Initial release: AI-powered job application framework

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-09-17 16:46:24 +00:00 · 2026-03-23 08:34:06 +01:00
commit c66d599d75
73 changed files with 6539 additions and 0 deletions
@@ -0,0 +1,197 @@
+export const BASE_URL = "https://www.jobindex.dk"
+
+export function writeError(error: string, code: string): void {
+  process.stderr.write(JSON.stringify({ error, code }) + "\n")
+}
+
+export async function apiFetch<T>(path: string, params?: Record<string, string>): Promise<T> {
+  let url = `${BASE_URL}${path}`
+  if (params && Object.keys(params).length > 0) {
+    const qs = new URLSearchParams(params)
+    url += `?${qs.toString()}`
+  }
+
+  const maxRetries = 6
+  let delay = 500
+  for (let attempt = 0; attempt <= maxRetries; attempt++) {
+    const response = await fetch(url)
+    if (response.status === 429 || response.status >= 500) {
+      if (attempt === maxRetries) {
+        throw new Error(`API request failed: ${response.status} ${response.statusText}`)
+      }
+      const jitter = Math.floor(Math.random() * 500)
+      await new Promise((resolve) => setTimeout(resolve, delay + jitter))
+      delay = Math.min(delay * 2, 5000)
+      continue
+    }
+    if (!response.ok) {
+      throw new Error(`API request failed: ${response.status} ${response.statusText}`)
+    }
+    return response.json() as Promise<T>
+  }
+  throw new Error("API request failed after max retries")
+}
+
+export async function htmlFetch(url: string): Promise<string> {
+  const maxRetries = 6
+  let delay = 500
+  for (let attempt = 0; attempt <= maxRetries; attempt++) {
+    const response = await fetch(url, {
+      headers: {
+        "User-Agent": "Mozilla/5.0 (compatible; jobindex-cli/1.0)",
+        "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
+        "Accept-Language": "da,en;q=0.9",
+      },
+      redirect: "follow",
+    })
+    if (response.status === 429 || response.status >= 500) {
+      if (attempt === maxRetries) {
+        throw new Error(`API request failed: ${response.status} ${response.statusText}`)
+      }
+      const jitter = Math.floor(Math.random() * 500)
+      await new Promise((resolve) => setTimeout(resolve, delay + jitter))
+      delay = Math.min(delay * 2, 5000)
+      continue
+    }
+    if (response.status === 404) {
+      throw new Error(`Job not found`)
+    }
+    if (!response.ok) {
+      throw new Error(`API request failed: ${response.status} ${response.statusText}`)
+    }
+    return response.text()
+  }
+  throw new Error("Request failed after max retries")
+}
+
+export interface JobCard {
+  id: string
+  title: string
+  company: string | null
+  companyUrl: string | null
+  location: string | null
+  date: string | null
+  url: string
+  description: string | null
+}
+
+/**
+ * Decode HTML entities in text
+ */
+function decodeHtmlEntities(text: string): string {
+  return text
+    .replace(/&amp;/g, "&")
+    .replace(/&lt;/g, "<")
+    .replace(/&gt;/g, ">")
+    .replace(/&quot;/g, '"')
+    .replace(/&#39;/g, "'")
+    .replace(/&apos;/g, "'")
+    .replace(/&#(\d+);/g, (_, code) => String.fromCharCode(parseInt(code, 10)))
+    .replace(/&nbsp;/g, " ")
+}
+
+/**
+ * Strip HTML tags from text
+ */
+function stripTags(html: string): string {
+  return html.replace(/<[^>]+>/g, "").trim()
+}
+
+/**
+ * Parse job cards from result_list_box_html using regex.
+ * node-html-parser has nesting bugs with this specific HTML structure
+ * (unclosed tags inside buttons cause incorrect DOM tree).
+ * Regex parsing is more reliable for this specific HTML format.
+ */
+export function parseJobCards(html: string): JobCard[] {
+  const results: JobCard[] = []
+
+  // Split HTML by jobad-wrapper to get individual card HTML chunks
+  const wrapperPattern = /<div[^>]+id="jobad-wrapper-(h\d+|r\d+)"[^>]*>([\s\S]*?)(?=<div[^>]+id="jobad-wrapper-|$)/g
+
+  let match: RegExpExecArray | null
+  while ((match = wrapperPattern.exec(html)) !== null) {
+    const id = match[1]
+    const cardHtml = match[2]
+
+    // Extract title: look for <h4>...<a|A href="...">Title</a>...</h4>
+    const titleMatch = cardHtml.match(/<h4[^>]*>[\s\S]*?<[Aa][^>]+href="([^"]+)"[^>]*>([\s\S]*?)<\/[Aa]>/i)
+    if (!titleMatch) continue
+    const rawTitle = stripTags(titleMatch[2])
+    const title = decodeHtmlEntities(rawTitle)
+    if (!title) continue
+
+    // Determine URL: prefer jobindex.dk /jobannonce/ URL, fallback to constructed URL
+    let url: string
+    const jobannonce = cardHtml.match(/href="(https:\/\/www\.jobindex\.dk\/jobannonce\/[^"]+)"/)
+    if (jobannonce) {
+      url = jobannonce[1]
+    } else {
+      // Construct canonical URL from ID
+      url = `${BASE_URL}/jobannonce/${id}`
+    }
+
+    // Extract company: <a ...> inside jix-toolbar-top__company
+    let company: string | null = null
+    let companyUrl: string | null = null
+    const companySection = cardHtml.match(/class="jix-toolbar-top__company"[^>]*>([\s\S]*?)<\/div>/i)
+    if (companySection) {
+      const companyLinkMatch = companySection[1].match(/<[Aa][^>]+href="([^"]+)"[^>]*>([\s\S]*?)<\/[Aa]>/i)
+      if (companyLinkMatch) {
+        company = decodeHtmlEntities(stripTags(companyLinkMatch[2])) || null
+        companyUrl = companyLinkMatch[1] || null
+      }
+    }
+
+    // Extract location: <span class="jix_robotjob--area">Location</span>
+    const locMatch = cardHtml.match(/<span[^>]+class="jix_robotjob--area"[^>]*>([\s\S]*?)<\/span>/i)
+    const location = locMatch ? decodeHtmlEntities(stripTags(locMatch[1])) || null : null
+
+    // Extract date: <time datetime="YYYY-MM-DD">
+    const dateMatch = cardHtml.match(/<time[^>]+datetime="([^"]+)"/)
+    const date = dateMatch ? dateMatch[1] : null
+
+    // Extract description: first <p class="..."> or first standalone <p> (not in toolbar)
+    // Skip the toolbar/menu section and look for the description paragraph
+    let description: string | null = null
+    const innerSection = cardHtml.match(/class="PaidJob-inner"[^>]*>([\s\S]*?)(?:<\/div>\s*<\/div>|$)/i) ||
+                         cardHtml.match(/class="jix_robotjob-inner"[^>]*>([\s\S]*?)(?:<\/div>\s*<\/div>|$)/i)
+    if (innerSection) {
+      const pMatch = innerSection[1].match(/<p[^>]*>([\s\S]*?)<\/p>/i)
+      if (pMatch) {
+        const text = decodeHtmlEntities(stripTags(pMatch[1]))
+        description = text.length > 0 ? text.substring(0, 300) : null
+      }
+    } else {
+      // Fallback: look for p after the jobannonce link
+      const pMatches = [...cardHtml.matchAll(/<p[^>]*>([\s\S]*?)<\/p>/gi)]
+      for (const pm of pMatches) {
+        const text = decodeHtmlEntities(stripTags(pm[1]))
+        if (text.length > 20) {
+          description = text.substring(0, 300)
+          break
+        }
+      }
+    }
+
+    results.push({
+      id,
+      title,
+      company: company || null,
+      companyUrl: companyUrl || null,
+      location: location || null,
+      date: date || null,
+      url,
+      description: description || null,
+    })
+  }
+
+  return results
+}
+
+export function parseHitCount(html: string): number {
+  const match = html.match(/af <strong>([\d.]+)<\/strong>/)
+  if (!match) return 0
+  const numStr = match[1].replace(/\./g, "")
+  return parseInt(numStr, 10) || 0
+}