def extract_product(self):
next_page = "https://www.ceneo.pl/{}#tab=reviews".format(
self.product_id)
while next_page:
respons = requests.get(next_page)
page_dom = BeautifulSoup(respons.text, "html.parser")
opinions = page_dom.select("div.js_product-review")
for opinion in opinions:
self.opinions.append(
Opinion().extract_opinion(opinion).transform_opinion())
try:
next_page = "https://www.ceneo.pl" + \
page_dom.select("a.pagination__next").pop()["href"]
except IndexError:
next_page = None
print(next_page)
if self.product_name == None:
try:
self.product_name = page_dom.find(
"h1",
class_=
"product-top__product-info__name long-name js_product-h1-link js_product-force-scroll js_searchInGoogleTooltip default-cursor"
).text[1:]
except AttributeError:
self.product_name = "none"
if self.product_name == "none":
try:
self.product_name = page_dom.find(
"h1",
class_=
"product-top__product-info__name js_product-h1-link js_product-force-scroll js_searchInGoogleTooltip default-cursor"
).text[1:]
except AttributeError:
self.product_name = "none"
def importProduct(self):
with open(f"app/products/{self.productId}.json", "r",
encoding="UTF-8") as f:
product = json.load(f)
self.productName = product['productName']
opinions = product['opinions']
for opinion in opinions:
self.opinions.append(Opinion(**opinion))
def read_from_json(self):
print(self.product_id)
with open(f"app/products/{self.product_id}.json", "r", encoding="UTF-8") as fp:
prod = json.load(fp)
fp.close()
self.product_name = prod['product_name']
opinions = prod['opinions']
for opinion in opinions:
self.opinions.append(Opinion(**opinion))
def extract_product(self):
next_page = "https://www.ceneo.pl/{}#tab=reviews".format(
self.product_id)
while next_page:
respons = requests.get(next_page)
page_dom = BeautifulSoup(respons.text, "html.parser")
opinions = page_dom.select("div.js_product-review")
for opinion in opinions:
self.opinions.append(
Opinion().extract_opinion(opinion).transform_opinion())
try:
next_page = "https://www.ceneo.pl" + \
page_dom.select("a.pagination__next").pop()["href"]
except IndexError:
next_page = None
print(next_page)
def extractProduct(self):
respons = requests.get("https://www.ceneo.pl/{}#tab=reviews".format(
self.productId))
page = 2
while respons:
pageDOM = BeautifulSoup(respons.text, 'html.parser')
opinions = pageDOM.select("div.js_product-review")
for opinion in opinions:
self.opinions.append(
Opinion().extractOpinion(opinion).transformOpinion())
respons = requests.get(
"https://www.ceneo.pl/{}/opinie-".format(self.productId) +
str(page),
allow_redirects=False)
if respons.status_code == 200:
page += 1
else:
break