{ "_id": "6a212156cd65a98ecbd1f2a0", "Package": "archiveRetriever", "Title": "Retrieve Archived Web Pages from the 'Internet Archive'", "Version": "0.4.1", "Authors@R": "c(person(given = \"Lukas\",\nfamily = \"Isermann\",\nrole = c(\"aut\", \"cre\"),\nemail = \"lukas.isermann@uni-mannheim.de\",\ncomment = c(ORCID = \"https://orcid.org/0000-0002-7195-9302\")),\nperson(given = \"Konstantin\",\nfamily = \"Gavras\",\nrole = \"aut\",\nemail = \"konstantin@gavras.de\",\ncomment = c(ORCID = \"https://orcid.org/0000-0002-9222-0101\")))", "Description": "Scraping content from archived web pages stored in the\n'Internet Archive' () using a systematic\nworkflow. Get an overview of the mementos available from the\nrespective homepage, retrieve the Urls and links of the page\nand finally scrape the content. The final output is stored in\ntibbles, which can be then easily used for further analysis.", "License": "Apache License (>= 2.0)", "URL": "https://github.com/liserman/archiveRetriever/", "Encoding": "UTF-8", "Roxygen": "list(markdown = TRUE)", "RoxygenNote": "7.3.3", "Config/pak/sysreqs": "libicu-dev libxml2-dev libssl-dev", "Repository": "https://liserman.r-universe.dev", "Date/Publication": "2026-05-05 10:37:02 UTC", "RemoteUrl": "https://github.com/liserman/archiveretriever", "RemoteRef": "HEAD", "RemoteSha": "50bef5c1ed9d3598380b6d6ce4d9c6c59b645f57", "NeedsCompilation": "no", "Packaged": { "Date": "2026-06-04 06:51:29 UTC", "User": "root" }, "Author": "Lukas Isermann [aut, cre] (ORCID:\n),\nKonstantin Gavras [aut] (ORCID:\n)", "Maintainer": "Lukas Isermann ", "MD5sum": "b2ffc2662ff6815f065d77cd723e4ade", "_user": "liserman", "_type": "src", "_file": "archiveRetriever_0.4.1.tar.gz", "_fileid": "ff911ec4279ddb8d4dfea44f0d019d87d7a76df3cd939b90258776aa8dbc77a0", "_filesize": 2859960, "_sha256": "ff911ec4279ddb8d4dfea44f0d019d87d7a76df3cd939b90258776aa8dbc77a0", "_created": "2026-06-04T06:51:29.000Z", "_published": "2026-06-04T06:55:18.794Z", "_distro": "noble", "_jobs": [ { "job": 79465440731, "time": 184, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "7404944013" }, { "job": 79465440758, "time": 170, "config": "linux-release-x86_64", "r": "4.6.0", "check": "OK", "artifact": "7404940611" }, { "job": 79465440695, "time": 137, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "7404940727" }, { "job": 79465440700, "time": 162, "config": "macos-release-arm64", "r": "4.6.0", "check": "OK", "artifact": "7404941272" }, { "job": 79465017356, "time": 193, "config": "source", "r": "4.6.0", "check": "OK", "artifact": "7404895929" }, { "job": 79465440703, "time": 122, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "7404928745" }, { "job": 79465440734, "time": 136, "config": "windows-devel", "r": "4.7.0", "check": "OK", "artifact": "7404932154" }, { "job": 79465440746, "time": 171, "config": "windows-oldrel", "r": "4.5.3", "check": "OK", "artifact": "7404941139" }, { "job": 79465440732, "time": 139, "config": "windows-release", "r": "4.6.0", "check": "OK", "artifact": "7404933236" } ], "_buildurl": "https://github.com/r-universe/liserman/actions/runs/26935749309", "_status": "success", "_host": "GitHub-Actions", "_upstream": "https://github.com/liserman/archiveretriever", "_commit": { "id": "50bef5c1ed9d3598380b6d6ce4d9c6c59b645f57", "author": "Lukas Isermann <61188540+liserman@users.noreply.github.com>", "committer": "GitHub ", "message": "Add tinyverse badge to README", "time": 1777977422 }, "_maintainer": { "name": "Lukas Isermann", "email": "lukas.isermann@uni-mannheim.de", "orcid": "0000-0002-7195-9302" }, "_registered": true, "_dependencies": [ { "package": "anytime", "role": "Imports" }, { "package": "dplyr", "role": "Imports" }, { "package": "ggplot2", "role": "Imports" }, { "package": "gridExtra", "role": "Imports" }, { "package": "httr", "role": "Imports" }, { "package": "jsonlite", "role": "Imports" }, { "package": "lubridate", "role": "Imports" }, { "package": "rvest", "role": "Imports" }, { "package": "stringr", "role": "Imports" }, { "package": "tibble", "role": "Imports" }, { "package": "tidyr", "role": "Imports" }, { "package": "utils", "role": "Imports" }, { "package": "xml2", "role": "Imports" }, { "package": "vcr", "version": ">= 2.0.0", "role": "Suggests" }, { "package": "testthat", "role": "Suggests" }, { "package": "webmockr", "role": "Suggests" } ], "_owner": "liserman", "_selfowned": true, "_usedby": 0, "_updates": [ { "week": "2025-42", "n": 4 }, { "week": "2026-19", "n": 1 } ], "_tags": [ { "name": "v0.4.1", "date": "2025-10-16" } ], "_stars": 18, "_contributors": [ { "user": "liserman", "count": 136, "uuid": 61188540 }, { "user": "kostagav", "count": 72, "uuid": 13746746 }, { "user": "alsogwenny", "count": 13, "uuid": 77443182 }, { "user": "datapumpernickel", "count": 2, "uuid": 65470117 } ], "_userbio": { "uuid": 61188540, "type": "user", "name": "Lukas Isermann", "description": "PhD candidate in Political Science @ University of Mannheim. Issue competition | Political behaviour & attitudes | Climate change | Applied quantitative methods" }, "_downloads": { "count": 237, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/archiveRetriever" }, "_devurl": "https://github.com/liserman/archiveretriever", "_searchresults": 16, "_rbuild": "4.6.0", "_assets": [ "extra/archiveRetriever.html", "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/NEWS.html", "extra/NEWS.txt", "extra/readme.html", "extra/readme.md", "manual.pdf" ], "_homeurl": "https://github.com/liserman/archiveretriever", "_realowner": "liserman", "_cranurl": true, "_releases": [ { "version": "0.0.1", "date": "2021-03-10" }, { "version": "0.0.2", "date": "2021-03-19" }, { "version": "0.1.0", "date": "2021-05-27" }, { "version": "0.1.1", "date": "2022-03-03" }, { "version": "0.1.2", "date": "2022-06-07" }, { "version": "0.2.0", "date": "2022-06-21" }, { "version": "0.3.0", "date": "2022-12-20" }, { "version": "0.3.1", "date": "2022-12-23" }, { "version": "0.4.0", "date": "2024-06-11" }, { "version": "0.4.1", "date": "2025-10-16" } ], "_exports": [ "archive_overview", "retrieve_links", "retrieve_urls", "scrape_urls" ], "_help": [ { "page": "archive_overview", "title": "archive_overview: Getting a first glimpse of mementos available in the Internet Archive", "topics": [ "archive_overview" ] }, { "page": "retrieve_links", "title": "retrieve_links: Retrieving Links of Lower-level web pages of mementos from the Internet Archive", "topics": [ "retrieve_links" ] }, { "page": "retrieve_urls", "title": "retrieve_urls: Retrieving Urls from the Internet Archive", "topics": [ "retrieve_urls" ] }, { "page": "scrape_urls", "title": "scrape_urls: Scraping Urls from the Internet Archive", "topics": [ "scrape_urls" ] } ], "_pkglogo": "https://github.com/liserman/archiveretriever/raw/HEAD/man/figures/logo.png", "_readme": "https://github.com/liserman/archiveretriever/raw/HEAD/README.md", "_rundeps": [ "anytime", "askpass", "BH", "cli", "cpp11", "curl", "dplyr", "farver", "generics", "ggplot2", "glue", "gridExtra", "gtable", "httr", "isoband", "jsonlite", "labeling", "lifecycle", "lubridate", "magrittr", "mime", "openssl", "pillar", "pkgconfig", "purrr", "R6", "RColorBrewer", "Rcpp", "rlang", "rvest", "S7", "scales", "selectr", "stringi", "stringr", "sys", "tibble", "tidyr", "tidyselect", "timechange", "utf8", "vctrs", "viridisLite", "withr", "xml2" ], "_score": 4.936513742478893, "_indexed": true, "_nocasepkg": "archiveretriever", "_universes": [ "liserman" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "0.4.1", "date": "2026-06-04T06:54:04.000Z", "distro": "noble", "commit": "50bef5c1ed9d3598380b6d6ce4d9c6c59b645f57", "fileid": "432ce5b0a67a707afeb7f1e6b074573c08851e7edaaa60d83f881d41c1d5798c", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/liserman/actions/runs/26935749309" }, { "r": "4.6.0", "os": "linux", "version": "0.4.1", "date": "2026-06-04T06:53:55.000Z", "distro": "noble", "commit": "50bef5c1ed9d3598380b6d6ce4d9c6c59b645f57", "fileid": "817e3f5fb88b82c72479623b8f52a8e954e40740430808b89b824478197a9f45", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/liserman/actions/runs/26935749309" }, { "r": "4.5.3", "os": "mac", "version": "0.4.1", "date": "2026-06-04T06:53:58.000Z", "commit": "50bef5c1ed9d3598380b6d6ce4d9c6c59b645f57", "fileid": "08d30fef079c6530b78f569644216662a63b220f347c2db0154cb9ddd9322a98", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/liserman/actions/runs/26935749309" }, { "r": "4.6.0", "os": "mac", "version": "0.4.1", "date": "2026-06-04T06:54:06.000Z", "commit": "50bef5c1ed9d3598380b6d6ce4d9c6c59b645f57", "fileid": "10c07cb48707d7cd1c3586701eed804c6dc58414fb19e5a3e55708eb876c471c", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/liserman/actions/runs/26935749309" }, { "r": "4.6.0", "os": "wasm", "version": "0.4.1", "date": "2026-06-04T06:53:53.000Z", "commit": "50bef5c1ed9d3598380b6d6ce4d9c6c59b645f57", "fileid": "164929cd91b785c0e43e9c7f86f0ab460a8851e97b59dae28a3ec2dcffd1dc00", "status": "success", "buildurl": "https://github.com/r-universe/liserman/actions/runs/26935749309" }, { "r": "4.7.0", "os": "win", "version": "0.4.1", "date": "2026-06-04T06:53:07.000Z", "commit": "50bef5c1ed9d3598380b6d6ce4d9c6c59b645f57", "fileid": "2b929cb7472bb054fc95b65b73e8dd8f109acaa634d4ef19f1bf4f97eb508c0a", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/liserman/actions/runs/26935749309" }, { "r": "4.5.3", "os": "win", "version": "0.4.1", "date": "2026-06-04T06:53:39.000Z", "commit": "50bef5c1ed9d3598380b6d6ce4d9c6c59b645f57", "fileid": "762226612990deff7d52711a97fe0c5ec125e442ea295fca2f3bc1b3a6d03172", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/liserman/actions/runs/26935749309" }, { "r": "4.6.0", "os": "win", "version": "0.4.1", "date": "2026-06-04T06:53:14.000Z", "commit": "50bef5c1ed9d3598380b6d6ce4d9c6c59b645f57", "fileid": "582cdc7ecbe4e3bb0853fba22d6432ea8323724e4cad7b32f5583ecd90a61c08", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/liserman/actions/runs/26935749309" } ] }