Scrap data from Canadian Academy of Periodontology (http://www.cap-acp.ca) and export in Excel file.

import pdb

from string import ascii_lowercase

import requests

import xlsxwriter

from bs4 import BeautifulSoup

row = 0

col = 0

workbook = xlsxwriter.Workbook('users_data.xlsx')

worksheet = workbook.add_worksheet()

worksheet.write(row, col, 'Name')

worksheet.write(row, col + 1, 'Address')

worksheet.write(row, col + 2, 'Country')

worksheet.write(row, col + 3, 'PinCode')

worksheet.write(row, col + 4, 'Phone Number')

worksheet.write(row, col + 5, 'Fax')

worksheet.write(row, col + 6, 'Email ID')

worksheet.write(row, col + 7, 'Web Site')

row += 1

for ascii_char in ascii_lowercase:

try:

page_link = 'http://www.cap-acp.ca/en/search/index.php?page=4&search=' + ascii_char

page_response = requests.get(

page_link, timeout=9999)

page_content = BeautifulSoup(page_response.content, "html.parser")

data = page_content.findAll('div', attrs={'class': 'main'})

for div in data:

links = div.findAll('a')

for a in links:

if a['href'] != 'index.php':

child_page_response = requests.get(

"http://www.cap-acp.ca" + a['href'], timeout=5555)

child_page_content = BeautifulSoup(

child_page_response.content, "html.parser")

new_data = child_page_content.findAll(

'div', attrs={'class': 'panel'})

new_data = new_data[0].text

user = new_data.split('\n')

name = user[2]

address = user[3]

country = user[4]

pin_code = user[5]

phone_number = user[6]

fax = ''

if 'Fax' in user[7]:

fax = user[7]

email = ''

if 'E-mail' in user[8]:

email = user[8]

website = ''

if 'Web site' in user[9]:

website = user[9]

worksheet.write(row, col, name)

worksheet.write(row, col + 1, address)

worksheet.write(row, col + 2, country)

worksheet.write(row, col + 3, pin_code)

worksheet.write(row, col + 4, phone_number)

worksheet.write(row, col + 5, fax)

worksheet.write(row, col + 6, email)

worksheet.write(row, col + 7, website)

row += 1

except:

pass

workbook.close()