add trustpilot scraper

Author: mazen-r

.github/workflows/trustpilot.yaml

@@ -0,0 +1,49 @@
+name: Trustpilot.com Test
+on:
+  workflow_dispatch:
+  schedule:
+    - cron:  '0 12 * * MON'
+
+env:
+  PROJECT_DIR: trustpilot-scraper
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        test: [test_company_scraping, test_search_scraping, test_review_scraping]
+
+    steps:
+    - uses: actions/checkout@v2
+
+    - name: Set up Python
+      uses: actions/setup-python@v2
+      with:
+        python-version: "3.10"
+
+    - name: Install Poetry
+      run: |
+        curl -sSL https://install.python-poetry.org | python3 -
+
+    - name: Cache Poetry virtual environment
+      uses: actions/cache@v2
+      id: cache
+      with:
+        path: ~/.cache/pypoetry/virtualenvs
+        key: ${{ runner.os }}-poetry-${{ hashFiles('**/${{ env.PROJECT_DIR }}/pyproject.toml') }}
+        restore-keys: |
+          ${{ runner.os }}-poetry-
+
+    - name: Install dependencies
+      run: |
+        cd ${{ env.PROJECT_DIR }}
+        poetry install
+
+    - name: Run test
+      env:
+        SCRAPFLY_KEY: ${{ secrets.SCRAPFLY_KEY }}
+      run: |
+        cd ${{ env.PROJECT_DIR }}
+        poetry run pytest test.py -k ${{ matrix.test }}

README.md

@@ -69,6 +69,11 @@ The following is the list of supported websites grouped by type.
 - [Zillow.com](#zillow)
 - [Zoopla.co.uk](#zoopla)
 
+### Reviews
+- [Yellowpages.com](#yellowpages)
+- [Yelp.com](#yelp)
+- [Trustpilot.com](#trustpilot)
+
 ### Social Media
 - [Instagram.com](#instagram)
 - [Threads.net](#threads)
@@ -78,10 +83,6 @@ The following is the list of supported websites grouped by type.
 - [Booking.com](#booking)
 - [Tripadvisor.com](#tripadvisor)
 
-### Other
-- [Yellowpages.com](#yellowpages)
-- [Yelp.com](#yelp)
-
 ------------
 
 ### Aliexpress
@@ -598,6 +599,21 @@ The [tripadvisor.com scraper](./tripadvisor-scraper/) can scrape the following d
 
 For the full guide, refer to our blog article [How to Scrape TripAdvisor.com (2023 Updated)](https://scrapfly.io/blog/how-to-scrape-tripadvisor/)
 
+### Trustpilot
+The [trustpilot.com scraper](./trustpilot-scraper/) can scrape the following data:
+- Company pages for a specific company data.
+- Reviews data in a specific company reviews.
+- Search pages for company listings data.
+
+<details class="is-code">
+  <summary>View sample data</summary>  
+
+  - [Company pages](./trustpilot-scraper/results/companies.json)  
+  - [Reviews pages](./trustpilot-scraper/results/reviews.json)  
+  - [Search pages](./trustpilot-scraper/results/search.json)  
+
+</details> 
+
 ### Twitter(X)
 <!-- <p align="left">
   <img width="100" height="100" src="./.github/assets/x.svg">

trustpilot-scraper/README.md

@@ -0,0 +1,48 @@
+# Trustpilot.com Scraper
+
+This scraper is using [scrapfly.io](https://scrapfly.io/) and Python to scrape product listing data from Trustpilot.com. 
+
+Full tutorial 
+
+The scraping code is located in the `trustpilot.py` file. It's fully documented and simplified for educational purposes and the example scraper run code can be found in `run.py` file.
+
+This scraper scrapes:
+- Trustpilot company pages for company data
+- Trustpilot search pages for company listing data
+- Trustpilot review pages for company reviews
+
+For output examples see the `./results` directory.
+
+## Fair Use Disclaimer
+
+Note that this code is provided free of charge as is, and Scrapfly does __not__ provide free web scraping support or consultation. For any bugs, see the issue tracker.
+
+## Setup and Use
+
+This Trustpilot.com scraper uses __Python 3.10__ with [scrapfly-sdk](https://pypi.org/project/scrapfly-sdk/) package which is used to scrape and parse Trustpilot's data.
+
+0. Ensure you have __Python 3.10__ and [poetry Python package manager](https://python-poetry.org/docs/#installation) on your system.
+1. Retrieve your Scrapfly API key from <https://scrapfly.io/dashboard> and set `SCRAPFLY_KEY` environment variable:
+    ```shell
+    $ export SCRAPFLY_KEY="YOUR SCRAPFLY KEY"
+    ```
+2. Clone and install Python environment:
+    ```shell
+    $ git clone https://github.com/scrapfly/scrapfly-scrapers.git
+    $ cd scrapfly-scrapers/trustpilot-scraper
+    $ poetry install
+    ```
+3. Run example scrape:
+    ```shell
+    $ poetry run python run.py
+    ```
+4. Run tests:
+    ```shell
+    $ poetry install --with dev
+    $ poetry run pytest test.py
+    # or specific scraping areas
+    $ poetry run pytest test.py -k test_company_scraping
+    $ poetry run pytest test.py -k test_search_scraping
+    $ poetry run pytest test.py -k test_review_scraping
+    ```
+

trustpilot-scraper/pyproject.toml

@@ -0,0 +1,33 @@
+[tool.poetry]
+name = "scrapfly-trustpilot"
+version = "0.1.0"
+description = "demo web scraper for Trustpilot.com using Scrapfly"
+authors = ["Mazen Ramadan <[email protected]>"]
+license = "NPOS-3.0"
+readme = "README.md"
+
+[tool.poetry.dependencies]
+python = "^3.10"
+scrapfly-sdk = {extras = ["all"], version = "^0.8.5"}
+loguru = "^0.7.0"
+
+[tool.poetry.group.dev.dependencies]
+black = "^23.3.0"
+ruff = "^0.0.269"
+cerberus = "^1.3.4"
+pytest = "^7.3.1"
+pytest-asyncio = "^0.21.0"
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"
+
+[tool.pytest.ini_options]
+python_files = "test.py"
+
+[tool.black]
+line-length = 120
+target-version = ['py37', 'py38', 'py39', 'py310', 'py311']
+
+[tool.ruff]
+line-length = 120