[Init]

crawl-prime/.gitignore

@@ -1,160 +1 @@
-# Byte-compiled / optimized / DLL files
+.idea
-__pycache__/
-*.py[cod]
-*$py.class
-
-# C extensions
-*.so
-
-# Distribution / packaging
-.Python
-build/
-develop-eggs/
-dist/
-downloads/
-eggs/
-.eggs/
-lib/
-lib64/
-parts/
-sdist/
-var/
-wheels/
-share/python-wheels/
-*.egg-info/
-.installed.cfg
-*.egg
-MANIFEST
-
-# PyInstaller
-#  Usually these files are written by a python script from a template
-#  before PyInstaller builds the exe, so as to inject date/other infos into it.
-*.manifest
-*.spec
-
-# Installer logs
-pip-log.txt
-pip-delete-this-directory.txt
-
-# Unit test / coverage reports
-htmlcov/
-.tox/
-.nox/
-.coverage
-.coverage.*
-.cache
-nosetests.xml
-coverage.xml
-*.cover
-*.py,cover
-.hypothesis/
-.pytest_cache/
-cover/
-
-# Translations
-*.mo
-*.pot
-
-# Django stuff:
-*.log
-local_settings.py
-db.sqlite3
-db.sqlite3-journal
-
-# Flask stuff:
-instance/
-.webassets-cache
-
-# Scrapy stuff:
-.scrapy
-
-# Sphinx documentation
-docs/_build/
-
-# PyBuilder
-.pybuilder/
-target/
-
-# Jupyter Notebook
-.ipynb_checkpoints
-
-# IPython
-profile_default/
-ipython_config.py
-
-# pyenv
-#   For a library or package, you might want to ignore these files since the code is
-#   intended to run in multiple environments; otherwise, check them in:
-# .python-version
-
-# pipenv
-#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
-#   However, in case of collaboration, if having platform-specific dependencies or dependencies
-#   having no cross-platform support, pipenv may install dependencies that don't work, or not
-#   install all needed dependencies.
-#Pipfile.lock
-
-# poetry
-#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
-#   This is especially recommended for binary packages to ensure reproducibility, and is more
-#   commonly ignored for libraries.
-#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
-#poetry.lock
-
-# pdm
-#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
-#pdm.lock
-#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
-#   in version control.
-#   https://pdm.fming.dev/#use-with-ide
-.pdm.toml
-
-# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
-__pypackages__/
-
-# Celery stuff
-celerybeat-schedule
-celerybeat.pid
-
-# SageMath parsed files
-*.sage.py
-
-# Environments
-.env
-.venv
-env/
-venv/
-ENV/
-env.bak/
-venv.bak/
-
-# Spyder project settings
-.spyderproject
-.spyproject
-
-# Rope project settings
-.ropeproject
-
-# mkdocs documentation
-/site
-
-# mypy
-.mypy_cache/
-.dmypy.json
-dmypy.json
-
-# Pyre type checker
-.pyre/
-
-# pytype static type analyzer
-.pytype/
-
-# Cython debug symbols
-cython_debug/
-
-# PyCharm
-#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
-#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
-#  and can be added to the global gitignore or merged into this file.  For a more nuclear
-#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
-#.idea/

crawl-prime/README.md

@@ -1,2 +1,27 @@
 # crawl-prime
+
 Crawl all prime available on http://compoasso.free.fr/primelistweb/page/prime/liste_online_en.php
+
+## Installation
+
+1. Clone this repository:
+   ```bash
+   git clone https://github.com/tiennm99/crawl-prime.git
+   cd crawl-prime
+
+2. Create a virtual environment:
+   ```bash
+   python -m venv venv
+   source venv/bin/activate   # On macOS/Linux
+   venv\Scripts\activate      # On Windows
+   ```
+
+3. Install the dependencies:
+   ```bash
+    pip install -r requirements.txt
+    ```
+
+4. Run the script:
+   ```bash
+    python main.py
+    ```

crawl-prime/main.py

@@ -0,0 +1,33 @@
+import requests
+from bs4 import BeautifulSoup
+
+url = "http://compoasso.free.fr/primelistweb/page/prime/liste_online_en.php"
+max = 1_000_000
+current = 0
+
+while current < max:
+  data = {
+    "primePageInput": "600",
+    "numberInput": current,
+  }
+
+  response = requests.post(url, data=data)
+
+  if response.status_code == 200:
+    soup = BeautifulSoup(response.text, 'html.parser')
+    table = soup.find('table')
+    if table:
+      form = table.find('form')
+      if form:
+        table1 = form.find('table')
+        if table1:
+          td_elements = table1.find_all('td')
+          output_file = "primes.txt"
+
+          with open(output_file, "a", encoding="utf-8") as file:
+            for td in td_elements[0:-10]:
+              file.write(td.text + "\n")
+
+          current = int(td_elements[-11].text) + 1
+  else:
+    print("Error - current: " + current)