Yann/Projet2
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

remove url_base, refactor list get_data, fix comment and PEP8

Browse Source
This commit is contained in:
yann 2024-11-13 11:03:25 +01:00
parent 1adcf0b224
commit 3a6cf9b87e
1 changed files with 31 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
phase1/main.py
View File

@ -36,15 +36,34 @@ def product_description(soup):
desc = soup.find("p", class_='').string
return desc
#create a dict with all information for writing loop later
#create a list with all information consecutively
# /!\ don't know if that's the best way
def get_data(soup, url):
info = [url, product_information(soup)['UPC'], get_title(soup), product_information(soup)['Price (incl. tax)'], product_information(soup)['Price (excl. tax)'], product_information(soup)['Availability'], product_description(soup), "TODO", product_information(soup)['Number of reviews'], get_image_url(soup, url)]
info = [url, product_information(soup)['UPC'],
get_title(soup),
product_information(soup)['Price (incl. tax)'],
product_information(soup)['Price (excl. tax)'],
product_information(soup)['Availability'],
product_description(soup),
"TODO",
product_information(soup)['Number of reviews'],
get_image_url(soup, url)
]
return info
#write the file
def data_output(info, file):
fieldnames = ['product_page_url', 'universal_ product_code (upc)', 'title', 'price_including_tax', 'price_excluding_tax', 'number_available', 'product_description', 'category', 'review_rating', 'image_url']
fieldnames = ['product_page_url',
'universal_ product_code (upc)',
'title',
'price_including_tax',
'price_excluding_tax',
'number_available',
'product_description',
'category',
'review_rating',
'image_url']
with open(file, 'w') as csv_file:
writer = csv.writer(csv_file, delimiter = ',')
writer.writerow(fieldnames)
@ -57,7 +76,7 @@ def data_output(info, file):
def main():
url_site="https://books.toscrape.com"
url = "https://books.toscrape.com/catalogue/set-me-free_988/index.html"
html = extract_web(url)