{
"_id": "6a10553cacfb0bcc41ca2476",
"Package": "ORscraper",
"Type": "Package",
"Title": "Extract Information from Clinical Reports from 'Oncomine\nReporter' and NCBI 'ClinVar'",
"Version": "0.1.1",
"Authors@R": "c(\nperson(\"Samuel\", \"González\", email = \"samugonz0204@gmail.com\", role = c(\"aut\", \"cre\"), comment = c(ORCID = \"0009-0007-9531-9821\")),\nperson(\"Antonio Jesus\", \"Canepa\", role = \"ctb\", comment = c(ORCID = \"0000-0002-0608-2743\")),\nperson(\"Patricia\", \"Saiz\", role = \"ctb\", comment = c(ORCID = \"0000-0001-7106-5192\")),\nperson(\"María\", \"González\", role = \"ctb\", comment = c(ORCID = \"0009-0000-1887-4644\"))\n)",
"Description": "Clinical reports generated by 'Oncomine Reporter' software\ncontain critical data in unstructured PDF format, making manual\nextraction time-consuming and error-prone. 'ORscraper' provides\na coherent suite of functions to automate this process,\nallowing researchers to parse reports, identify key biomarkers,\nextract genetic variant tables, and filter results. It also\nintegrates with the NCBI 'ClinVar' API\n to enrich extracted\ndata.",
"License": "MIT + file LICENSE",
"Encoding": "UTF-8",
"RoxygenNote": "7.3.3",
"SystemRequirements": "poppler-cpp (>= 0.73)",
"Config/testthat/edition": "3",
"VignetteBuilder": "knitr",
"URL": "https://github.com/SamuelGonzalez0204/ORscraper",
"BugReports": "https://github.com/SamuelGonzalez0204/ORscraper/issues",
"Language": "en-US",
"Config/pak/sysreqs": "libicu-dev libjpeg-dev libxml2-dev libssl-dev\nlibpoppler-cpp-dev poppler-data",
"Repository": "https://samuelgonzalez0204.r-universe.dev",
"Date/Publication": "2026-03-10 20:37:03 UTC",
"RemoteUrl": "https://github.com/samuelgonzalez0204/orscraper",
"RemoteRef": "HEAD",
"RemoteSha": "30ef489dbaa16a2884dd1231c8a43beb41bb8595",
"NeedsCompilation": "no",
"Packaged": {
"Date": "2026-05-09 08:14:49 UTC",
"User": "root"
},
"Author": "Samuel González [aut, cre] (ORCID:\n),\nAntonio Jesus Canepa [ctb] (ORCID:\n),\nPatricia Saiz [ctb] (ORCID: ),\nMaría González [ctb] (ORCID: )",
"Maintainer": "Samuel González ",
"MD5sum": "75b8fe4db01be4c823b2a6f8ef0dbfd6",
"_user": "samuelgonzalez0204",
"_type": "src",
"_file": "ORscraper_0.1.1.tar.gz",
"_fileid": "0fae88e3bb00c492074e0644b136fbda478d943fdb7770ffe76e1b6c3ccf8b56",
"_filesize": 618136,
"_sha256": "0fae88e3bb00c492074e0644b136fbda478d943fdb7770ffe76e1b6c3ccf8b56",
"_created": "2026-05-09T08:14:49.000Z",
"_published": "2026-05-22T13:08:12.063Z",
"_distro": "noble",
"_jobs": [
{
"job": 77385691491,
"time": 137,
"config": "linux-devel-x86_64",
"r": "4.7.0",
"check": "NOTE",
"artifact": "6894253536"
},
{
"job": 77385691696,
"time": 128,
"config": "linux-release-x86_64",
"r": "4.6.0",
"check": "NOTE",
"artifact": "6894253225"
},
{
"job": 77385691736,
"time": 144,
"config": "macos-oldrel-arm64",
"r": "4.5.3",
"check": "NOTE",
"artifact": "6894251749"
},
{
"job": 77385691063,
"time": 121,
"config": "macos-release-arm64",
"r": "4.6.0",
"check": "NOTE",
"artifact": "6894250301"
},
{
"job": 77385690577,
"time": 220,
"config": "source",
"r": "4.6.0",
"check": "OK",
"artifact": "6894241010"
},
{
"job": 77385690757,
"time": 120,
"config": "wasm-release",
"r": "4.6.0",
"check": "OK",
"artifact": "7161243370"
},
{
"job": 77385691730,
"time": 89,
"config": "windows-devel",
"r": "4.7.0",
"check": "NOTE",
"artifact": "6894249371"
},
{
"job": 77385691763,
"time": 82,
"config": "windows-oldrel",
"r": "4.5.3",
"check": "NOTE",
"artifact": "6894248661"
},
{
"job": 77385691459,
"time": 86,
"config": "windows-release",
"r": "4.6.0",
"check": "NOTE",
"artifact": "6894248931"
}
],
"_buildurl": "https://github.com/r-universe/samuelgonzalez0204/actions/runs/25596191019",
"_status": "success",
"_host": "GitHub-Actions",
"_upstream": "https://github.com/samuelgonzalez0204/orscraper",
"_commit": {
"id": "30ef489dbaa16a2884dd1231c8a43beb41bb8595",
"author": "SamuelGonzalez0204 ",
"committer": "SamuelGonzalez0204 ",
"message": "cran-comments\n",
"time": 1773175023
},
"_maintainer": {
"name": "Samuel González",
"email": "samugonz0204@gmail.com",
"login": "samuelgonzalez0204",
"uuid": 154916568
},
"_registered": true,
"_dependencies": [
{
"package": "R",
"version": ">= 4.0.0",
"role": "Depends"
},
{
"package": "pdftools",
"role": "Imports"
},
{
"package": "stringr",
"role": "Imports"
},
{
"package": "readxl",
"role": "Imports"
},
{
"package": "rentrez",
"role": "Imports"
},
{
"package": "testthat",
"version": ">= 3.0.0",
"role": "Suggests"
},
{
"package": "rmarkdown",
"role": "Suggests"
},
{
"package": "knitr",
"role": "Suggests"
},
{
"package": "mockery",
"role": "Suggests"
},
{
"package": "spelling",
"role": "Suggests"
}
],
"_owner": "samuelgonzalez0204",
"_selfowned": true,
"_usedby": 0,
"_updates": [
{
"week": "2026-02",
"n": 5
},
{
"week": "2026-03",
"n": 1
},
{
"week": "2026-10",
"n": 2
},
{
"week": "2026-11",
"n": 3
}
],
"_tags": [
{
"name": "CRAN",
"date": "2026-01-17"
}
],
"_stars": 0,
"_contributors": [
{
"user": "samuelgonzalez0204",
"count": 3,
"uuid": 154916568
}
],
"_userbio": {
"uuid": 154916568,
"type": "user",
"name": "SamuelGonzalez0204"
},
"_downloads": {
"count": 474,
"source": "https://cranlogs.r-pkg.org/downloads/total/last-month/ORscraper"
},
"_devurl": "https://github.com/samuelgonzalez0204/orscraper",
"_searchresults": 0,
"_rbuild": "4.6.0",
"_assets": [
"extra/citation.cff",
"extra/citation.html",
"extra/citation.json",
"extra/citation.txt",
"extra/contents.json",
"extra/NEWS.html",
"extra/NEWS.txt",
"extra/ORscraper.html",
"extra/readme.html",
"extra/readme.md",
"manual.pdf"
],
"_homeurl": "https://github.com/samuelgonzalez0204/orscraper",
"_realowner": "samuelgonzalez0204",
"_cranurl": true,
"_releases": [
{
"version": "0.1.0",
"date": "2026-01-16"
},
{
"version": "0.1.1",
"date": "2026-03-11"
}
],
"_exports": [
"classify_biopsy",
"extract_chip_id",
"extract_fusions",
"extract_intermediate_values",
"extract_values_from_tables",
"extract_values_start_end",
"filter_pathogenic_only",
"read_pdf_content",
"read_pdf_files",
"search_ncbi_clinvar"
],
"_help": [
{
"page": "classify_biopsy",
"title": "Determine the type of biopsy from identifiers",
"topics": [
"classify_biopsy"
]
},
{
"page": "extract_chip_id",
"title": "Extract numeric identifiers from file names",
"topics": [
"extract_chip_id"
]
},
{
"page": "extract_fusions",
"title": "Extract fusion variants from text",
"topics": [
"extract_fusions"
]
},
{
"page": "extract_intermediate_values",
"title": "Extract intermediate values from text lines",
"topics": [
"extract_intermediate_values"
]
},
{
"page": "extract_values_from_tables",
"title": "Extract values from tables within text",
"topics": [
"extract_values_from_tables"
]
},
{
"page": "extract_values_start_end",
"title": "Extract values from start or end patterns",
"topics": [
"extract_values_start_end"
]
},
{
"page": "extract_variable",
"title": "Extract variable value from text lines",
"topics": [
"extract_variable"
]
},
{
"page": "filter_pathogenic_only",
"title": "Filter for pathogenic results only",
"topics": [
"filter_pathogenic_only"
]
},
{
"page": "narrow_text",
"title": "Extract a subset of text based on start and end patterns",
"topics": [
"narrow_text"
]
},
{
"page": "read_pdf_content",
"title": "Read content from a PDF file",
"topics": [
"read_pdf_content"
]
},
{
"page": "read_pdf_files",
"title": "Read all PDF files in a directory",
"topics": [
"read_pdf_files"
]
},
{
"page": "search_ncbi_clinvar",
"title": "Search for pathogenicity information in NCBI ClinVar",
"topics": [
"search_ncbi_clinvar"
]
},
{
"page": "search_value",
"title": "Search for a specific value in text lines",
"topics": [
"search_value"
]
}
],
"_readme": "https://github.com/samuelgonzalez0204/orscraper/raw/HEAD/README.md",
"_rundeps": [
"askpass",
"cellranger",
"cli",
"cpp11",
"crayon",
"curl",
"glue",
"hms",
"httr",
"jsonlite",
"lifecycle",
"magrittr",
"mime",
"openssl",
"pdftools",
"pillar",
"pkgconfig",
"prettyunits",
"progress",
"qpdf",
"R6",
"Rcpp",
"readxl",
"rematch",
"rentrez",
"rlang",
"stringi",
"stringr",
"sys",
"tibble",
"utf8",
"vctrs",
"XML"
],
"_vignettes": [
{
"source": "ORscraper.Rmd",
"filename": "ORscraper.html",
"title": "ORscraper",
"author": "Samuel González",
"engine": "knitr::rmarkdown",
"headings": [
"Introduction",
"Installation",
"Data Structure and Input Format",
"Input File Format",
"Processing Multiple Files",
"Recommended File Path Structure",
"Recommended Naming Convention",
"Language Compatibility",
"Example Input File",
"Core functions",
"Example Workflow",
"Step 1: Load and Process PDF Files",
"Step 2: Extract Text from PDFs",
"Step 3: Extract Key Information from Text",
"Step 4: Extract Additional Information",
"Step 5: Extract Genetic Mutation Data",
"Step 6: Identify Gene Fusions",
"Step 7: Search for Pathogenicity Information",
"Step 8: Filter Pathogenic Mutations",
"Step 9: Classify Biopsies",
"Step 10: Extract Chip Identifier",
"Additional Features",
"Shiny App",
"Conclusion"
],
"created": "2026-01-11 20:27:06",
"modified": "2026-01-11 20:27:06",
"commits": 1
}
],
"_score": 4.301029995663981,
"_indexed": true,
"_nocasepkg": "orscraper",
"_universes": [
"samuelgonzalez0204"
],
"_binaries": [
{
"r": "4.7.0",
"os": "linux",
"version": "0.1.1",
"date": "2026-05-09T08:17:06.000Z",
"distro": "noble",
"commit": "30ef489dbaa16a2884dd1231c8a43beb41bb8595",
"fileid": "04dbdad5f73cb8adc9bae4888a25f79d659c743cc5175a3ae88b630123c9b39c",
"status": "success",
"check": "NOTE",
"buildurl": "https://github.com/r-universe/samuelgonzalez0204/actions/runs/25596191019"
},
{
"r": "4.6.0",
"os": "linux",
"version": "0.1.1",
"date": "2026-05-09T08:17:05.000Z",
"distro": "noble",
"commit": "30ef489dbaa16a2884dd1231c8a43beb41bb8595",
"fileid": "4e76ec96498fd8af156eea4f51516bbf978ac44f6d2fcb9e2c1ffd694610d026",
"status": "success",
"check": "NOTE",
"buildurl": "https://github.com/r-universe/samuelgonzalez0204/actions/runs/25596191019"
},
{
"r": "4.5.3",
"os": "mac",
"version": "0.1.1",
"date": "2026-05-09T08:16:53.000Z",
"commit": "30ef489dbaa16a2884dd1231c8a43beb41bb8595",
"fileid": "0cbff3686f39c037b3ed31624295136168b1237101860907e370d0fd95199d6e",
"status": "success",
"check": "NOTE",
"buildurl": "https://github.com/r-universe/samuelgonzalez0204/actions/runs/25596191019"
},
{
"r": "4.6.0",
"os": "mac",
"version": "0.1.1",
"date": "2026-05-09T08:16:39.000Z",
"commit": "30ef489dbaa16a2884dd1231c8a43beb41bb8595",
"fileid": "74c18b5de3c2b5ecdedcb7bfdc3274627beb91dcda5b41411b419ee0f9c458a1",
"status": "success",
"check": "NOTE",
"buildurl": "https://github.com/r-universe/samuelgonzalez0204/actions/runs/25596191019"
},
{
"r": "4.7.0",
"os": "win",
"version": "0.1.1",
"date": "2026-05-09T08:16:14.000Z",
"commit": "30ef489dbaa16a2884dd1231c8a43beb41bb8595",
"fileid": "ce338a583160e1b90c5dc0170311510944aecd5c2d3902b6ff0d56fb8846af50",
"status": "success",
"check": "NOTE",
"buildurl": "https://github.com/r-universe/samuelgonzalez0204/actions/runs/25596191019"
},
{
"r": "4.5.3",
"os": "win",
"version": "0.1.1",
"date": "2026-05-09T08:16:06.000Z",
"commit": "30ef489dbaa16a2884dd1231c8a43beb41bb8595",
"fileid": "d18f2a38ad280ecd2d948c78afa3304c97979449553623396495a5d948a1fee7",
"status": "success",
"check": "NOTE",
"buildurl": "https://github.com/r-universe/samuelgonzalez0204/actions/runs/25596191019"
},
{
"r": "4.6.0",
"os": "win",
"version": "0.1.1",
"date": "2026-05-09T08:16:08.000Z",
"commit": "30ef489dbaa16a2884dd1231c8a43beb41bb8595",
"fileid": "9b07b68910d6a8643556f15a23c088c7d6f17ebe1ccd62289be190d2f90bf0b5",
"status": "success",
"check": "NOTE",
"buildurl": "https://github.com/r-universe/samuelgonzalez0204/actions/runs/25596191019"
},
{
"r": "4.6.0",
"os": "wasm",
"version": "0.1.1",
"date": "2026-05-22T13:07:45.000Z",
"commit": "30ef489dbaa16a2884dd1231c8a43beb41bb8595",
"fileid": "4a9044145faf5857aea2377ff2d061a105246300970ad8d733e2045d914c0bb6",
"status": "success",
"buildurl": "https://github.com/r-universe/samuelgonzalez0204/actions/runs/25596191019"
}
]
}