Get package objects from HTML

This commit is contained in:
agatha 2023-12-02 14:49:46 -05:00
parent 44362f32ab
commit 6c33e418e2
2 changed files with 45 additions and 0 deletions

44
main.py Normal file
View File

@ -0,0 +1,44 @@
"""buyvm stock checker"""
from bs4 import BeautifulSoup
def get_packages(html):
soup = BeautifulSoup(html, 'html.parser')
packages = []
package_elements = soup.find_all('div', class_='package')
for package_element in package_elements:
package = {}
package_name = package_element.find('h3', class_='package-name').text.strip()
package['name'] = package_name
package_quantity = package_element.find('div', class_='package-qty').text.strip()
package['qty'] = package_quantity
order_button = package_element.find('a', class_='btn-primary')
if order_button:
order_url = order_button['href']
package['url'] = order_url
else:
package['url'] = ''
packages.append(package)
return packages
def main():
with open('tests/data/stock.html', 'r', encoding='utf-8') as file:
html = file.read()
packages = get_packages(html)
for package in packages:
print('Package Name:', package['name'])
print('Package Quantity:', package['qty'])
print('Order URL:', package['url'])
print('---------------------------')
if __name__ == '__main__':
main()

1
requirements.txt Normal file
View File

@ -0,0 +1 @@
beautifulsoup4