lakshay-arora

%%time
data['Number_of_divisor'] = data.Number.apply(countDivisors)

lakshay-arora

%%time

pool = mp.Pool(processes = (mp.cpu_count() - 1))
answer = pool.map(countDivisors,random_data)
pool.close()
pool.join()

lakshay-arora

"""
Web Scraping - Beautiful Soup
"""

# importing required libraries
import requests
from bs4 import BeautifulSoup
import pandas as pd

# target URL to scrap

lakshay-arora

# find all the sections with specifiedd class name
cards_data = data.find_all('div', attrs={'class', 'width100 fl htlListSeo hotel-tile-srp-container hotel-tile-srp-container-template new-htl-design-tile-main-block'})

# total number of cards
print('Total Number of Cards Found : ', len(cards_data))

# source code of hotel cards
for card in cards_data:
    print(card)

lakshay-arora

# extract the hotel name and price per room
for card in cards_data:

    # get the hotel name
    hotel_name = card.find('p')

    # get the room price
    room_price = card.find('li', attrs={'class': 'htl-tile-discount-prc'})
    print(hotel_name.text, room_price.text)

lakshay-arora

# create a list to store the data
scraped_data = []

for card in cards_data:

    # initialize the dictionary
    card_details = {}

    # get the hotel name
    hotel_name = card.find('p')

lakshay-arora

"""
Web Scraping - Scrap Images
"""

# importing required libraries
import requests
from bs4 import BeautifulSoup

# target URL
url = "https://www.goibibo.com/hotels/hotels-in-shimla-ct/"

lakshay-arora

# select src tag
image_src = [x['src'] for x in images]

# select only jp format images
image_src = [x for x in image_src if x.endswith('.jpg')]

for image in image_src:
    print(image)

lakshay-arora

image_count = 1
for image in image_src:
    with open('image_'+str(image_count)+'.jpg', 'wb') as f:
        res = requests.get(image)
        f.write(res.content)
    image_count = image_count+1

lakshay-arora

# create a sample list
my_list = [i for i in range(1,10000000)]

# parallelize the data
rdd_0 = sc.parallelize(my_list,3)

rdd_0