Development of a script for analyzing and scoring business profiles on Yelp

Hello!

The Dev Company team is interested in developing a tool for automating the collection and analysis of data from Yelp with monthly updates and Score calculation.

Stack
We see the optimal option as follows:
- Backend: Node.js / Python (scraper + Score calculation logic).
- Scheduler: cron (Cloud / serverless), running on the 1st of each month.
- Storage: Google Sheets API or CSV export to Google Drive.
… - If necessary, we can add a low-code/AI agent (for example, a separate LLM module for assessing "photo quality" or text communication).

Bypassing Yelp blocks
- Proxy rotation + request rate limiting (rate limiting, random delays).
- Mimicking a real browser (headless Chrome/Playwright, correct headers/cookies).
- Backup scenario: partial collection through official/semi-official API, if possible for certain data.
We structure the collection to avoid "hammering" Yelp and minimize the risk of blocking.

What you will receive
- A table (Google Sheets or CSV) with fields: photo/content, response to reviews (response rate/time), rating + number of reviews, profile completeness + final Score according to your formula.
- Automatic monthly run with logs (success/errors by businesses).

Experience
We have experience in building AI/automations (AI CRM, API integrations, Google Sheets, cron jobs, bots, data pipes). We have worked with "vibe coding"/AI agents (Claude, ChatGPT) as an auxiliary layer for content and text analysis.

I will be able to provide the exact amount and timeline after agreeing on the Score formula and volumes (number of businesses, geography, update frequency).

We are ready to have a brief call to finalize the criteria and propose a final implementation plan.

Show original

Translate

Good day! I am ready to complete this project. Extensive experience in developing various applications.

Show original

Translate

We can create a smart parser using AI-first methodology. It may take up to 4 weeks, but possibly faster. Issues with blocking are resolved through anti-detect technologies. Stack: bun/rust. I will be able to provide budget guidance in private, I will be waiting.

Show original

Translate

Hello, Kateryna!

I specialize in exactly these tasks — data collection automation, web scraping, analytics, etc.

The stack I propose
I use a hybrid approach to obtain the most accurate data without blocks:
- Python as the basis for logic and data processing
- Yelp Fusion API — ratings, reviews, hours of operation, photos, categories
- Playwright — to collect what is not available in the API (response time, owner responses, photo quality)
… - AI image analysis (Claude or GPT-Vision) — to assess the visual quality of photos
- Google Sheets API / CSV — for automatic table generation
- Cron (or n8n / Airflow) — for automatic launch on the 1st of each month

Bypassing Yelp's anti-bot protection
Yelp has quite aggressive protection, but this can be resolved:
- Firecrawl / Playwright render JS and bypass Cloudflare
- The possibility of using residential proxies for large volumes. I have a partner business account with leading providers.
- No Selenium windows or unstable solutions — everything works reliably

What will be collected
- ratings, number of reviews, categories
- number of photos + their quality (AI assessment)
- hours of operation, services, claimed/unclaimed
- response time, response rate
- contact details, website
- final Score according to your formula (weights to be discussed)

Automation
The system automatically launches on the 1st of each month, collects all data, recalculates the Score, and updates the table.

Estimated budget
Depends on the number of businesses in the sample, but for an average volume (50–200 profiles):
- Tool development: 200–450 USD
- Setting up auto-launch + documentation: included in the cost
- Support (optional): 30–50 USD/month

Timeline
- 2 days — test run on 5–10 businesses
- 5 days — full implementation with documentation

A small personal note
I am a female developer, and I would be happy if you support women in technical professions ❤️
I promise careful, reliable, and high-quality implementation — with a focus on stability and data accuracy.

I am ready to discuss the details. Write to me. I am confident you will be satisfied with the result!

Show original

Translate

1. node js
2. I will suggest implementation methods after you choose which one will be the most convenient for you and the bypassing of blocks is resolved in advance, I did not see any blocks, anti-captcha opening a real headless browser
3. depending on which implementation option you choose, starting from $150 with the possibility of further support
4. from 7 days

Show original

Translate

Hello, Kateryna!

We have worked on similar tasks — web scraping + AI analysis of business profiles. We have experience bypassing anti-bot systems using Playwright + residential proxies.

For your project, we propose a hybrid approach: Yelp Fusion API (ratings, reviews, photos, hours of operation, occupancy) + Playwright scraping (response speed to reviews, response rate). We evaluate the quality of photos through Claude AI — automatic analysis of visual content. All data → Google Sheets with a final Score according to your formula.

Automatic launch on the 1st of each month — via cron or n8n scheduler, without manual intervention.

On the 2nd day — a test run on 5-10 businesses to agree on the scoring formula and data accuracy. Full delivery with documentation — 5 days.
…
One clarification: how many businesses approximately need to be analyzed in one run? This affects the cost, timelines, and choice of Yelp API and proxy plan. Currently, the price and timelines are indicated for an average number (50-200 businesses).

The FlipFactory Team

Show original

Translate

Good day, I am ready to complete your task quickly and efficiently, I have extensive experience in creating various parsers and data analysis. Write to me in private messages and we will discuss the details. I will be happy to help)

Show original

Translate

Hello. I can implement this project, I have some developments.

1. Browser Automation Studio, there will be a fairly high-quality browser profile, but possibly another solution.
2. High-quality fingerprint and proxy.
3. Approximately 8000 UAH.
4. Approximately 3 days.

Show original

Translate

hello
1. python
2. proxy, if there are captchas they can be bypassed
3. 7-10k UAH, need to discuss the details
4. 10 days

the criteria seem quite simple, so I think they can be counted without a hitch
write

Show original

Translate

Hello! I have reviewed your project and am ready to start working. I guarantee high quality and prompt execution.

Show original

Translate

Hello! What is the approximate number of business pages that will need to be analyzed each month?

I will clarify the exact deadlines and budget in personal correspondence.

How we will implement the project:
1. I will create a stable parser with bypassing Yelp's protection using proxy rotation and user action emulation.
2. I will automate the collection and evaluation of data according to your criteria, calculating the final score using the agreed formula.
3. I will set up a monthly export of results to Google Sheets or a CSV file with subsequent testing of the functionality.

… Thank you for considering my proposal. I will be happy to work on your project!

Show original

Translate