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

data dict to list and write header then list

Browse Source
This commit is contained in:
yann 2024-11-12 19:17:30 +01:00
parent 9d7edf3e9a
commit 1adcf0b224
1 changed files with 6 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
phase1/main.py
View File

@ -39,30 +39,16 @@ def product_description(soup):
#create a dict with all information for writing loop later
# /!\ don't know if that's the best way
def get_data(soup, url):
info= {}
info = {
'product_page_url': url,
'universal_ product_code (upc)': product_information(soup)['UPC'],
'title': get_title(soup),
'price_including_tax': product_information(soup)['Price (incl. tax)'],
'price_excluding_tax': product_information(soup)['Price (excl. tax)'],
'number_available': product_information(soup)['Availability'],
'product_description': product_description(soup),
'category': "TODO",
'review_rating': product_information(soup)['Number of reviews'],
'image_url': 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']
with open('output.csv', 'w') as csv_file:
writer = csv.DictWriter(csv_file, fieldnames=fieldnames )
writer.writeheader()
for line in info:
writer.writerow(line)
with open(file, 'w') as csv_file:
writer = csv.writer(csv_file, delimiter=',')
writer.writerow(fieldnames)
writer.writerow(info)
@ -80,6 +66,7 @@ def main():
print(test['Availability'])
info=get_data(soup, url)
print(info)
data_output(info, 'output.csv')
if __name__ == "__main__":