\nconst intro = $(\"p:nth-of-type(2)\").first().text();\nconsole.log(intro);","2025-08-14T13:33:38.449Z","test","https://www.val.town/x/nbreitkopf/test/code/","nbreitkopf",[195,197,199,200],{"_127":145,"_129":196,"_130":22},"import { fetchText } from \"https://esm.town/v/stevekrouse/fetchText?v=6\";",{"_127":160,"_129":198,"_130":137},"import { load } from \"npm:cheerio\";",{"_127":163,"_129":72,"_130":22},{"_127":166,"_129":201,"_130":22},"const html = await fetchText(",{"_104":203,"_106":204,"_108":205,"_110":174,"_112":206,"_114":207,"_116":208,"_118":209,"_120":210,"_122":-5,"_123":-5,"_124":211,"_144":145},"da48fd7a-716f-11f0-b21a-0224a6c84d84","https://www.val.town/x/talhabalaj/whatsapp-me/code/main.tsx","da463bee-716f-11f0-b21a-0224a6c84d84","import * as cheerio from \"npm:cheerio\";\n\nconst secret = Deno.env.get(\"SECRET\");\n\nconst logger = console;\n\ninterface MovieSession {\n date: string;\n dateISO: string;\n times: Array<{\n time: string;\n timeISO: string;\n bookingUrl: string;\n attributes: string[];\n }>;\n}\n\ninterface CinemaData {\n cinemaName: string;\n cinemaUrl: string;\n sessions: MovieSession[];\n}\n\nfunction parseMovieShowtimes(html: string): CinemaData | null {\n const $ = cheerio.load(html);\n\n // Extract cinema information\n const cinemaName = $(\".film-title\").text().trim();\n const cinemaUrl = $(\".film-title\").parent(\"a\").attr(\"href\");\n\n if (!cinemaName) {\n return null; // No movie times available\n }\n\n const sessions: MovieSession[] = [];\n\n // Process each session\n $(\".session\").each((_, sessionElement) => {\n const $session = $(sessionElement);\n\n // Get session date\n const dateText = $session.find(\".session-date\").text().trim();\n\n // Extract times for this session\n const times: MovieSession[\"times\"] = [];\n\n $session.find(\".session-times\").each((_, timesElement) => {\n const $times = $(timesElement);\n\n // Get attributes for this time slot\n const attributes: string[] = [];\n $times.find(\".session-attributes-list img\").each((_, img) => {\n const alt = $(img).attr(\"alt\");\n if (alt) {\n attributes.push(alt);\n }\n });\n\n // Get individual show times\n $times.find(\".session-time\").each((_, timeElement) => {\n const $time = $(timeElement);\n const timeText = $time.find(\"time\").text().trim();\n const timeISO = $time.find(\"time\").attr(\"datetime\") || \"\";\n const bookingUrl = $time.attr(\"href\") || \"\";\n\n times.push({\n time: timeText,\n timeISO: timeISO,\n bookingUrl: bookingUrl.startsWith(\"//\")\n ? `https:${bookingUrl}`\n : bookingUrl,\n attributes: [...attributes],\n });\n });\n });\n\n if (times.length > 0) {\n // Parse date to ISO format\n let dateISO = \"\";\n if (dateText) {\n try {\n const parsedDate = new Date(dateText);\n dateISO = parsedDate.toISOString().split(\"T\")[0];\n } catch (e) {\n dateISO = dateText;\n }\n }\n\n sessions.push({\n date: dateText,\n dateISO: dateISO,\n times: times,\n });\n }\n });\n\n return {\n cinemaName: cinemaName,\n cinemaUrl: cinemaUrl\n ? cinemaUrl.startsWith(\"//\")\n ? `https:${cinemaUrl}`\n : cinemaUrl\n : \"\",\n sessions: sessions,\n };\n}\n\nexport default async function (req: Request): Promise {\n const params = new URL(req.url).searchParams;\n const movieId = params.get(\"movieId\");\n\n if (!movieId) {\n return new Response(\"No movie ID provided\", { status: 400 });\n }\n\n // if (!secret) {\n // return new Response(\"not ready to serve!\", { status: 500 });\n // }\n\n // if (req.headers.get(\"x-secret\") !== secret) {\n // return new Response(\"bye\", { status: 403 });\n // }\n\n logger.log(\"Checking for movie timings\");\n\n const cueData = await fetch(\n `https://cuecinemas.com/Browsing/Movies/Details/${movieId}`\n );\n const cueDataJson = await cueData.text();\n\n const $ = cheerio.load(cueDataJson);\n const showTimesHtml = $(\"#show-times\").html();\n\n console.log(showTimesHtml);\n\n if (showTimesHtml) {\n const movieData = parseMovieShowtimes(showTimesHtml);\n\n if (movieData) {\n return new Response(JSON.stringify(movieData), { status: 200 });\n } else {\n return new Response(\"No movie times available\", { status: 200 });\n }\n } else {\n return new Response(\"No show-times element found\", { status: 200 });\n }\n}\n","2025-08-04T21:26:24.332Z","whatsapp-me","https://www.val.town/x/talhabalaj/whatsapp-me/code/","talhabalaj",[212,213,214],{"_127":145,"_129":164,"_130":137},{"_127":160,"_129":72,"_130":22},{"_127":163,"_129":215,"_130":22},"const secret = Deno.env.get(\"SECRET\");",{"_104":217,"_106":218,"_108":219,"_110":220,"_112":221,"_114":222,"_116":223,"_118":224,"_120":225,"_122":-5,"_123":-5,"_124":226,"_144":145},"69d198a6-6966-11f0-b266-0224a6c84d84","https://www.val.town/x/j_dog_scott/untitled-9009/code/scrape.tsx","c50a4a20-6965-11f0-9e48-0224a6c84d84","scrape.tsx","import { blob } from \"https://esm.town/v/std/blob\";\nimport * as cheerio from \"npm:cheerio\";\n\nconst KEY = new URL(import.meta.url).pathname;\nconst SCRAPE_INTERVAL = 30 * 1000;\nconst LASTFM_USER = \"j_dog_scott\";\n\nexport default async function (req: Request): Promise {\n try {\n const cachedData = await blob.getJSON(KEY) as {\n song: string;\n artist: string;\n album: string;\n lastScrapeTime: number;\n } || { song: \"\", artist: \"\", album: \"\", lastScrapeTime: 0 };\n\n const currentTime = new Date().getTime();\n\n if (currentTime - cachedData.lastScrapeTime >= SCRAPE_INTERVAL) {\n const url = `https://www.last.fm/user/${LASTFM_USER}`;\n const response = await fetch(url);\n const html = await response.text();\n const $ = cheerio.load(html);\n\n let songName = $(\".chartlist-name\").first().text().trim();\n let artistName = $(\".chartlist-artist\").first().text().trim();\n let albumName = $(\".chartlist-album\").first().text().trim();\n\n if (songName && artistName) {\n await blob.setJSON(KEY, {\n song: songName,\n artist: artistName,\n album: albumName || \"\",\n lastScrapeTime: currentTime,\n });\n\n return Response.json({\n song: songName,\n artist: artistName,\n album: albumName,\n status: \"fresh\",\n timestamp: currentTime,\n });\n }\n }\n\n return Response.json({\n song: cachedData.song,\n artist: cachedData.artist,\n album: cachedData.album,\n status: \"cached\",\n timestamp: cachedData.lastScrapeTime,\n });\n } catch (error) {\n return Response.json({ error: error.message }, { status: 500 });\n }\n}","2025-07-25T14:49:43.826Z","untitled-9009","https://www.val.town/x/j_dog_scott/untitled-9009/code/","j_dog_scott",[227,228,229,230],{"_127":145,"_129":183,"_130":22},{"_127":160,"_129":164,"_130":137},{"_127":163,"_129":72,"_130":22},{"_127":166,"_129":231,"_130":22},"const KEY = new URL(import.meta.url).pathname;",{"_104":233,"_106":234,"_108":235,"_110":150,"_112":236,"_114":237,"_116":238,"_118":239,"_120":240,"_122":-5,"_123":-5,"_124":241,"_144":145},"ef02225f-2650-444f-8427-0fdafa14245e","https://www.val.town/x/AIWB/url-to-markdown/code/main.ts","d2eaed04-612f-11f0-aab4-0224a6c84d84","import { load } from \"npm:cheerio\";\nimport TurndownService from \"npm:turndown\";\n\n// almost all from https://www.val.town/x/paulkinlan/markdownify_webpage\n\nexport default async function(req: Request) {\n const url = new URL(req.url).searchParams.get(\"url\");\n\n if (url == \"\" || url == undefined || url == null) {\n return new Response(`\nInvalid Url\n\nPlease ensure that there is a url parameter on the query string. It should be uri-encoded but .. its also fine if it isnt.\n\neg:\n${req.url.replace(\"\\?.*\", \"\")}?url=https://example.com`);\n }\n\n let response;\n try {\n response = await fetch(url);\n } catch (error) {\n return new Response(`# Fetch failed\\n\\nThe ${url} could not fetched.\\n\\n${error}`);\n }\n\n const turndown = new TurndownService();\n const html = await response.text();\n const $ = load(html);\n\n const title = $(\"title\").first().text();\n const bodyText = $(\"body\").first().html();\n\n turndown.addRule(\"no-style\", {\n filter: [\"style\", \"script\", \"footer\", \"iframe\", \"head\", \"img\", \"input\"],\n replacement: function(content) {\n return \"\";\n },\n });\n\n turndown.addRule(\"no-link\", {\n filter: [\"a\"],\n replacement: function(content) {\n return content;\n },\n });\n\n const markdown = turndown.turndown(bodyText);\n return new Response(`# ${title}\\n\\n${markdown}`);\n}","2025-07-15T03:57:27.818Z","url-to-markdown","https://www.val.town/x/AIWB/url-to-markdown/code/","AIWB",[242,243,245],{"_127":145,"_129":198,"_130":137},{"_127":160,"_129":244,"_130":22},"import TurndownService from \"npm:turndown\";",{"_127":163,"_129":72,"_130":22},{"_104":247,"_106":248,"_108":249,"_110":150,"_112":236,"_114":250,"_116":238,"_118":251,"_120":252,"_122":253,"_123":-5,"_124":254,"_144":145},"ed2cd90c-5db5-11f0-96fb-0224a6c84d84","https://www.val.town/x/paulirish/url-to-markdown/code/main.ts","ed2a4e30-5db5-11f0-96fb-0224a6c84d84","2025-07-11T00:43:42.997Z","https://www.val.town/x/paulirish/url-to-markdown/code/","paulirish","thx kinlan",[255,256,257],{"_127":145,"_129":198,"_130":137},{"_127":160,"_129":244,"_130":22},{"_127":163,"_129":72,"_130":22},{"_104":259,"_106":260,"_108":261,"_110":174,"_112":262,"_114":263,"_116":264,"_118":265,"_120":266,"_122":267,"_123":-5,"_124":268,"_144":145},"74e929c2-5c3a-11f0-9e7a-0224a6c84d84","https://www.val.town/x/dr_hex/untitled-5156/code/main.tsx","74e64b6c-5c3a-11f0-9e7a-0224a6c84d84","import axios from \"npm:axios\";\nimport * as cheerio from \"npm:cheerio\";\n\nconst headers = {\n \"sec-ch-ua\": \"\\\"Not_A Brand\\\";v=\\\"8\\\", \\\"Chromium\\\";v=\\\"120\\\", \\\"Microsoft Edge\\\";v=\\\"120\\\"\",\n \"sec-ch-ua-mobile\": \"?0\",\n \"sec-ch-ua-platform\": \"\\\"Windows\\\"\",\n // 'Sec-Fetch-Site': 'none',\n // 'Sec-Fetch-User': '?1',\n \"User-Agent\":\n \"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36 Edg/120.0.0.0\",\n};\n\nconst decode = function(value: string) {\n if (value === undefined) {\n return \"\";\n }\n return atob(value.toString());\n};\n\nexport async function hubcloudExtracter(link: string) {\n try {\n console.log(\"hubcloudExtracter\", link);\n const baseUrl = link.split(\"/\").slice(0, 3).join(\"/\");\n const streamLinks = [];\n const vLinkRes = await axios.get(link, { headers });\n const vLinkText = vLinkRes.data;\n const $vLink = cheerio.load(vLinkText);\n const vLinkRedirect = vLinkText.match(/var\\s+url\\s*=\\s*'([^']+)';/) || [];\n let vcloudLink = decode(vLinkRedirect[1]?.split(\"r=\")?.[1])\n || vLinkRedirect[1]\n || $vLink(\".fa-file-download.fa-lg\").parent().attr(\"href\")\n || link;\n console.log(\"vcloudLink\", vcloudLink);\n if (vcloudLink?.startsWith(\"/\")) {\n vcloudLink = `${baseUrl}${vcloudLink}`;\n console.log(\"New vcloudLink\", vcloudLink);\n }\n const vcloudRes = await fetch(vcloudLink, {\n headers,\n redirect: \"follow\",\n });\n const $ = cheerio.load(await vcloudRes.text());\n // console.log('vcloudRes', $.text());\n\n const linkClass = $(\".btn-success.btn-lg.h6,.btn-danger,.btn-secondary\");\n for (const element of linkClass) {\n const itm = $(element);\n let link = itm.attr(\"href\") || \"\";\n if (link?.includes(\".dev\") && !link?.includes(\"/?id=\")) {\n streamLinks.push({ server: \"Cf Worker\", link: link, type: \"mkv\" });\n }\n if (link?.includes(\"pixeld\")) {\n if (!link?.includes(\"api\")) {\n const token = link.split(\"/\").pop();\n const baseUrl = link.split(\"/\").slice(0, -2).join(\"/\");\n link = `${baseUrl}/api/file/${token}?download`;\n }\n streamLinks.push({ server: \"Pixeldrain\", link: link, type: \"mkv\" });\n }\n if (link?.includes(\"hubcloud\") || link?.includes(\"/?id=\")) {\n try {\n const newLinkRes = await axios.head(link, { headers });\n const newLink = newLinkRes.request?.responseURL?.split(\"link=\")?.[1] || link;\n streamLinks.push({ server: \"hubcloud\", link: newLink, type: \"mkv\" });\n } catch (error) {\n console.log(\"hubcloudExtracter error in hubcloud link: \", error);\n }\n }\n if (link?.includes(\"cloudflarestorage\")) {\n streamLinks.push({ server: \"CfStorage\", link: link, type: \"mkv\" });\n }\n if (link?.includes(\"fastdl\")) {\n streamLinks.push({ server: \"FastDl\", link: link, type: \"mkv\" });\n }\n if (link.includes(\"hubcdn\")) {\n streamLinks.push({\n server: \"HubCdn\",\n link: link,\n type: \"mkv\",\n });\n }\n }\n console.log(\"streamLinks\", streamLinks);\n return streamLinks;\n } catch (error) {\n console.log(\"hubcloudExtracter error: \", error);\n return [];\n }\n}\n\nhubcloudExtracter(\n \"https://hubcloud.one/drive/jx2cssa921j0cah\",\n);","2025-07-08T21:34:14.665Z","untitled-5156","https://www.val.town/x/dr_hex/untitled-5156/code/","dr_hex","Test2",[269,271,272,273],{"_127":145,"_129":270,"_130":22},"import axios from \"npm:axios\";",{"_127":160,"_129":164,"_130":137},{"_127":163,"_129":72,"_130":22},{"_127":166,"_129":274,"_130":22},"const headers = {",{"_104":276,"_106":277,"_108":278,"_110":174,"_112":279,"_114":280,"_116":281,"_118":282,"_120":283,"_122":-5,"_123":-5,"_124":284,"_144":145},"1391f802-58ca-11f0-8ac8-f69ea79377d9","https://www.val.town/x/ryoid/etfdb-aum/code/main.tsx","1390655a-58ca-11f0-8ac8-f69ea79377d9","import * as cheerio from \"npm:cheerio\";\nimport ky from \"npm:ky\";\n\nconst ETFDB_BASE_URL = \"https://etfdb.com/etf\";\n\nasync function fetchETFHtml(ticker: string): Promise {\n const url = `${ETFDB_BASE_URL}/${ticker}/#etf-ticker-profile`;\n\n try {\n const response = await ky.get(url, {\n headers: {\n \"User-Agent\": \"Mozilla/5.0 (compatible; ETF-AUM-Scraper/1.0)\",\n \"Accept\": \"text/html\",\n },\n timeout: 10000,\n });\n\n return await response.text();\n } catch (error) {\n throw new Error(`Failed to fetch ETF page for ${ticker}: ${error}`);\n }\n}\n\nfunction extractAUM(html: string): string | null {\n const $ = cheerio.load(html);\n\n // This selector may need adjustment if the site's structure changes\n const aumElement = $(\"li:contains(\\\"Assets Under Management\\\") span\");\n\n const aumText = aumElement.text().trim();\n\n return aumText || null;\n}\n\nasync function getETFAssetsUnderManagement(ticker: string): Promise {\n const html = await fetchETFHtml(ticker);\n console.log(\"html\", html);\n const aum = extractAUM(html);\n\n if (!aum) {\n throw new Error(`AUM not found for ${ticker}`);\n }\n\n return aum;\n}\n\n// Run example\n(async () => {\n const ticker = \"SPY\";\n\n try {\n const aum = await getETFAssetsUnderManagement(ticker);\n console.log(`${ticker} AUM: ${aum}`);\n } catch (err) {\n console.error(err instanceof Error ? err.message : err);\n }\n})();","2025-07-04T11:30:58.298Z","etfdb-aum","https://www.val.town/x/ryoid/etfdb-aum/code/","ryoid",[285,286,288],{"_127":145,"_129":164,"_130":137},{"_127":160,"_129":287,"_130":22},"import ky from \"npm:ky\";",{"_127":163,"_129":72,"_130":22},"projectResults",[],"userResults",[],"docResults",[295,353],{"_106":296,"_112":297,"_298":299,"_300":301,"_308":309,"_329":330,"_336":337,"_338":339,"_340":341,"_342":343,"_344":345},"https://docs.val.town/guides/web-scraping/","Web scraping. Copy page Copy page. Copy this page as Markdown for LLMs. View as Markdown View this page as plain text. Open in ChatGPT Ask questions about this page. You can use vals to scrape websites, either by fetching HTML and using a parsing library, or by making an API call to an external service that runs a headless browser for you. Locate the HTML element that contains the data you need. Section titled “Locate the HTML element that contains the data you need” Right click on the section of a website that contains the data you want to fetch and then inspect the element. In Chrome, the option is called Inspect and it highlights the HTML element in the Chrome DevTools panel. For example, to scrape the introduction paragraph of the OpenAI page on Wikipedia, inspect the first word of the first paragraph. In the Elements tab, look for the the data you need and right click the parent element and choose Copy selector to get the CSS selector: #mw-content-text > div.mw-parser-output > p:nth-child(7). If you know a little CSS, it’s better to write your own selector by hand to make it more generic. This can make the selector less vulnerable to the website being updated and, e.g., class names changing. In this case, you can use p:nth-of-type(2). Optionally, use document.querySelector in the Console to check your CSS selector is correct. Parsing HTML. Section titled “Parsing HTML” The OpenAI page on Wikipedia is rendered on the server and arrives as a complete HTML document. This makes it a good fit for cheerio which parses HTML markup and provides an API for traversing/manipulating the resulting data structure. We also recommend node-html-parser and linkedom. ExampleRun in Val Town ↗ import { fetchText } from \"https://esm.town/v/stevekrouse/fetchText?v=6\"; import { load } from \"npm:cheerio\"; const html = await fetchText(\"https://en.wikipedia.org/wiki/OpenAI\"); const $ = load(html); // Cheerio accepts a CSS selector, here we pick the second

Search

Docs2

Docs
2