themify_scrapper.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-

"""
themify_downloader.py
Copyright (C) 2018 Dhaval Savalia <[email protected]>
All rights reserved.
"""

"""
NOTICE:
All content that you download through this script is owned by Themify.me (https://themify.me)
and you need to have active membership on their website.
This script is developed ONLY for educational and NON-commercial purposes only.
I DO NOT take any responsibility if you use this script to something illegal.
"""

"""
Themify.me (https://themify.me)
All Themify products are licensed under the GNU General Public License.
You may modify and use the themes on unlimited number of websites.
"""


import requests
from bs4 import BeautifulSoup
import sys
import getpass

url = 'https://themify.me/member/member'

def create_session(url, username, password):
    """
    Create session at Themify with cookie.

    @param string url
    @param string username
    @param string password
    @return object
    """

    ## Start session
    s = requests.Session()

    ## Make a request to url to generate a fresh cookie for us
    s.get(url)

    ## Send POST data payload containing username and password
    s.post(url, data={'amember_login': username, 'amember_pass': password})

    ## Return `s` object that is authenticated at Themify.me
    return s


## Get username and password from user
username = input("Please enter you themify username: ")
password = getpass.getpass("Please enter your themify password: ")


## Created the session
current_session = create_session(url, username, password)

## Get the HTTP page
page = current_session.get(url)

## Turn that page into bs4 object
soup = BeautifulSoup(page.content, 'html.parser')

## Get all `a` tags
all_li = soup.find_all('a')

## This is where all the links will be stored
all_links = []

## Ask user if they want text file containing all the links
store_in_txt = input("Do you want to store all the links in txt(y/n)? ")

## If yes, open/create new `links.txt` file
if (store_in_txt == 'y') or (store_in_txt == 'Y'):
    f = open('links.txt', 'w+')

## Append link containing only `zip` in them, so we get what we want
for new_link in all_li:
    if 'zip' in new_link['href']:
        all_links.append(new_link['href'])
    if (store_in_txt == 'y') or (store_in_txt == 'Y'):
        f.write('{}\n'.format(new_link['href']))

## Kindly close the file
if (store_in_txt == 'y') or (store_in_txt == 'Y'):
    f.close()


## Finally download files!
for link in all_links:
    r = current_session.get(link)
    open('{}'.format(link.split('/')[-1]), 'wb').write(r.content)