6 Commits

3 changed files with 176 additions and 22 deletions

2
.gitignore vendored
View File

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

80
main.py
View File

@@ -1,12 +1,19 @@
from typing import cast
from requests import Response, Session
from requests import HTTPError, Response, Session
from bs4 import BeautifulSoup, Tag
from collections import OrderedDict
from json import loads
from json import JSONDecodeError, loads
class _ScraperData:
"""_summary_
"""
def __init__(self, data: dict[str, object]) -> None:
"""_summary_
Args:
data (dict[str, object]): _description_
"""
self._data: dict[str, object] = data
def _getcontent(self) -> dict[str, object] | None:
@@ -55,7 +62,6 @@ class _ScraperData:
prix_calcule: float | None = None
for item in items:
if not isinstance(item, dict):
continue
@@ -114,7 +120,7 @@ class _ScraperData:
return None
val = cast(str, app_dict.get("value")).rstrip("+").split("-")
if len(val) > 1:
if len(val) > 1 and val[1] != "":
val[0] = str((int(val[0]) + int(val[1])) / 2)
return val[0]
@@ -146,7 +152,7 @@ class _ScraperData:
prix = self.prix()
except ValueError:
prix = None
return f"{appellation},{parker},{robinson},{suckling},{prix}"
@@ -285,3 +291,67 @@ class Scraper:
return _ScraperData(cast(dict[str, object], current_data))
def _geturlproductslist(self, subdir: str):
"""_summary_
Args:
subdir (str): _description_
Returns:
_type_: _description_
"""
try:
data: dict[str, object] = self.getjsondata(subdir).getdata()
for element in ["initialReduxState", "categ", "content"]:
data: dict[str, object] = cast(dict[str, object], data.get(element))
if not isinstance(data, dict):
return None
products: list[str] = cast(list[str], data.get("products"))
if isinstance(products, list):
return products
except (JSONDecodeError, HTTPError):
return None
def getvins(self, subdir: str, filename: str):
"""_summary_
Args:
subdir (str): _description_
filename (str): _description_
"""
with open(filename, "a") as f:
cache: set[str] = set[str]()
page = 0
while True:
page += 1
products_list = self._geturlproductslist(f"{subdir}?page={page}")
if not products_list:
break
products_list_length = len(products_list)
for i, product in enumerate(products_list):
if not isinstance(product, dict):
continue
link = product.get("seoKeyword")
if link and link not in cache:
try:
infos = self.getjsondata(link).informations()
_ = f.write(infos + "\n")
print(
f"page: {page} | {i + 1}/{products_list_length} {link}"
)
cache.add(link)
except (JSONDecodeError, HTTPError) as e:
print(f"Erreur sur le produit {link}: {e}")
f.flush()
if __name__ == "__main__":
Scraper().getvins("bordeaux.html", "donnee.csv")

View File

@@ -1,5 +1,5 @@
from json import dumps
from bs4 import Tag
from unittest.mock import patch, mock_open
import pytest
from requests_mock import Mocker
from main import Scraper
@@ -71,10 +71,10 @@ def mock_site():
"_id": "J4131/22/C/CC/6-11652",
"partnumber": "J4131/22/C/CC/6",
"taxRate": "H",
"listPrice": 390,
"offerPrice": 390,
"seoKeyword": "nino-negri-5-stelle-sfursat-2022-c-cc-6.html",
"shortdesc": "Un carton de 6 Bouteilles (75cl)",
"listPrice": 842,
"offerPrice": 842,
"seoKeyword": "vin-de-charazade1867.html",
"shortdesc": "Une bouteille du meilleur vin du monde?",
"attributes": {
"promotion_o_n": {
"valueId": "0",
@@ -101,9 +101,9 @@ def mock_site():
"isSpirit": False,
},
"nbunit": {
"valueId": "6",
"valueId": "1",
"name": "nbunit",
"value": "6",
"value": "1",
"isSpirit": False,
},
},
@@ -120,14 +120,14 @@ def mock_site():
"appellation": {
"valueId": "433",
"name": "Appellation",
"value": "Sforzato di Valtellina",
"url": "sforzato-di-valtellina.html",
"value": "Madame-Loïk",
"url": "Madame-loik.html",
"isSpirit": False,
"groupIdentifier": "appellation_433",
},
"note_rp": {
"valueId": "91",
"name": "Parker",
"name": "Peter Parker",
"value": "91",
"isSpirit": False,
},
@@ -139,7 +139,7 @@ def mock_site():
},
"note_js": {
"valueId": "93-94",
"name": "J. Suckling",
"name": "J. cherazade",
"value": "93-94",
"isSpirit": False,
},
@@ -166,6 +166,79 @@ def mock_site():
text=html_product,
)
html_product = f"""
<html>
<body>
<h1>MILLESIMA</h1>
<script id="__NEXT_DATA__" type="application/json">
{dumps(json_data)}
</script>
</body>
</html>
"""
list_pleine = f"""
<html>
<body>
<h1>LE WINE</h1>
<script id="__NEXT_DATA__" type="application/json">
{dumps({
"props": {
"pageProps": {
"initialReduxState": {
"categ": {
"content": {
"products": [
{"seoKeyword": "/nino-negri-5-stelle-sfursat-2022.html",},
{"seoKeyword": "/poubelle",},
{"seoKeyword": "/",}
]
}
}
}
}
}
}
)}
</script>
</body>
</html>
"""
list_vide = f"""
<html>
<body>
<h1>LE WINE</h1>
<script id="__NEXT_DATA__" type="application/json">
{dumps({
"props": {
"pageProps": {
"initialReduxState": {
"categ": {
"content": {
"products": [
]
}
}
}
}
}
}
)}
</script>
</body>
</html>
"""
m.get(
"https://www.millesima.fr/wine.html",
complete_qs=False,
response_list=[
{"text": list_pleine},
{"text": list_vide},
],
)
# on return m sans fermer le server qui simule la page
yield m
@@ -190,7 +263,7 @@ def test_appellation(scraper: Scraper):
contenu = scraper.getjsondata("nino-negri-5-stelle-sfursat-2022.html")
assert vide.appellation() is None
assert poubelle.appellation() is None
assert contenu.appellation() == "Sforzato di Valtellina"
assert contenu.appellation() == "Madame-Loïk"
def test_fonctionprivee(scraper: Scraper):
@@ -207,7 +280,6 @@ def test_fonctionprivee(scraper: Scraper):
assert contenu._getattributes() is not None
def test_critiques(scraper: Scraper):
vide = scraper.getjsondata("")
poubelle = scraper.getjsondata("poubelle")
@@ -232,13 +304,23 @@ def test_prix(scraper: Scraper):
contenu = scraper.getjsondata("nino-negri-5-stelle-sfursat-2022.html")
assert vide.prix() is None
assert poubelle.prix() is None
assert contenu.prix() == 65.0
assert contenu.prix() == 842.0
def test_informations(scraper: Scraper):
contenu = scraper.getjsondata("nino-negri-5-stelle-sfursat-2022.html")
assert contenu.informations() == "Sforzato di Valtellina,91,17,93.5,65.0"
assert contenu.informations() == "Madame-Loïk,91,17,93.5,842.0"
vide = scraper.getjsondata("")
poubelle = scraper.getjsondata("poubelle")
assert vide.informations() == "None,None,None,None,None"
assert poubelle.informations() == "None,None,None,None,None"
def test_search(scraper: Scraper):
m = mock_open()
with patch("builtins.open", m):
scraper.getvins("wine.html", "fake_file.csv")
assert m().write.called
all_writes = "".join(call.args[0] for call in m().write.call_args_list)
assert "Madame-Loïk,91,17,93.5,842.0" in all_writes