dineline scraper 28-11

import urllib2
from bs4 import BeautifulSoup
import re


def extract_link(url):
    page = urllib2.urlopen(url)
    return BeautifulSoup(page, 'html.parser')


def dineline(link):
    page = urllib2.urlopen(link)
    page_text = page.read()
    new_text = re.sub('<br>', '', page_text)
    new_text = re.sub('</br>', '', new_text)
    soup = BeautifulSoup(new_text, 'html.parser')
    resto = soup.find_all('div', class_='ui segment brtop')
    # print resto[2]
    # resto name, time working fine...
    # rating is not...
    one_resto(soup, resto[5]) # index is the entry..


def one_resto(soup, resto):
    body = resto.find('div', class_='content')
    resto_block = body.find('a')
    name = resto_block.string # name of the restaurant
    link = resto_block.attrs[u'href']
    entity_id = resto_block.attrs[u'data-entity_id']

    rev_time = resto.find('time').attrs[u'datetime']

    review_block = resto.find('div', class_='act-body mbot0')
    review_block = review_block.find('div', class_='rev-text')
    class_name = 'left bold zdhl2 tooltip icon-font-level-5'
    # rating = float(review_block.find('div', class_=class_name).attrs[u'aria-label'].split()[-1])
    rev_text_block = review_block.find('div', class_='clear')
    review_text = rev_text_block.previous # actual review text

    print 'Restaurant: {}, Rating: , Review Date: {}, ' \
          '\n Review Text: {}'.format(name, rev_time, review_text)

def main():
    dineline(r"file:\\C:\\Users\\cereal_killer\\PycharmProjects\\zomato\\dl.html")


if __name__ == '__main__':
    main()