download source releases from samsung OSRC using a terminal

osrc_download.py

#!/usr/bin/env python3
# Copyright (c) 2017 Simon Shields
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in all
# copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.
#
# Before using this script, first run `pip install requests beautifulsoup4`
# or use your distro's package manager

import time
import requests
import os
from bs4 import BeautifulSoup

print("Note: by downloading anything from Samsung OSRC using this script, you agree to the terms laid out on this page: http://opensource.samsung.com/reception/receptionSub.do?method=modal")

try: # py3
    from urllib.parse import quote_plus
except ImportError: # py2
    from urllib import quote_plus

def bytes_to_human(b):
    units = ['B', 'kB', 'MB', 'GB', 'TB']
    uidx = 0
    while b > 2048:
        b = float(b) / 1024.0
        uidx += 1

    return '%.02f %s'%(b, units[uidx])

def seconds_to_human(b):
    sec = b % 60
    b = b // 60
    mts = b % 60
    b = b // 60
    if b > 0:
        return '%dh %02dm %02ds'%(b, mts, sec)
    elif mts > 0:
        return '%02dm %02ds'%(mts, sec)
    else:
        return '%02ds'%sec

SEARCH_URL = 'http://opensource.samsung.com/reception/receptionSub.do?method=search&searchValue=%s'
CSRF_URL = 'http://opensource.samsung.com/reception/receptionSub.do?method=modal'
DOWNLOAD_URL = 'http://opensource.samsung.com/reception/receptionSub.do?method=downLoad'
# to download
# get files matching query
session = requests.Session()
session.headers.update({'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:55.0) Gecko/20100101 Firefox/55.0'})


query = input('Enter search query: ')
res = session.get(SEARCH_URL % quote_plus(query))

soup = BeautifulSoup(res.text, 'html.parser')
rows = soup.find_all('table', class_='bT')[0].find_all('tr')[1:] # first row is table header

i = 0
fmt = '%15s | %14s | %s'
print(('[%2s] ' + fmt) %('id', 'model', 'version', 'filename'))
post_data = {}
for row in rows:
    cells = row.find_all('td')
    print(('[%02d] ' + fmt)%(i, cells[1].text.strip(), cells[2].text.strip(), cells[3].text.strip()))
    post_data[i] = {
            'attach_id': row.find_all(id='s_attach_id_%d'%i)[0].get('value'),
            'down_purpose': 'EVU',
            'down_purpose_memo': '',
            'searchValue': query,
            'page': '1',
            'countPerPage': '15',
            'countPerBlock': '15',
    }
    i += 1
if i == 0:
    raise "No results!"
choice = int(input('Which one to download? [0-%d] '%(i-1)))
if choice >= i:
    raise "Invalid choice"

data = post_data[choice]
res = session.get(CSRF_URL)

soup = BeautifulSoup(res.text, 'html.parser')
data['_csrf'] = soup.find_all(id='_csrf')[0].get('value')
data['returnValue'] = 'Y,EVU,,' + data['_csrf']
resp = session.post(DOWNLOAD_URL, data=data, stream=True)
print(resp.status_code)
print(resp.headers)
if not resp.headers['Content-Type'].startswith('application/octet-stream'):
    print('Error: non-zip response from OSRC, aborting')
    raise Exception()

dlen = int(resp.headers['Content-Length'])
filename = resp.headers['Content-Disposition'].split('=')[1][:-1]
if os.path.exists(filename):
    i = 1
    while os.path.exists(filename + '.' +  str(i)):
        i += 1
    filename += '.' + str(i)

print('Downloading %s to %s'%(bytes_to_human(dlen), filename))

progress = 0
start = int(time.time()) - 1
with open(filename, mode='wb') as f:
    for chunk in resp.iter_content(chunk_size=512 * 1024):
        f.write(chunk)
        progress += len(chunk)
        delta = int(time.time()) - start
        speed = progress/delta
        if speed > 0:
            eta = seconds_to_human((dlen-progress) / speed)
        else:
            eta = 'No ETA'
        print('Downloading %s - %s/%s, %s/s, ETA %s'%(
            filename,
            bytes_to_human(progress),
            bytes_to_human(dlen),
            bytes_to_human(speed),
            eta), end='       \r')