${cdata(article.plus ? `${article.title} [Plus]` : article.title)}

{\n const html = await fetchHtml(article.link);\n if (!html) return article;\n\n const $ = cheerio.load(html);\n const root = $(\"div.mod_artikelDetail\").first();\n if (root.length === 0) return article;\n\n const rawTitle = root.find(\"h1\").first().text().replace(/\\s+/g, \" \").trim() ||\n ($('meta[property=\"og:title\"]').attr(\"content\") ?? \"\").trim();\n // Ein \"+\" am Titelende kennzeichnet kostenpflichtige Artikel\n const plus = rawTitle.endsWith(\"+\");\n const title = plus ? rawTitle.replace(/\\s*\\+$/, \"\") : rawTitle;\n\n const categories = root.find(\"span.Ortsmarke\")\n .map((_, el) => $(el).text().replace(/\\s+/g, \" \").trim()).get().filter(Boolean);\n if (plus) categories.push(\"Plus\");\n\n const author = root.find(\"span.pl-fallback\").first().text().replace(/\\s+/g, \" \").trim();\n\n return {\n ...article,\n title,\n plus,\n categories,\n author: author || \"Wiler Nachrichten\",\n description: $('meta[property=\"og:description\"]').attr(\"content\")?.trim(),\n image: absolute($('meta[property=\"og:image\"]').attr(\"content\") ?? \"\", article.link),\n pubDate: parseSwissDate(root.find(\"span.timestamp\").first().text().trim()),\n content: buildContent($, article.link),\n };\n}\n\nexport default async function (req: Request): Promise {\n try {\n const candidates = await discoverArticles();\n const articles = (await runWithConcurrency(candidates, CONCURRENCY, enrichArticle))\n .filter((a) => a.title)\n .sort((a, b) => (b.pubDate?.getTime() ?? 0) - (a.pubDate?.getTime() ?? 0))\n .slice(0, MAX_ITEMS);\n\n const now = new Date();\n const itemsXml = articles.map((article) => {\n const date = article.pubDate ?? now;\n const summary = `

${\n article.image ? `

` : \"\"\n }

${article.description ?? \"\"}

`;\n\n return [\n \" \",\n ` ${cdata(article.plus ? `${article.title} [Plus]` : article.title)}`,\n ` ${cdata(summary)}`,\n article.content ? ` ${cdata(article.content)}` : \"\",\n ` ${escapeXml(article.link)}`,\n ` ${escapeXml(article.link)}#${FEED_REVISION}`,\n article.image\n ? ` `\n : \"\",\n article.image ? ` ` : \"\",\n article.image\n ? ` `\n : \"\",\n article.author ? ` ${cdata(article.author)}` : \"\",\n ...article.categories.map((c) => ` ${cdata(c)}`),\n ` ${date.toUTCString()}`,\n \" \",\n ].filter(Boolean).join(\"\\n\");\n }).join(\"\\n\");\n\n const xml = `\n\n \n ${cdata(FEED_TITLE)}\n ${cdata(FEED_DESCRIPTION)}\n ${SOURCE_URL}/\n Val.town RSS Scraper (cheerio)\n ${now.toUTCString()}\n \n de-CH\n${itemsXml}\n \n`;\n\n return new Response(xml, {\n status: 200,\n headers: {\n \"Content-Type\": \"application/rss+xml; charset=utf-8\",\n \"Cache-Control\": \"public, max-age=300\",\n },\n });\n } catch (err) {\n return new Response(\n `Fehler beim Erzeugen des RSS-Feeds: ${err instanceof Error ? err.message : String(err)}`,\n { status: 500, headers: { \"Content-Type\": \"text/plain; charset=utf-8\" } },\n );\n }\n}\n","label",[132],"ca55e893-0816-4bcc-a471-7cb877d52790","new-file-1488.ts","779bd31a-a156-11f1-9ead-1607ee4eb77e",6,["D",1787755674867],4,"import * as cheerio from \"npm:cheerio@1.0.0\";\nimport { Feed } from \"npm:feed@4.2.2\";\n\nconst SOURCE_URL = \"https://wiler-nachrichten.ch\";\nconst USER_AGENT =\n \"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36\";\n\n// Nur Artikel der letzten X Tage aufnehmen\nconst DAYS_BACK = 30;\n// Sicherheitsobergrenze für die Anzahl Artikel im Feed\nconst MAX_ITEMS = 100;\nconst CONCURRENCY = 10;\n\n// Kategorie-Seiten, die durchsucht werden (Sport, Inserate, Jobs bewusst NICHT enthalten)\nconst CATEGORY_PATHS = [\n \"/\", // Startseite (mischt aktuelle Artikel aus allen Kategorien)\n \"/wil-/-zuzwil\",\n \"/region\",\n \"/hinterthurgau\",\n \"/vereine\",\n \"/lifestyle\",\n \"/community\",\n];\n\n// Kategorie-Segmente, die aus dem Feed ausgeschlossen werden\nconst EXCLUDED_CATEGORY_SEGMENTS = [\"sport\", \"inserate\", \"jobs\"];\n\n// Artikel-URLs enden auf /detail/, z.B. /region/detail/windkraft-ernuechternde-bilanz\nconst ARTICLE_PATH_RE = /\\/detail\\/[a-z0-9\\-]+\\/?$/i;\n\ninterface Article {\n title: string;\n link: string;\n description?: string;\n image?: string;\n pubDate?: Date;\n}\n\nfunction isExcludedCategory(pathname: string): boolean {\n const firstSegment = pathname.split(\"/\").filter(Boolean)[0]?.toLowerCase() ??\n \"\";\n return EXCLUDED_CATEGORY_SEGMENTS.some((c) => firstSegment.includes(c));\n}\n\nfunction titleFromSlug(pathname: string): string {\n const slug = pathname.split(\"/\").filter(Boolean).pop() ?? pathname;\n return slug\n .split(\"-\")\n .filter(Boolean)\n .map((w) => w.charAt(0).toUpperCase() + w.slice(1))\n .join(\" \");\n}\n\nfunction guessImageType(url: string): string {\n const ext = url.split(\"?\")[0].split(\".\").pop()?.toLowerCase();\n switch (ext) {\n case \"png\":\n return \"image/png\";\n case \"webp\":\n return \"image/webp\";\n case \"gif\":\n return \"image/gif\";\n default:\n return \"image/jpeg\";\n }\n}\n\n/** Einfacher Concurrency-Pool. */\nasync function runWithConcurrency(\n items: T[],\n limit: number,\n worker: (item: T) => Promise,\n): Promise {\n const results: R[] = new Array(items.length);\n let index = 0;\n\n async function next(): Promise {\n const current = index++;\n if (current >= items.length) return;\n results[current] = await worker(items[current]);\n return next();\n }\n\n const runners = Array.from(\n { length: Math.min(limit, items.length) },\n () => next(),\n );\n await Promise.all(runners);\n return results;\n}\n\n/** Versucht, ein Schweizer Datum \"DD.MM.YYYY - HH:MM\" aus Text zu parsen (Fallback). */\nfunction parseGermanDate(text: string): Date | undefined {\n const swissMatch = text.match(\n /(\\d{2})\\.(\\d{2})\\.(\\d{4})\\s*-?\\s*(\\d{2}):(\\d{2})/,\n );\n if (swissMatch) {\n const [, day, month, year, hour, minute] = swissMatch;\n const d = new Date(`${year}-${month}-${day}T${hour}:${minute}:00`);\n if (!isNaN(d.getTime())) return d;\n }\n return undefined;\n}\n\n/** Sammelt Artikel-Links von einer einzelnen Listing-Seite (Startseite oder Kategorie). */\nasync function collectFromListingPage(path: string): Promise {\n try {\n const res = await fetch(`${SOURCE_URL}${path}`, {\n headers: {\n \"User-Agent\": USER_AGENT,\n Accept: \"text/html,application/xhtml+xml\",\n },\n });\n if (!res.ok) return [];\n const html = await res.text();\n const $ = cheerio.load(html);\n\n // Pro Artikel-Link (href) den besten (längsten) Text sammeln — dieselbe Seite verlinkt\n // denselben Artikel oft mehrfach (Bild-Link ohne Text, Titel-Link, \"Weiterlesen\"-Link).\n const bestTitleByLink = new Map();\n\n $(\"a[href]\").each((_, el) => {\n const href = $(el).attr(\"href\");\n if (!href) return;\n let url: URL;\n try {\n url = new URL(href, SOURCE_URL);\n } catch {\n return;\n }\n if (url.hostname.replace(/^www\\./, \"\") !== \"wiler-nachrichten.ch\") return;\n if (!ARTICLE_PATH_RE.test(url.pathname)) return;\n if (isExcludedCategory(url.pathname)) return;\n\n const cleanLink = `${url.origin}${url.pathname}`;\n const linkText = $(el).text().replace(/\\s+/g, \" \").trim();\n const candidate = /^weiterlesen$/i.test(linkText) ? \"\" : linkText;\n\n const existing = bestTitleByLink.get(cleanLink);\n if (!existing || candidate.length > existing.length) {\n bestTitleByLink.set(cleanLink, candidate);\n }\n });\n\n return Array.from(bestTitleByLink.entries()).map(([link, title]) => {\n const pathname = new URL(link).pathname;\n return { title: title || titleFromSlug(pathname), link };\n });\n } catch {\n return [];\n }\n}\n\n/** Durchsucht alle erlaubten Kategorie-Seiten + Startseite und dedupliziert. */\nasync function discoverArticles(): Promise {\n const perPage = await Promise.all(CATEGORY_PATHS.map(collectFromListingPage));\n const seen = new Set();\n const items: Article[] = [];\n\n for (const page of perPage) {\n for (const article of page) {\n if (seen.has(article.link)) continue;\n seen.add(article.link);\n items.push(article);\n }\n }\n\n return items;\n}\n\n/**\n * Ruft eine Artikelseite ab und liest Titel/Beschreibung/Bild (Open Graph)\n * sowie das Publikationsdatum aus (Meta-Tag, sonst sichtbares Schweizer Datumsformat).\n */\nasync function enrichWithMeta(article: Article): Promise

{\n const controller = new AbortController();\n const timeout = setTimeout(() => controller.abort(), 8000);\n\n try {\n const res = await fetch(article.link, {\n headers: {\n \"User-Agent\": USER_AGENT,\n Accept:\n \"text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8\",\n \"Accept-Language\": \"de-CH,de;q=0.9\",\n },\n signal: controller.signal,\n });\n\n if (!res.ok) return article;\n\n const html = await res.text();\n const $ = cheerio.load(html);\n\n const ogTitle = $('meta[property=\"og:title\"]').attr(\"content\")?.trim();\n const ogDescription =\n $('meta[property=\"og:description\"]').attr(\"content\")?.trim() ||\n $('meta[name=\"description\"]').attr(\"content\")?.trim();\n let ogImage = $('meta[property=\"og:image\"]').attr(\"content\")?.trim();\n if (ogImage) {\n try {\n ogImage = new URL(ogImage, SOURCE_URL).toString();\n } catch {\n // ungültige Bild-URL ignorieren\n }\n }\n\n let pubDate: Date | undefined;\n const publishedMeta =\n $('meta[property=\"article:published_time\"]').attr(\"content\") ||\n $(\"time[datetime]\").attr(\"datetime\");\n if (publishedMeta) {\n const d = new Date(publishedMeta);\n if (!isNaN(d.getTime())) pubDate = d;\n }\n if (!pubDate) {\n pubDate = parseGermanDate($(\"body\").text());\n }\n\n return {\n ...article,\n title: ogTitle || article.title,\n description: ogDescription,\n image: ogImage,\n pubDate,\n };\n } catch {\n return article;\n } finally {\n clearTimeout(timeout);\n }\n}\n\nexport default async function (req: Request): Promise {\n const isDebug = new URL(req.url).searchParams.has(\"debug\");\n\n try {\n const candidates = await discoverArticles();\n let articles = await runWithConcurrency(\n candidates,\n CONCURRENCY,\n enrichWithMeta,\n );\n\n const cutoff = new Date(Date.now() - DAYS_BACK * 24 * 60 * 60 * 1000);\n // Artikel ohne erkennbares Datum werden NICHT rausgefiltert (lieber zeigen als fälschlich verstecken)\n articles = articles.filter((a) => !a.pubDate || a.pubDate >= cutoff);\n\n articles.sort((a, b) =>\n (b.pubDate?.getTime() ?? 0) - (a.pubDate?.getTime() ?? 0)\n );\n\n if (isDebug) {\n return new Response(\n JSON.stringify(\n {\n candidatesFound: candidates.length,\n afterDateFilter: articles.length,\n cutoffDate: cutoff.toISOString(),\n items: articles.slice(0, 15),\n },\n null,\n 2,\n ),\n {\n status: 200,\n headers: { \"Content-Type\": \"application/json; charset=utf-8\" },\n },\n );\n }\n\n const feed = new Feed({\n title: \"Wiler Nachrichten – Alle Themen (ohne Sport, Inserate, Jobs)\",\n description:\n `Automatisch generierter RSS-Feed von wiler-nachrichten.ch der letzten ${DAYS_BACK} Tage`,\n id: SOURCE_URL,\n link: SOURCE_URL,\n language: \"de-CH\",\n updated: new Date(),\n generator: \"Val.town RSS Scraper (cheerio + feed)\",\n feedLinks: { rss: req.url },\n });\n\n for (const article of articles.slice(0, MAX_ITEMS)) {\n if (!article.title) continue;\n\n const contentParts: string[] = [];\n if (article.image) {\n contentParts.push(` $\"\"$ `);\n }\n if (article.description) {\n contentParts.push(`

${article.description}

`);\n }\n\n feed.addItem({\n title: article.title,\n id: article.link,\n link: article.link,\n description: article.description,\n content: contentParts.length > 0 ? contentParts.join(\"\\n\") : undefined,\n image: article.image,\n enclosure: article.image\n ? { url: article.image, type: guessImageType(article.image) }\n : undefined,\n date: article.pubDate ?? new Date(),\n });\n }\n\n return new Response(feed.rss2(), {\n status: 200,\n headers: { \"Content-Type\": \"application/rss+xml; charset=utf-8\" },\n });\n } catch (err) {\n return new Response(\n `Fehler beim Erzeugen des RSS-Feeds: ${\n err instanceof Error ? err.message : String(err)\n }`,\n { status: 500, headers: { \"Content-Type\": \"text/plain; charset=utf-8\" } },\n );\n }\n}",[144],"1658a361-5ac8-4b54-9c28-ab2f8feab148","main.ts","7421a5de-a156-11f1-8a3c-1607ee4eb77e",1,["D",1787752811267],[152],"pulls","branches","forks","envVars",{"_164":61,"_166":61},"connections",{"_164":61,"_165":61},"count","unfilledCount","emptyCount",{"_42":151,"_32":152,"_30":153,"_134":-5,"_40":41,"_39":154,"_136":48,"_37":177,"_13":61,"_33":34,"_35":53,"_24":48,"_141":-5,"_171":178,"_27":179},{"_42":143,"_32":144,"_30":145,"_134":-5,"_40":41,"_39":146,"_136":48,"_37":174,"_13":148,"_33":139,"_35":149,"_24":48,"_141":-5,"_171":175,"_27":176},{"_42":131,"_32":132,"_30":133,"_134":-5,"_40":41,"_39":135,"_136":25,"_37":170,"_13":138,"_33":139,"_35":140,"_24":48,"_141":-5,"_171":172,"_27":173},["D",1789296236261],"children",[],[132],["D",1787755674867],[],[144],["D",1787752811267],[],[152],["D",1787752811234],["D",1789575110896],{"_98":97,"_106":102},{"_98":97,"_99":100,"_101":102,"_18":55,"_103":104,"_105":48},{"_13":87,"_32":88,"_42":41,"_89":43,"_90":-5,"_91":-5,"_92":-5,"_93":-5,"_94":-5,"_95":44,"_96":97},"ctx",{"_80":-5,"_125":218,"_219":220,"_221":222,"_223":48,"_224":48,"_225":48,"_226":25,"_227":-5,"_228":-7,"_229":-7,"_230":61,"_231":48,"_232":48,"_233":-5,"_234":48,"_235":48,"_236":48,"_237":-5},"ENV",{"_189":190,"_191":192,"_193":88,"_194":195,"_196":197,"_198":199,"_200":201,"_202":203,"_204":205,"_206":207,"_208":209,"_210":211,"_212":213,"_214":215,"_216":217},"REACT_APP_SENTRY_DSN","https://586020d86f05489db63a554690acf1e9@o1398359.ingest.sentry.io/6724499","RENDER_GIT_COMMIT","811aa22498c9b0b5a47e8d778de579cdb990f332","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",[],"preferencesKeybindings","default","preferencesTheme","light","preferencesFixers","preferencesCopilot","preferencesSelectionAi","preferencesCloseBrackets","preferencesChatPanelState","preferencesDprint","preferencesDenofmt","notificationCount","flagDenols","isBusinessOrgMember","businessOrgHandle","isBusinessOrgAdmin","isHigherTownieTier","navCollapsed","currentOrgId"]

${escapeHtml(text)}

Diff · v20