import requests
from bs4 import BeautifulSoup
import re
import datetime
import dateutil.parser as dparser
class analyssaita:
    def __init__(self):
        self.page = requests.get('https://www.pkmpei.ru/')
        self.soup = BeautifulSoup(self.page.text, 'html.parser')
    def timetable(self):
        timetable1 = []
        timetable2 = []
        timetable3 = []
        timetable4 = []
        self.timetable = dict()
        s = ''
        l = 0
        timetable = str(self.soup.find(class_='title2'))
        timetable = re.split('; ', timetable)
        for i in timetable:
            if 'left' in i or 'center' in i:
                timetable1.append(i)
        for i in timetable1:
            if '<b>' in i:
                timetable2.append(i)
                timetable2 = re.split(';', str(timetable2))
                for i in timetable2:
                    if '"><b>' in i:
                        start = '"><b>'
                        end = '</b></td>\\n<td style="text-align: center'
                        i = i[i.find(start)+len(start):i.rfind(end)]
                        timetable3.append(i)
                for i in timetable2:
                    if '\\xa0' in i:
                        if 'Выходной' in i:
                            i = 'Выходной'
                        else:
                            i = re.findall('\d+', i)
                            for j in range(len(i) - 2):
                                if i[j] == '0':
                                    del i[j]
                                elif i[j] == '010':
                                    i[j] = '10'
                                elif i[-1] == '0':
                                    del i[-1]
                        i = ''.join(map(str, i))
                        timetable4.append(i)
                for i in range(len(timetable4)):
                    if timetable4[i] == '010001700':
                        timetable4[i] = '10:00 - 17:00'
                    elif timetable4[i] == '10001700':
                        timetable4[i] = '10:00 - 17:00'
                    elif timetable4[i] == '10001600':
                        timetable4[i] = '10:00 - 16:00'
        for i in range(len(timetable3)):
            self.timetable[l] = timetable3[i] + ': ' + timetable4[i]
            l = l +1
        print(self.timetable)
    def adress(self):
        adress = str(self.soup(class_="text"))
        start = 'Наш адрес'
        end = '/><br/><h1'
        adress = adress[adress.find(start)+len(start):adress.rfind(end)]
        start1 = '<div style="text-align: left;">'
        end1 = ', аудитория Б-209<br'
        adress1 = adress[adress.find(start1)+len(start1):adress.rfind(end1)]
        print(adress1)
        start2 = '<div style="text-align: left;">'
        end2 = '<br'
        self.adress2 = adress[adress.find(start2)+len(start2):adress.rfind(end2)]
        adress1 =adress1.replace(' ', '')
        self.adress1 = 'https://www.google.com/search?q=' + adress1
        print(self.adress1)
    def contactniedannie(self):
        contactniedannie = str(self.soup(class_="text"))
        start = 'Контактные данные'
        end = '</span><br/> </b></b>'
        start1 = '</h1> <br/> <b>'
        end1 = '<b><br/>'
        contactniedannie = contactniedannie[contactniedannie.find(start)+len(start):contactniedannie.rfind(end)] + 'JFKLDSJFLSD'
        self.telefon = contactniedannie[contactniedannie.find(start1)+len(start1):contactniedannie.rfind(end1)]
        print(self.telefon)
        start3 = '<span style="color: rgb(0, 0, 255);">'
        end3 = 'JFKLDSJFLSD'
        self.email = 'e-mail: ' + contactniedannie[contactniedannie.find(start3)+len(start3):contactniedannie.rfind(end3)]
        print(self.email)
    def novosti(self):
        novosti = str(self.soup.find_all(id="right_news_item"))
        novosti1 = []
        data = []
        data2 = []
        d = re.split(',', novosti)
        self.novosti = dict()
        urls = []
        news = []
        for i in d:
            if '<div id="right_news_item"' in i:
                novosti1.append(i)

        #print(novosti1)
        for i in range(len(novosti1)):
            start = 'href="'
            end ='">\n<div>'
            l = novosti1[i][novosti1[i].find(start)+len(start):novosti1[i].rfind(end)]
            url = 'https://www.pkmpei.ru/' + l
            urls.append(url)
        for i in urls:
            page = requests.get(i)
            soup = BeautifulSoup(page.text, 'html.parser')
            data1= str(soup.find(class_= 'title3'))
            start1 = '<div class="title3">'
            end1 = '</div>'
            data1 = data1[data1.find(start1)+len(start1):data1.rfind(end1)]
            data.append(data1)
            for i in data:
                if i not in data2:
                    data2.append(i)
            text = str(soup.find_all(class_= 'text'))
            start2 ='<h1>'
            end2 = '</h1>'
            text = text[text.find(start2)+len(start2):text.rfind(end2)]
            news.append(text)
            for i in range(len(news)):
                if '</h1>\n<br><h1>' in news[i]:
                    news[i] = news[i][news[i].find('<h1>'):]
                    news[i] = news[i][4:]
            for i in range(len(data2)):
                self.novosti[data2[i]] = 'НОВОСТИ:' + '\n' + data2[i] + '\n' + news[i] + '\n' + 'Ссылка: ' + urls[i]
            print(self.novosti)
t = analyssaita()
print(t.timetable())
print(t.adress())
print(t.contactniedannie())
print(t.novosti())