guezoloic/archived-millesima-projetS6
1
0
Fork 0
mirror of https://github.com/guezoloic/millesima_projetS6.git synced 2026-03-28 19:13:42 +00:00
Code Issues Packages Projects Releases Wiki Activity

ajout(main.py): ajout dans csv

Browse Source
This commit is contained in:
Loïc GUEZO
2026-02-11 23:58:51 +01:00
parent 011bb6a689
commit dd430b9861
3 changed files with 24 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.gitignore vendored
View File

@@ -205,3 +205,5 @@ cython_debug/
marimo/_static/ marimo/_static/
marimo/_lsp/ marimo/_lsp/
__marimo__/ __marimo__/
*.csv

0
donnee.csv
View File

41
main.py
View File

@@ -299,31 +299,34 @@ class Scraper:
except JSONDecodeError | HTTPError: except JSONDecodeError | HTTPError:
return None return None
def getvins(self, subdir: str): def getvins(self, subdir: str, filename: str):
cache: set[str] = set[str]() cache: set[str] = set[str]()
page = 0 page = 0
while True: with open(filename, 'a') as f:
page += 1 while True:
products_list = self._geturlproductslist(f"{subdir}?page={page}") page += 1
products_list = self._geturlproductslist(f"{subdir}?page={page}")
print(f"---- {page} ----") print(f"---- {page} ----")
if not products_list: if not products_list:
break break
for product in products_list: for product in products_list:
if not isinstance(product, dict): if not isinstance(product, dict):
continue continue
link = product.get("seoKeyword") link = product.get("seoKeyword")
if link and link not in cache: if link and link not in cache:
try: try:
infos = self.getjsondata(link).informations() infos = self.getjsondata(link).informations()
print(infos) _ = f.write(infos + "\n")
cache.add(link) print(infos)
except JSONDecodeError | HTTPError as e: cache.add(link)
print(f"Erreur sur le produit {link}: {e}") except JSONDecodeError | HTTPError as e:
print(f"Erreur sur le produit {link}: {e}")
f.flush()
# Scraper().getvins("bordeaux.html") Scraper().getvins("bordeaux.html", "donnee.csv")