   "errors": 0,
   "notes": "syracuse_exhibit: 5 rec / 5 img (worked); pc_gallery: 8 rec / 8 img (worked); invaluable: 9 rec / 9 img (worked); pophistorydig: 8 rec / 8 img (worked); truthdig: 2 rec / 2 img (worked)",
   "url": "https://library.syracuse.edu/extsites/cartoonists/conrad.php",
   "access_notes": "Each sub-source is registered separately; images are URL metadata only; copies flagged as reprints."
  },
  {
   "source_id": "wichita",
   "name": "Wichita State University Special Collections \u2014 MS 90-18",
   "repository": "Wichita State University",
   "classification": "PHYSICAL_ARCHIVE",
   "status": "blocked",
   "rows": 0,
   "item": 0,
   "folder": 0,
   "box_range": 0,
   "public_image": 0,
   "archive": 0,
   "pages": 1,
   "errors": 3,
   "notes": "https://specialcollections.wichita.edu/collections/ms/90-18/90-18-a.html: retired/redirected; blocked: https://archivesspace.wichita.edu/repositories/3/resources/166; blocked: https://archivesspace.wichita.edu/repositories/3/archival_objects/111935; REQUIRES_PERMISSION for automated access; relying on seed_wichita cache (r.jina.ai provenance)",
   "url": "https://archivesspace.wichita.edu/repositories/3/resources/166",
   "access_notes": "Item-level ArchivesSpace records (Series 2, 1968-1971); originals viewable in Special Collections."
  },
  {
   "source_id": "wikidata",
   "name": "Wikidata (Paul Conrad, Q2059192)",
   "repository": null,
   "classification": "PUBLIC_API",
   "status": "worked",
   "rows": 0,
   "item": 0,
   "folder": 0,
   "box_range": 0,
   "public_image": 0,
   "archive": 0,
   "pages": null,
   "errors": null,
   "notes": "entity read; notable-work (P800) claims=0; reverse 'creator = Q2059192' needs SPARQL or Special:WhatLinksHere, both robots-disallowed -> not queried; 0 item records. MediaWiki API (/w/api.php), Wikidata API and query.wikidata.org SPARQL are robots.txt-disallowed for generic agents -> not queried; only robots-permitted /wiki/ pages and Special:EntityData were read",
   "url": "https://www.wikidata.org/wiki/Special:EntityData/Q2059192.json",
   "access_notes": null
  },
  {
   "source_id": "wikimedia_commons",
   "name": "Wikimedia Commons (Category:Paul Conrad)",
   "repository": null,
   "classification": "PUBLIC_HTML",
   "status": "worked",
   "rows": 0,
   "item": 0,
   "folder": 0,
   "box_range": 0,
   "public_image": 0,
   "archive": 0,
   "pages": null,
   "errors": null,
   "notes": "category lists 1 file(s): Otis Chandler (Los Angeles Times) [file] \u2014 none is a Conrad cartoon; 0 item records. MediaWiki API (/w/api.php), Wikidata API and query.wikidata.org SPARQL are robots.txt-disallowed for generic agents -> not queried; only robots-permitted /wiki/ pages and Special:EntityData were read",
   "url": "https://commons.wikimedia.org/wiki/Category:Paul_Conrad",
   "access_notes": null
  },
  {
   "source_id": "worldcat",
   "name": "WorldCat",
   "repository": null,
   "classification": "METADATA_ONLY",
   "status": "not_attempted",
   "rows": 0,
   "item": 0,
   "folder": 0,
   "box_range": 0,
   "public_image": 0,
   "archive": 0,
   "pages": null,
   "errors": null,
   "notes": "No keyless API; bibliographic lead only (not crawled).",
   "url": "https://search.worldcat.org/search?q=au%3AConrad%2C+Paul%2C+1924-2010",
   "access_notes": null
  }
 ]
}