Update README.md

README.md

@@ -33,7 +33,7 @@ The dataset is divided into the following splits:
 - `test.txt` : 192 MB  - 100,575 rows   - 5%
 - `valid.txt`: 192 MB  - 100,575 rows   - 5%
 
-Each article in the dataset exceeds 1200 characters in length.
+Each article in the dataset exceeds 1400 characters in length.
 
 ## Data Cleaning and Preprocessing
 
@@ -55,4 +55,38 @@ You can use the `explore_dataset.py` script to explore the dataset by randomly d
 
 ## Additional Information
 
-This dataset is a subset of a larger 10GB French dataset, which also contains several thousand books and theses in French, as well as several hundred thousand Francophone news articles.
+This dataset is a subset of a larger 10GB French dataset, which also contains several thousand books and theses in French, as well as several hundred thousand Francophone news articles.
+
+Certainly! Here's an adapted and translated version for a `README.md` file:
+
+---
+
+# WIKIPEDIA EXTRACT
+
+Inside the `/extract_wiki/` directory, you'll find Python scripts used to extract text to compile this dataset.
+
+## Requirements:
+```python
+pip install datasets aiohttp aiofiles beautifulsoup4 langid
+```
+
+## Scripts:
+
+1. **1_extract_link.py**
+   ```python
+   python 1_extract_link.py
+   ```
+   Script to download the Wikipedia dataset from Hugging Face, extract URLs, and save them to a text file for further processing.
+
+2. **2_extract_content.py**
+   ```python
+   python 2_extract_content.py
+   ```
+   This script retrieves the source code of Wikipedia pages based on URLs found in a text file. Instead of saving the entire HTML of the page, it trims the content, focusing on the main article section, thereby limiting the size of each record.
+
+3. **3_extract_txt.py**
+   ```python
+   python 3_extract_txt.py
+   ```
+   This script extracts the text from the HTML pages and conducts tests to filter the content that should be retained or excluded. This includes language checks, special characters, numbers, etc.
+