mirror of
https://github.com/guezoloic/millesima-ai-engine.git
synced 2026-03-28 18:03:47 +00:00
fix: correction et ajout de tests
This commit is contained in:
59
main.py
59
main.py
@@ -6,10 +6,11 @@ from json import loads
|
||||
|
||||
|
||||
class _ScraperData:
|
||||
def __init__(self, data: dict[str, object]) -> None:
|
||||
def __init__(self, data: dict[str, object], scraper: Scraper | None = None) -> None:
|
||||
self._data: dict[str, object] = data
|
||||
self._scraper: Scraper | None = scraper
|
||||
|
||||
def _getcontent(self) -> dict[str, object]:
|
||||
def _getcontent(self) -> dict[str, object] | None:
|
||||
"""_summary_
|
||||
|
||||
Returns:
|
||||
@@ -17,31 +18,39 @@ class _ScraperData:
|
||||
"""
|
||||
current_data: dict[str, object] = self._data
|
||||
for key in ["initialReduxState", "product", "content"]:
|
||||
current_data = cast(dict[str, object], current_data[key])
|
||||
new_data: object | None = current_data.get(key)
|
||||
if new_data is None:
|
||||
return None
|
||||
current_data: dict[str, object] = cast(dict[str, object], new_data)
|
||||
|
||||
return current_data
|
||||
|
||||
def _getattributes(self) -> dict[str, object]:
|
||||
def _getattributes(self) -> dict[str, object] | None:
|
||||
"""_summary_
|
||||
|
||||
Returns:
|
||||
dict[str, object]: _description_
|
||||
"""
|
||||
current_data: object = self._getcontent()["attributes"]
|
||||
return cast(dict[str, object], current_data)
|
||||
current_data: object = self._getcontent()
|
||||
if current_data is None:
|
||||
return None
|
||||
return cast(dict[str, object], current_data.get("attributes"))
|
||||
|
||||
def appellation(self) -> str:
|
||||
def appellation(self) -> str | None:
|
||||
"""_summary_
|
||||
|
||||
Returns:
|
||||
str: _description_
|
||||
"""
|
||||
current_value: dict[str, object] = self._getattributes()
|
||||
app_dict: dict[str, object] = cast(
|
||||
dict[str, object], current_value["appellation"]
|
||||
)
|
||||
return cast(str, app_dict["value"])
|
||||
attrs: dict[str, object] | None = self._getattributes()
|
||||
|
||||
def _getvin(self, name: str) -> str | 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
|
||||
|
||||
def _getcritiques(self, name: str) -> str | None:
|
||||
"""_summary_
|
||||
|
||||
Args:
|
||||
@@ -50,28 +59,30 @@ class _ScraperData:
|
||||
Returns:
|
||||
str | None: _description_
|
||||
"""
|
||||
current_value: dict[str, object] = self._getattributes()
|
||||
app_dict: dict[str, object] | None = cast(
|
||||
dict[str, object] | None, current_value.get(name)
|
||||
)
|
||||
|
||||
if app_dict is None:
|
||||
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
|
||||
|
||||
val: list[str] = cast(str, app_dict.get("attributes")).rstrip("+").split("-")
|
||||
# dans le cas où 93-94 -> [93, 94] -> 93.5
|
||||
val = cast(str, app_dict.get("value")).rstrip("+").split("-")
|
||||
if len(val) > 1:
|
||||
val[0] = str((int(val[0]) + int(val[1])) / 2)
|
||||
|
||||
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
|
||||
@@ -211,5 +222,3 @@ class Scraper:
|
||||
raise ValueError(f"Clé manquante dans le JSON : {key}")
|
||||
|
||||
return _ScraperData(cast(dict[str, object], current_data))
|
||||
|
||||
# print(Scraper().getjsondata("bordeaux.html?page=1").getdata())
|
||||
|
||||
114
test_main.py
114
test_main.py
@@ -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 = {
|
||||
@@ -80,16 +120,16 @@ def mock_site():
|
||||
"isSpirit": False,
|
||||
},
|
||||
"note_jr": {
|
||||
"valueId": "17",
|
||||
"valueId": "17+",
|
||||
"name": "J. Robinson",
|
||||
"value": "17",
|
||||
"value": "17+",
|
||||
"isSpirit": False,
|
||||
},
|
||||
"note_js": {
|
||||
"valueId": "93-94",
|
||||
"name": "J. Suckling",
|
||||
"value": "93-94",
|
||||
"isSpirit": False
|
||||
"isSpirit": False,
|
||||
},
|
||||
},
|
||||
}
|
||||
@@ -101,6 +141,8 @@ def mock_site():
|
||||
|
||||
html_product = f"""
|
||||
<html>
|
||||
<body>
|
||||
<h1>MILLESIMA</h1>
|
||||
<script id="__NEXT_DATA__" type="application/json">
|
||||
{dumps(json_data)}
|
||||
</script>
|
||||
@@ -122,30 +164,50 @@ 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
|
||||
|
||||
Reference in New Issue
Block a user