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

add text for fancy output and remove previous print (were testing)

Browse Source
This commit is contained in:
yann 2024-11-14 13:20:33 +01:00
parent 4247f1ac83
commit c35f7454a2
1 changed files with 6 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
phase2/main.py
View File

@ -52,7 +52,7 @@ def get_product_url_list(url_category_page, url):
def main():
# init
url = "https://books.toscrape.com/"
category = "fantasy"
category = "default"
# get functional variables
soup = get_html(url)
@ -64,17 +64,17 @@ def main():
# check if multiple page and get url list
url_list = check_for_pages(category_url)
print("Liste des URLs des pages: ", url_list)
# print("Liste des URLs des pages: ", url_list)
# get product list for each url_list, extend the main product url list with
product_url_list = []
for i in url_list:
product_url_list.extend(get_product_url_list(i, url))
# print("Liste des URL des produits: ", product_url_list)
# print("Longueur de la liste: ", len(product_url_list))
print("Nombre de livres: ", len(product_url_list))
# combine with phase 1 and write in csv for each url from product_url_list named with category
# combine with phase 1 and write in csv for each url from product_url_list named with category
data = []
for page_url in product_url_list:
page_soup = get_html(page_url)
@ -83,7 +83,8 @@ def main():
# print(phase1.get_data(page_soup, page_url))
data.append(phase1.get_data(page_soup, page_url))
phase1.data_output(data, category)
print("Done.\n Fichier " + phase1.data_output(data, category))
if __name__ == '__main__':
main()