import urllib.request
from bs4 import BeautifulSoup
from datetime import datetime

prefix = "https://www.ceneo.pl/"
postfix = "/opinie-"
product_id = "45498942"
page_num = 1

url = prefix+product_id+postfix+str(page_num)

#pobranie zawartosci strony
site = urllib.request.urlopen(url)
page = site.read()

page_tree = BeautifulSoup(page, 'html.parser')

opinions_num = int(page_tree.find("span", attrs={"itemprop": "reviewCount"}).string)
print(opinions_num)


#parsowanie kodu strony
# opinions = page_tree.find_all("li" , attrs={ "class": "review-box"})
opinions = page_tree.select("li.review-box")

for opinion in opinions:


    id = int(opinion["data-entry-id"])

    author = (opinion.select("div.reviewer-name-line")).pop().stringa
    try:
        recomendation = (opinion.select("div.product-review-summary > em")).pop().string
    except IndexError:
        recomendation = "BRAK"

    stars =  (opinion.select("span.review-score-count")).pop().string
    content = (opinion.select("p.product-review-body")).pop().get_text()
    useful = (opinion.select("[id^=votes-yes]")).pop().string
    unuseful = (opinion.select("[id^=votes-no]")).pop().string
    time = opinion.select("div > span.review-time > time")

    add_date = datetime.strptime(time.pop()["datetime"], "%Y-%m-%d %H:%M:%S")

    if time:
        purchase_date = datetime.strptime(time.pop()["datetime"], "%Y-%m-%d %H:%M:%S")
    else:
        purchase_date = None

    adavnatges = (opinion.select("div.cons-cell > ul")).pop().get_text()

    print(adavnatges)
    #print(author, id, recomendation, stars, content, useful, unuseful, end="\n")