filesfm-i18n/filesfm.py

from sys import version_info
from bs4 import BeautifulSoup
from urllib.parse import urlparse, unquote, urlencode
import shutil, cgi, os, urllib.request, argparse, sys, re, json, gettext
gettext.install('messages', localedir='po')

#global variables
base_folder = 'fmloader/'
version = '0.0.5'
#end global variables

#declarative jumbo
try:
	assert version_info >= (3,6)
except:
	print(_("you must have python 3.6 or higher installed\nthe script was intended to run on 3.6 or higher and won't account for python2 at all as well!"))
	sys.exit()
#end declarative jumbo

def check_folder(folder):
	try:
		os.mkdir(folder)
	except FileExistsError:
		pass #¯\_(ツ)_/¯

def _declare_opener(additional_header=None): #do not touch, it works as is, not that it needs better user-agents >.>
	opener = urllib.request.build_opener()
	if additional_header is None:
		opener.addheaders = [('User-agent', 'Mozilla/5.0 (Windows NT 10.0; WOW64; rv:55.0) Gecko/20100101 Firefox/55.0')]
	else:
		opener.addheaders = [('User-agent', 'Mozilla/5.0 (Windows NT 10.0; WOW64; rv:55.0) Gecko/20100101 Firefox/55.0')] + additional_header
	urllib.request.install_opener(opener)

def _download_file(link, file_link, additional_header=None, additional_fold=''): #original file link for the referrer, file_link is actual download link
	try:
		if additional_header is not None:
			_declare_opener([('Referer', link),additional_header])
		else:
			_declare_opener([('Referer', link),])
		with urllib.request.urlopen(file_link) as response:
			folder = base_folder+additional_fold
			Buffy = folder.split('/')
			buf = ''
			for i in range(len(Buffy)-1):
				buf += Buffy[i] + '/'
				check_folder(buf)
			try:
				_, params = cgi.parse_header(response.headers.get('Content-Disposition', ''))
				print('Downloading file '+params['filename']+'...')
				out_file = open(folder+params['filename'], 'wb')
			except KeyError:
				filename = unquote(os.path.basename(urlparse(file_link).path))
				print('Downloading file '+filename+'...')
				out_file = open(folder+filename, 'wb')
			shutil.copyfileobj(response, out_file)
	except ValueError:
		raise ValueError
		print(_('Something\'s wrong with the link download routine'))
		return -1
	else:
		print(_('Done!'))
		return 0

def __zippyshare(parsed,baseurl):
	try:
		result = parsed.find('div', class_='right').find('script').string.split(' ')[6:17]

		for i in range(len(result)): result[i] = result[i].replace('(','').replace(')','').replace('\"','').replace(';','').replace('\n','')

		href = result[0] + str( (int(result[2]) % int(result[4])) + (int(result[6]) % int(result[8])) ) + result[10]
		return [1,'http://' + baseurl +  href]
	except:
		return [0,'']
def __filesfm_folder(parsed, link):
	file_array = []
	counter = 1
	for i in parsed.find_all('div', class_='file'):
		file_array.append([i.get('title').strip().split('<br/>'),i.find('div', class_='item_name').get('onclick').replace('\'',"")[16:]])
		print(str(counter)+' - '+file_array[-1][0][0]+' -- '+file_array[-1][0][1][:-1])
		counter = counter+1
	return file_array

def __filesfm_file(parsed):
	result = [0,'']
	try:
		result[1] = (parsed.find('div', class_='drop-down-options').find('a').get('href'))
	except:
		#print(_("Required div element not found or incorrect site"))
		return result
	if result[1].startswith('//'):
		if args.interactive:
			result[0] = 2
		else:
			result = [1,str('https://'+result[1][2:])]
	elif result[1].startswith('/d'):
		result = [1,str('https://files.fm'+result[1])]
	return result

def get_json(link, post=None):
	if post is not None:
		data = urlencode(post)
		data = bytearray(data, 'utf-8')

		req = urllib.request.Request(link,data)
		request = urllib.request.urlopen(req)
	else:
		request = urllib.request.urlopen(link)
	return json.loads(request.read().decode('utf-8'))

def __mediafire_crawler(folder_key, folder, link):
	folder_folders = get_json('https://www.mediafire.com/api/1.4/folder/get_content.php?r=mgsp&content_type=folders&filter=all&order_by=name&order_direction=asc&chunk=1&version=1.5&folder_key='+folder_key+'&response_format=json')
	folder_files = get_json('https://www.mediafire.com/api/1.4/folder/get_content.php?r=plqv&content_type=files&filter=all&order_by=name&order_direction=asc&chunk=1&version=1.5&folder_key='+folder_key+'&response_format=json')

	folders = folder_folders['response']['folder_content']['folders']
	files = folder_files['response']['folder_content']['files']

	buf = []
	if folders is not None:
		for i in folders:
			buf += __mediafire_crawler(i['folderkey'],folder+i['name']+'/', link)
	for i in files:
		file = __mediafire_file(url2bs(i['links']['normal_download']),i['links']['normal_download'])[1]
		buf.append([i['filename'],file,folder])
		_download_file(link, file, additional_fold=folder)
	return buf

def __mediafire_folder(parsed, link):
	folder_key = link[link.find('folder')+7:link.rfind('/')]

	_declare_opener([('Referer', link),('Content-Type','application/json')])
	folder_info = get_json('https://www.mediafire.com/api/1.4/folder/get_info.php',(('folder_key', folder_key), ('response_format', 'json'), ('recursive','yes')))
	__mediafire_crawler(folder_key, folder_info['response']['folder_info']['name']+'/',link)
	return 0

def __mediafire_file(parsed, link):
	if link.find('folder') != -1:
		return [2,'']

	result = (parsed.find('div',class_='download_link').find('script'))
	regex = r"http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+"
	result = re.findall(regex, result.string)

	if len(result) == 1:
		return [1,result[0]]
	else:
		return [0,'']

def _parse_files(parsed, link, __func_host): #this function is intended for folders only, but it may work for single files as well
	file_array = __func_host(parsed, link) #['filename','directurl']
	input_invalid = True
	if args.interactive:
		while input_invalid:
			user_input = input('\n' + _('Select your desired files by their indexes, comma separated (ex. 1,3,4): '))
			try:
				user_input = user_input.replace(' ',"").split(',')
				for i in range(len(user_input)):
					user_input[i] = int(user_input[i])-1
			except:
				print('Your input was invalid, try again')
			else:
				input_invalid = False

		for i in user_input:
			try:
				pull = file_array[i][1]
			except:
				print(_('Errored index, continuing...'))
				continue
			_download_file(link,pull)
	elif file_array == 0:
		return 0
	else:
		for i in file_array:
			_download_file(link, i[1])

def url2bs(link): #simple, feed a link, poop a beautifulsoup object
	try:
		parsed = urllib.request.urlopen(link)
		parsed_bs = BeautifulSoup(parsed.read().decode('utf-8'), 'html.parser')
	except ValueError:
		print(_("Incorrect URL typed in, please copy and paste the link from the browser bar if possible! (recommended formatting: https://files.fm/u/{FILEID} )"))
		return -1
	else:
		return parsed_bs

def parse_link(link): #core function, if you'll ever intend to import it obv. feed it with a files.fm link
	check_folder(base_folder)
	_declare_opener()
	parsed = url2bs(link)

	try:
		url = urlparse(link)
	except:
		raise ValueError

	if url.netloc.endswith('files.fm'): result = __filesfm_file(parsed); __func_host = __filesm_folder
	elif url.netloc.endswith('.zippyshare.com'): result = __zippyshare(parsed, url.netloc)
	elif url.netloc.endswith('.mediafire.com'): result = __mediafire_file(parsed, link); __func_host = __mediafire_folder
	else: print('wrong url'); return -1

	if result[0] == 0: print('url could not be retrieved'); return -1
	elif result[0] == 1:
		if len(result) == 3: return _download_file(link,result[1], headers)
		else: return _download_file(link,result[1])
	elif result[0] == 2: return _parse_files(parsed, link, __func_host)
	else: print(_('this should not happen')); return -1

if __name__ == '__main__':
	parser = argparse.ArgumentParser(description=_('FilesFM python file&folder downloader'))
	parser.add_argument('--interactive','-i', action='store_true', help=_('Enables prompts done during the download\nEnable this to activate partial folder downloads'))
	parser.add_argument('urls', help=_('links to filehosts'), nargs='*', type=str)
	args = parser.parse_args()
	if len(sys.argv) > 1:
		for i in args.urls:
			parse_link(i)
	else:
		parser.print_help()
		sys.exit(1)