TF

Assistant Store Manager (40hr) - Markham- Canal Walk

TFG

Full-time Western Cape, South Africa, ZA
Posted 1 week, 3 days ago 15 views 0 applications

Job Description

Here's a thinking process: 1. **Analyze User Input:** - User is acting as a job listing editor. - I receive raw scraped text from a job website. - My job: extract ONLY actual job information, return clean, readable format. - Must REMOVE: social sharing, author bylines, "you may also like", navigation, comments, ads/promotions, cookie/subscription notices, duplicate text, category labels not part of job, stray numbers/formatting artifacts. - Must KEEP and STRUCTURE: job title, company/name, location, job description/responsibilities, requirements/qualifications, how to apply, salary, deadline/closing date, job ID/reference number, contract type/level. - Return ONLY the cleaned job text. No commentary, no headers like "Here is the cleaned version", no markdown. Just the clean job listing text. Wait, the actual prompt I received is different. Let me re-read carefully. The user says: "You receive a plain-text job description. Your ONLY job is to format it as clean semantic HTML." Then there are rules: - Use

for introductory paragraphs and general text - Use

for section headers (e.g. Responsibilities, Qualifications, Requirements, Education, Experience, Skills, How to Apply, Key Duties, About the Role) - Use
  • for list items (duties, requirements, qualifications, skills) - No CSS classes, no inline styles, no
    s, no
    tags - Preserve ALL original content word-for-word — do not add, remove, summarise, or rephrase - If text has no clear sections, just wrap paragraphs in

    tags - Return ONLY the HTML. No markdown fences, no explanation, no preamble. Then there's a big block of job description text. It's raw scraped text with lots of spans, classes, styles, non-breaking spaces, etc. My task: Take that raw text, strip out the HTML tags, classes, styles, inline styles, and format it into clean semantic HTML using only

    ,

    ,
      ,
    • tags. Preserve ALL original content word-for-word. No removing content, no summarizing. But I need to clean the formatting artifacts. Let me look at the raw text carefully. It's a single long string with many nested spans, classes like `SCXW196529815 BCX0`, styles like `margin: 0px; padding: 0px;`, ``, `

      `, `

        `, `
      • `, non-breaking spaces ` `, etc. Rules say: "Preserve ALL original content word-for-word — do not add, remove, summarise, or rephrase". But also: "No CSS classes, no inline styles, no
        s, no
        tags". So I need to strip the presentation tags (spans with classes/styles) but keep the text content. The challenge is that the text content is embedded inside these spans. I need to extract just the text, preserving the order and content, and re-wrap in

        ,

        ,
          ,
        • . Also: "If text has no clear sections, just wrap paragraphs in

          tags". The text does have clear sections: Responsibilities, Qualifications & Experience, Skills, Behaviours, and then another set of Responsibilities/Skills/Behaviours seems duplicated? Let me check. Looking at the raw text, there are multiple sections repeated or duplicated. There's a first part with Responsibilities, Qualifications & Experience, Skills, Behaviours. Then there's a duplicate section with similar content but slightly different phrasing (e.g., "A minimum of 3 years retail experience" vs "A minimum of 3 years retail or admin experience"). Then another Responsibilities section at the end. The instruction: "Preserve ALL original content word-for-word — do not add, remove, summarise, or rephrase". This is tricky if there are duplicates. Do I keep duplicates? The earlier job editor prompt said "Remove Duplicate text (if the title appears multiple times, keep it once)". But the current prompt's rules say: "Preserve ALL original content word-for-word — do not add, remove, summarise, or rephrase". There's a conflict. Let me re-read the very first prompt vs the current one. The first prompt was: "You are a job listing editor. You receive raw scraped text from a job website. Your job is to extract ONLY the actual job information and return it in a clean, readable format. REMOVE all of the following: ... Duplicate text (if the title appears multiple times, keep it once) ... Return ONLY the cleaned job text. Do not add any commentary, headers like "Here is the cleaned version", or markdown formatting. Just the clean job listing text." The current prompt is: "You receive a plain-text job description. Your ONLY job is to format it as clean semantic HTML. Rules: ... Preserve ALL original content word-for-word — do not add, remove, summarise, or rephrase ... Return ONLY the HTML. No markdown fences, no explanation, no preamble." So the current prompt is specifically about formatting as clean semantic HTML, preserving all content word-for-word. It doesn't say to remove duplicates. It says "Preserve ALL original content word-for-word". So I should keep all text, including duplicates, as they appear, just stripping the HTML tags and inline styles/classes. But wait, the rule also says: "No CSS classes, no inline styles, no

          s, no
          tags". So I need to remove all ``, ``, `
          `, `
          `, etc., and just keep the text content, wrapping in

          ,

          ,
            ,
          • . Also: "Use

            for section headers (e.g. Responsibilities, Qualifications, Requirements, Education, Experience, Skills, How to Apply, Key Duties, About the Role)". So I need to identify section headers and wrap them in

            . The section headers in the text are things like "Responsibilities:", "Qualifications & Experience:", "Skills:", "Behaviours:". I should treat these as

            headings, and the following lists as
            • . Let me parse the raw text structure. It's messy. Let me try to outline the text flow: - Starts with `

              Responsibilities:  

              ` then `
              • ...` - Then `

                 

                ` - `

                Qualifications & Experience:

                ` then `

MJC
ECHO
Your MJC Assistant

I'm ECHO, your MJC career assistant. I can help you find jobs, explore career tools, and connect with opportunities across Africa.

How was your experience with ECHO?