[{"_1":2,"_3":-5,"_4":-5},"loaderData",{"_5":6,"_7":8},"actionData","errors","root",{"_109":110,"_111":112},"routes/embed.x.$handle.$name.$",{"_9":10,"_11":12,"_13":14,"_15":16,"_17":18,"_19":20,"_21":-5},"handle","hrbrmstr","name","acm-queue-rss","path","scraper.ts","project",{"_22":45,"_11":12,"_33":46,"_47":-5,"_48":42,"_49":50,"_51":50,"_52":53,"_54":-5,"_55":56,"_57":58,"_59":32,"_60":-5,"_61":-5,"_62":63,"_64":65,"_66":67,"_68":69,"_70":71,"_72":-5,"_73":74,"_75":74,"_76":77,"_78":77,"_79":77,"_80":74,"_81":74,"_82":83,"_84":85,"_86":87,"_88":42},"file",{"_22":23,"_11":14,"_24":25,"_26":-5,"_27":28,"_29":30,"_31":32,"_33":34,"_35":36,"_37":38,"_39":40,"_41":42,"_43":-5,"_13":44},"permalink","https://www.val.town/x/hrbrmstr/acm-queue-rss/code/scraper.ts","extension","id","834d85c8-35d8-4a97-a2f2-ab685a2c9778","fileId","01a08bfd-346d-72ac-8a3b-35070e4ea120","parentId","branchId","ea6eabf2-9cae-40e3-b677-a6554a6f68c3","branchVersion",15,"latest",true,"createdAt",["D",1789058835894],"version",9,"fileType","script","content","// ACM Queue scraper — fetches recent articles from queue.acm.org.\n//\n// queue.acm.org itself sits behind aggressive Cloudflare bot protection and\n// returns 403 to datacenter IPs, so instead we read the ACM Digital Library's\n// official eTOC feed for Queue (RSS 1.0/RDF):\n//\n// https://dl.acm.org/action/showFeed?type=etoc&feed=rss&jc=queue\n//\n// It carries the latest issue's articles with title, authors, dates and DOI.\n// Links are normalized from the dl.acm.org referral URLs (?af=R) to\n// queue.acm.org/doi/full/ so readers land on the Queue site.\n\nimport { sqlite } from \"https://esm.town/v/std/sqlite/main.ts\";\n\nconst FEED_URL = \"https://dl.acm.org/action/showFeed?type=etoc&feed=rss&jc=queue\";\nconst BROWSER_UA =\n \"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36\";\n\nexport interface QueueArticle {\n slug: string; // DOI, e.g. \"10.1145/3831359\"\n title: string;\n authors: string | null;\n pubDate: string;\n description: string | null;\n link: string;\n}\n\n/** Extract text content from ALL occurrences of a tag inside an RDF block. */\nfunction tagAll(item: string, tag: string): string[] {\n const re = new RegExp(`<${tag}[^>]*>([\\\\s\\\\S]*?)`, \"g\");\n const out: string[] = [];\n for (const m of item.matchAll(re)) {\n const text = decodeEntities(m[1].replace(/<[^>]+>/g, \" \").replace(/\\s+/g, \" \").trim());\n if (text) out.push(text);\n }\n return out;\n}\n\nfunction decodeEntities(s: string): string {\n return s\n .replace(/&/g, \"&\")\n .replace(/</g, \"<\")\n .replace(/>/g, \">\")\n .replace(/"/g, '\"')\n .replace(/&#(\\d+);/g, (_m, n) => String.fromCodePoint(Number(n)));\n}\n\n/** Fetch and parse the ACM DL eTOC feed for Queue. */\nexport async function fetchQueueArticles(): Promise {\n const res = await fetch(FEED_URL, {\n headers: {\n \"User-Agent\": BROWSER_UA,\n \"Accept\": \"application/rss+xml, application/xml, text/xml, */*\",\n \"Accept-Language\": \"en-US,en;q=0.9\",\n },\n });\n if (!res.ok) {\n throw new Error(`Failed to fetch ACM Queue TOC feed: ${res.status} ${res.statusText}`);\n }\n\n const xml = await res.text();\n const entries: QueueArticle[] = [];\n const seen = new Set();\n\n const itemRe = //g;\n for (const item of xml.match(itemRe) ?? []) {\n const first = (tag: string) => tagAll(item, tag)[0] ?? null;\n const title = first(\"dc:title\") ?? first(\"title\");\n const doi = first(\"prism:doi\") ?? (first(\"dc:identifier\") ?? \"\").replace(/^doi:/, \"\");\n if (!title || !doi) continue;\n\n const slug = doi;\n if (seen.has(slug)) continue;\n seen.add(slug);\n\n const pubDate = first(\"dc:date\") ?? first(\"prism:coverDate\") ?? \"\";\n const authorList = tagAll(item, \"dc:creator\");\n // ACM's eTOC feed concatenates multiple authors with no separator\n // (e.g. \"A. MeyerB. MeyerC. Murphy\"), so split at lowercase→uppercase\n // boundaries (each author is \"Given Surname\" → next begins uppercase).\n const authors = authorList\n .map((a) => a.replace(/([a-z])(?=[A-Z])/g, \"$1, \").replace(/,\\s*,/g, \",\").trim())\n .join(\", \") || null;\n const description = first(\"description\");\n\n entries.push({\n slug,\n title,\n authors,\n pubDate: pubDate ? new Date(pubDate).toISOString() : \"\",\n description,\n link: `https://queue.acm.org/doi/full/${doi}`,\n });\n }\n\n console.log(`Parsed ${entries.length} ACM Queue articles from TOC feed`);\n return entries;\n}\n\n/** Upsert articles into SQLite. Returns rows affected. */\nexport async function upsertEntries(entries: QueueArticle[]): Promise {\n if (entries.length === 0) return 0;\n\n const statements = entries.map((entry) => ({\n sql: `INSERT INTO queue_articles (slug, title, authors, pub_date, description, link)\n VALUES (?, ?, ?, ?, ?, ?)\n ON CONFLICT(slug) DO UPDATE SET\n title = excluded.title,\n authors = excluded.authors,\n pub_date = CASE WHEN excluded.pub_date = '' THEN queue_articles.pub_date ELSE excluded.pub_date END,\n description = COALESCE(excluded.description, queue_articles.description),\n link = excluded.link,\n updated_at = datetime('now')`,\n args: [entry.slug, entry.title, entry.authors, entry.pubDate, entry.description, entry.link],\n }));\n\n const results = await sqlite.batch(statements);\n return results.reduce((sum, r) => sum + (r.rowsAffected ?? 0), 0);\n}\n\n/** Full scrape + store pipeline. Returns summary. */\nexport async function scrapeAndStore(): Promise {\n const entries = await fetchQueueArticles();\n const count = await upsertEntries(entries);\n const msg = `Scraped ${entries.length} articles, upserted ${count}`;\n console.log(msg);\n return msg;\n}\n","deleted",false,"label",[14],"85f81756-4d6c-4031-ada5-d90abfb110d6",["D",1789055022114],"deletedAt","legacyEnvVars","privacy","public","httpPrivacy","description","Unofficial RSS feed for the ACM Queue ","imageUrl","userId","660e611e-30de-4ed3-8449-79507be25f74","pinnedFileId","01a08bfd-346d-72ac-8a3b-2b364bb97477","pinPreview","pinMigrated","screenshotVersion","likeCount",0,"orgId","f4053730-af3b-4f20-9c5e-6d19f910dfd0","tursoName","85f817564d6c4031ada5d90abfb110d6","tursoHostname","85f817564d6c4031ada5d90abfb110d6-val-town.aws-us-east-2.turso.io","tursoMeasuredAt",["D",1789488693443],"pinned","userPerm","r","valPerm","blobPerm","rw","emailPerm","sqlitePerm","projectPerm","telemetryPerm","user",{"_9":10,"_108":104},"org",{"_9":10,"_102":-5,"_103":104,"_55":56,"_105":106,"_107":42},"branch",{"_35":89,"_11":90,"_22":28,"_91":45,"_92":93,"_94":95,"_96":50,"_97":98,"_99":65,"_100":12,"_101":10},"isOwned",16,"main","projectId","forkedBranchId","97df149b-8210-434c-b3d7-1d1b2ce3d5cf","forkedBranchVersion",10,"forkedProjectPrivacy","forkedProjectId","7f8d8abb-937e-4199-a86a-87d156d4c9e5","forkedProjectOrgId","projectName","userHandle","displayName","avatar","https://img.clerk.com/eyJ0eXBlIjoicHJveHkiLCJzcmMiOiJodHRwczovL2ltYWdlcy5jbGVyay5kZXYvb2F1dGhfZ2l0aHViL2ltZ18ybTQ2MzZSZEl6dm1wZjZnT1hJM2NGNjFCbWgifQ","tier","pro","canRestrictVals","profileImageUrl","ctx",{"_82":-5,"_142":143,"_144":145,"_146":147,"_148":42,"_149":42,"_150":42,"_151":32,"_152":-5,"_153":-7,"_154":-7,"_155":63,"_156":42,"_157":42,"_158":-5,"_159":42,"_160":42,"_161":42,"_162":-5},"ENV",{"_113":114,"_115":116,"_117":90,"_118":119,"_120":121,"_122":123,"_124":125,"_126":127,"_128":129,"_130":131,"_132":133,"_134":135,"_136":137,"_138":139,"_140":141},"REACT_APP_SENTRY_DSN","https://586020d86f05489db63a554690acf1e9@o1398359.ingest.sentry.io/6724499","RENDER_GIT_COMMIT","e87eb04e707cf64e7e532c8e8ec395f209e17f15","RENDER_GIT_BRANCH","POSTHOG_API_TOKEN","phc_nmoyuAkStEZuUp69rYlg1DZgrIt19Gx0Y4Hwf8tGgJP","POSTHOG_API_HOST","https://wart.val.town","WEB_API_TEMPLATE","https://{val}.web.val.run","APP_URL","https://www.val.town","MODULE_URL","https://esm.town","VANITY_WEB_API_TEMPLATE","https://{label}.val.run/","DENOLS_URL","https://lsp.val.town","NODE_ENV","production","CLOUDFLARE_TURNSTILE_SITE_KEY","0x4AAAAAACtaIZJH7s9rBMZ6","GOOGLE_CLIENT_ID","875989696899-jtsqkhlbdv5jrlsk8631p7ipjg3c6o62.apps.googleusercontent.com","STRIPE_PUBLISHABLE_KEY","pk_live_51N2zvWEpZTTLipIkVEwXrUG9AT0yeOOEYxszarZT1jpsZV58Ly6wlg3SltZpHN26CUalOBmUSY7adQRQiSkCZz2500qSXNkf8Y","API_URL","https://api.val.town","orgs",[],"preferencesKeybindings","default","preferencesTheme","light","preferencesFixers","preferencesCopilot","preferencesSelectionAi","preferencesCloseBrackets","preferencesChatPanelState","preferencesDprint","preferencesDenofmt","notificationCount","flagDenols","isBusinessOrgMember","businessOrgHandle","isBusinessOrgAdmin","isHigherTownieTier","navCollapsed","currentOrgId"]