guezoloic/millesima-ai-engine
1
0
Fork 0
mirror of https://github.com/guezoloic/millesima-ai-engine.git synced 2026-03-28 18:03:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'optimisation' into exo7

Browse Source
This commit is contained in:
Loïc GUEZO
2026-02-09 23:46:33 +01:00
parent 2bc5d57a31 5785d571b2
commit 9914e8af41
2 changed files with 127 additions and 61 deletions
Download Patch File Download Diff File Expand all files Collapse all files

56
main.py
View File

@@ -6,9 +6,8 @@ from json import loads
class _ScraperData:
def __init__(self, data: dict[str, object], scraper: Scraper | None = None) -> None:
def __init__(self, data: dict[str, object]) -> None:
self._data: dict[str, object] = data
self._scraper: Scraper | None = scraper
def _getcontent(self) -> dict[str, object] | None:
"""_summary_
@@ -42,23 +41,15 @@ class _ScraperData:
Returns:
str: _description_
"""
current_value: dict[str, object] | None = self._getattributes()
attrs: dict[str, object] | None = self._getattributes()
if current_value is None:
return None
if attrs is not None:
app_dict: object | None = attrs.get("appellation")
if isinstance(app_dict, dict):
return cast(str, app_dict.get("value"))
return None
app_dict: dict[str, object] = cast(
dict[str, object], current_value.get("appellation")
)
return cast(str, app_dict["value"])
def acceder(self, name: str) -> _ScraperData:
scraper: Scraper | None = self._scraper
if scraper is None:
scraper = Scraper()
return scraper.getjsondata(name)
def _getvin(self, name: str) -> str | None:
def _getcritiques(self, name: str) -> str | None:
"""_summary_
Args:
@@ -67,29 +58,30 @@ class _ScraperData:
Returns:
str | None: _description_
"""
current_value: dict[str, object] | None = self._getattributes()
if current_value is not None:
app_dict: dict[str, object] = cast(
dict[str, object], current_value.get(name)
)
if not app_dict:
return None
if current_value is None:
return None
val = cast(str, app_dict.get("value")).rstrip("+").split("-")
if len(val) > 1:
val[0] = str((int(val[0]) + int(val[1])) / 2)
app_dict: dict[str, object] = cast(
dict[str, object], current_value.get(name)
)
val: list[str] = cast(str, app_dict.get("attributes")).rstrip("+").split("-")
# dans le cas où 93-94 -> [93, 94] -> 93.5
if len(val) > 1:
val[0] = str((int(val[0]) + int(val[1])) / 2)
return val[0]
return val[0]
return None
def parker(self) -> str | None:
return self._getvin("note_rp")
return self._getcritiques("note_rp")
def robinson(self) -> str | None:
return self._getvin("note_jr")
return self._getcritiques("note_jr")
def suckling(self) -> str | None:
return self._getvin("note_js")
return self._getcritiques("note_js")
def getdata(self) -> dict[str, object]:
return self._data
@@ -228,5 +220,5 @@ class Scraper:
continue
raise ValueError(f"Clé manquante dans le JSON : {key}")
return _ScraperData(cast(dict[str, object], current_data), scraper=self)
return _ScraperData(cast(dict[str, object], current_data))

132
test_main.py
View File

@@ -10,7 +10,47 @@ def mock_site():
with Mocker() as m:
m.get(
"https://www.millesima.fr/",
text="<html><body><h1>MILLESIMA</h1></body></html>",
text=f"""
<html>
<body>
<script id="__NEXT_DATA__" type="application/json">
{dumps({
"props": {
"pageProps": {
"initialReduxState": {
"product": {
"content": {
"items": [],
"attributes": {}
}
}
}
}
}
})}
</script>
</body>
</html>
""",
)
m.get(
"https://www.millesima.fr/poubelle",
text=f"""
<html>
<body>
<h1>POUBELLE</h1>
<script id="__NEXT_DATA__" type="application/json">
{dumps({
"props": {
"pageProps": {
}
}
})}
</script>
</body>
</html>
""",
)
json_data = {
@@ -65,6 +105,18 @@ def mock_site():
}
],
"attributes": {
"equivbtl": {
"valueId": "1",
"name": "equivbtl",
"value": "1",
"isSpirit": False,
},
"nbunit": {
"valueId": "6",
"name": "nbunit",
"value": "6",
"isSpirit": False,
},
"appellation": {
"valueId": "433",
"name": "Appellation",
@@ -80,9 +132,9 @@ def mock_site():
"isSpirit": False,
},
"note_jr": {
"valueId": "17",
"valueId": "17+",
"name": "J. Robinson",
"value": "17",
"value": "17+",
"isSpirit": False,
},
"note_js": {
@@ -101,10 +153,12 @@ def mock_site():
html_product = f"""
<html>
<script id="__NEXT_DATA__" type="application/json">
{dumps(json_data)}
</script>
</body>
<body>
<h1>MILLESIMA</h1>
<script id="__NEXT_DATA__" type="application/json">
{dumps(json_data)}
</script>
</body>
</html>
"""
m.get(
@@ -122,31 +176,51 @@ def scraper() -> Scraper:
def test_soup(scraper: Scraper):
h1: Tag | None = scraper.getsoup("").find("h1")
assert isinstance(h1, Tag)
assert h1.text == "MILLESIMA"
# def test_getProductName(scraper: Scraper):
# jsondata = scraper.getjsondata("nino-negri-5-stelle-sfursat-2022.html")
# assert jsondata["productName"] == "Nino Negri : 5 Stelle Sfursat 2022"
# assert isinstance(jsondata["items"], list)
# assert len(jsondata["items"]) > 0
# assert jsondata["items"][0]["offerPrice"] == 390
vide = scraper.getsoup("")
poubelle = scraper.getsoup("poubelle")
contenu = scraper.getsoup("nino-negri-5-stelle-sfursat-2022.html")
assert vide.find("h1") is None
assert str(poubelle.find("h1")) == "<h1>POUBELLE</h1>"
assert str(contenu.find("h1")) == "<h1>MILLESIMA</h1>"
def test_appellation(scraper: Scraper):
appellation = scraper.getjsondata(
"nino-negri-5-stelle-sfursat-2022.html"
)
assert appellation.appellation() == "Sforzato di Valtellina"
vide = scraper.getjsondata("")
poubelle = scraper.getjsondata("poubelle")
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"
def test_fonctionprivee(scraper: Scraper):
vide = scraper.getjsondata("")
poubelle = scraper.getjsondata("poubelle")
contenu = scraper.getjsondata("nino-negri-5-stelle-sfursat-2022.html")
assert vide._getattributes() is not None
assert vide._getattributes() == {}
assert vide._getcontent() is not None
assert vide._getcontent() == {"items": [], "attributes": {}}
assert poubelle._getattributes() is None
assert poubelle._getcontent() is None
assert contenu._getcontent() is not None
assert contenu._getattributes() is not None
def test_critiques(scraper: Scraper):
critiques = scraper.getjsondata(
"nino-negri-5-stelle-sfursat-2022.html"
)
assert critiques.parker() == "91"
assert critiques.robinson() == "17"
assert critiques.suckling() == "93.5"
vide = scraper.getjsondata("")
poubelle = scraper.getjsondata("poubelle")
contenu = scraper.getjsondata("nino-negri-5-stelle-sfursat-2022.html")
assert vide.parker() is None
assert vide.robinson() is None
assert vide.suckling() is None
assert vide._getcritiques("test_ts") is None
assert poubelle.parker() is None
assert poubelle.robinson() is None
assert poubelle.suckling() is None
assert poubelle._getcritiques("test_ts") is None
assert contenu.parker() == "91"
assert contenu.robinson() == "17"
assert contenu.suckling() == "93.5"
assert contenu._getcritiques("test_ts") is None