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

refactor output counters

Browse Source
This commit is contained in:
yann 2024-11-14 14:16:36 +01:00
parent ebd5f5acd4
commit b34a5d123c
1 changed files with 11 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
phase3/main.py
View File

@ -140,16 +140,19 @@ def main():
soup = get_html(url)
# init counters
total_category = len(get_category_list(soup, url))
total_books = int(soup.form.strong.text)
processed_books = 0
print(total_books, " à traiter répartis en ", total_category, " catégories.\nGo.")
# go ahead for each category
for line in get_category_list(soup, url):
category = line[0]
category_url = line[1]
total_category -= 1
# display what category is processed
print("\n Traitement de la catégorie : " + category)
print("\n -> Traitement de la catégorie : " + category)
# check if multiple pages and create a URL list
url_list = check_for_pages(category_url)
@ -159,7 +162,7 @@ def main():
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("Nombre de livres: ", len(product_url_list))
print(len(product_url_list), " livres présents")
processed_books += len(product_url_list)
# combine with phase 1 and write in csv for each url from product_url_list named with category
@ -171,9 +174,12 @@ def main():
# print(phase1.get_data(page_soup, page_url))
data.append(get_data(page_soup, page_url))
print("Done.\n Fichier " + data_output(data, category))
print("Nombre total de livres traités : ", processed_books)
print("Livres restants à traiter : ", total_books - processed_books)
print(processed_books, " livres traités")
print(total_books - processed_books, " livres restants")
print(total_category, " catégories restantes")
print("Done.\n Fichier " + data_output(data, category))
print("\n Traitement terminé.")