import requests
from bs4 import BeautifulSoup
import re
import datetime
import dateutil.parser as dparser
from docx import Document
import os
class analyssaita:
    def __init__(self):
        self.page = requests.get('https://www.pkmpei.ru/')
        self.soup = BeautifulSoup(self.page.text, 'html.parser')
    def timetable(self):
        data =[]
        self.timetable = dict()
        table = self.soup.find("table", { "class" : "form-grid thin-grid" })
        table_body = table.find('tbody')
        rows = table_body.find_all('tr')
        for row in rows:
            cols = row.find_all('td')
            cols = [ele.text.strip() for ele in cols]
            data.append([ele for ele in cols if ele])
        for i in range(len(data)):
            self.timetable[i] = data[i]
        for i in range(len(self.timetable)):
            for j in range(len(self.timetable[i])):
                if '\xa0' in self.timetable[i][j]:
                    self.timetable[i][j] = self.timetable[i][j].replace('\xa0', ' ')
                if '*' in self.timetable[i][j]:
                    self.timetable[i][j] = self.timetable[i][j].replace('*', '')
            self.timetable[i] = self.timetable[i][0] + ': ' + self.timetable[i][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 = self.soup.find_all(id="right_news_item")
        urls = []
        data = []
        text1 = []
        self.novosti = dict()
        for i in novosti:
            f = i.find('a')
            d = f.get_attribute_list('href')[0]
            urls.append('https://www.pkmpei.ru' + d)
        for i in urls:
            page = requests.get(i)
            soup = BeautifulSoup(page.text, 'html.parser')
            text = soup.find_all(class_= 'text')
            for i in text:
                data.append(i.find(class_= 'title3').text)
                text1.append(i.find('h1').text)
        for i in range(len(data)):
            self.novosti[data[i]] = 'НОВОСТИ:' + '\n' + data[i] + '\n' + text1[i] + '\n' + 'Ссылка: ' + urls[i]
        print(self.novosti)
t = analyssaita()
t.timetable()
t.adress()
t.contactniedannie()
t.novosti()