Playlist interactive

acfun.py

@@ -33,7 +33,8 @@ def acfun_download_by_id(id, title, merge=True):
 	with open(title + '.json', 'w') as x:
 		x.write(srt)
 
-def acfun_download(url, merge=True):
+def acfun_download(url, config):
+	merge = config["merge"]
 	assert re.match(r'http://www.acfun.tv/v/ac(\d+)', url)
 	html = get_html(url).decode('utf-8')
 

bilibili.py

@@ -32,7 +32,7 @@ def parse_srt_p(p):
 	# pool 0: normal
 	# pool 1: srt
 	# pool 2: special?
-	
+
 	font_size = int(font_size)
 
 	font_color = '#%06x' % int(font_color)
@@ -61,7 +61,8 @@ def bilibili_download_by_cid(id, title, merge=True):
 	else:
 		raise NotImplementedError(urls[0])
 
-def bilibili_download(url, merge=True):
+def bilibili_download(url, config):
+	merge = config["merge"]
 	assert re.match(r'http://(www.bilibili.tv|bilibili.kankanews.com|bilibili.smgbb.cn)/video/av(\d+)', url)
 	html = get_html(url)
 

cntv.py

@@ -19,7 +19,8 @@ def cntv_download_by_id(id, title=None, output_dir='.', merge=True):
 	assert ext in ('flv', 'mp4')
 	download_urls(urls, title, str(ext), total_size=None, merge=merge)
 
-def cntv_download(url, merge=True):
+def cntv_download(url, config):
+	merge = config["merge"]
 	if re.match(r'http://\w+\.cntv\.cn/(\w+/\w+/(classpage/video/)?)?\d+/\d+\.shtml', url):
 		id = r1(r'<!--repaste.video.code.begin-->(\w+)<!--repaste.video.code.end-->', get_html(url))
 	elif re.match(r'http://xiyou.cntv.cn/v-[\w-]+\.html', url):

common.py

@@ -111,6 +111,72 @@ def url_size(url):
 def urls_size(urls):
 	return sum(map(url_size, urls))
 
+def select_playlist_info(alist):
+	"""Interactive select items from a list of {} with key "title" in it."""
+	result = set({})
+	alen = len(alist)
+	while True:
+		print("\nAvailable vidoes:")
+		for i, vid_info in enumerate(alist):
+			tag = " "
+			if i in result:
+				tag = "*"
+			print "%s%d) %s" % (tag, i+1, vid_info["title"])
+		print("Total: %d" % alen)
+		resp = raw_input("video numbers (h = HELP): ")
+		resp = resp.strip().strip(",").lower()
+		if len(resp) <= 0:
+			continue
+		elif resp in {"?", "h", "help"}:
+			print('=============== HELP ====================')
+			print('Select number and press <Enter>.')
+			print('Seperate numbers by ","; use range like: 3-5.')
+			print('Example: 1,3-5,8')
+			print('a = all; n = none; q = finish; h = help')
+			print('============= HELP END ==================')
+			raw_input("Press <Enter> to continue...")
+			continue
+		elif resp in {"a", "all"}:
+			result = set(range(alen))
+			continue
+		elif resp in {"n", "none"}:
+			result = set()
+			continue
+		elif resp in {"q", "quit", "finish", "exit", "bye"}:
+			break
+
+		resp = [x.strip() for x in resp.split(",")]
+		try:
+			ranges = []
+			for item in resp:
+				# also do range as 3-5
+				start, _, end = item.partition("-")
+				start = int(start.strip())
+				if end:
+					end = int(end.strip())
+				else:
+					end = start
+
+				ranges.append((start, end))
+
+			for start, end in ranges:
+				# user input count start from 1
+				for i in range(start - 1, end):
+					if i >= alen:
+						continue
+					if i in result:
+						result.remove(i)
+					else:
+						result.add(i)
+		except ValueError:
+			pass
+
+	ret = []
+	for i in range(len(alist)):
+		if i in result:
+			ret.append(alist[i])
+	return ret
+
 class SimpleProgressBar:
 	def __init__(self, total_size, total_pieces=1):
 		self.displayed = False
@@ -247,9 +313,9 @@ def f(*args, **kwargs):
 
 def script_main(script_name, download, download_playlist=None):
 	if download_playlist:
-		help = 'python %s.py [--playlist] [-c|--create-dir] [--no-merge] url ...' % script_name
-		short_opts = 'hc'
-		opts = ['help', 'playlist', 'create-dir', 'no-merge']
+		help = 'python %s.py [--playlist] [-c|--create-dir] [--no-merge] [-i|--interactive] url ...' % script_name
+		short_opts = 'hci'
+		opts = ['help', 'playlist', 'create-dir', 'no-merge', 'interactive']
 	else:
 		help = 'python [--no-merge] %s.py url ...' % script_name
 		short_opts = 'h'
@@ -261,6 +327,9 @@ def script_main(script_name, download, download_playlist=None):
 		print help
 		sys.exit(1)
 	playlist = False
+
+	config = {}
+	config["interactive"] = False
 	create_dir = False
 	merge = True
 	for o, a in opts:
@@ -273,16 +342,20 @@ def script_main(script_name, download, download_playlist=None):
 			create_dir = True
 		elif o in ('--no-merge'):
 			merge = False
+		elif o in ('-i', '--interactive'):
+			config["interactive"] = True
 		else:
 			print help
 			sys.exit(1)
 	if not args:
 		print help
 		sys.exit(1)
 
+	config["create_dir"] = create_dir
+	config["merge"] = merge
 	for url in args:
 		if playlist:
-			download_playlist(url, create_dir=create_dir, merge=merge)
+			download_playlist(url, config=config)
 		else:
-			download(url, merge=merge)
+			download(url, config=config)
 

iask.py

@@ -18,7 +18,8 @@ def iask_download_by_id(id, title=None, merge=True):
 	assert title
 	download_urls(urls, title, 'flv', total_size=None, merge=merge)
 
-def iask_download(url, merge=True):
+def iask_download(url, config):
+	merge = config["merge"]
 	id = r1(r'vid:(\d+),', get_html(url))
 	iask_download_by_id(id, merge=merge)
 

ifeng.py

@@ -17,7 +17,8 @@ def ifeng_download_by_id(id, title=None, merge=True):
 	assert url.endswith('.mp4')
 	download_urls([url], title, 'mp4', total_size=None, merge=merge)
 
-def ifeng_download(url, merge=True):
+def ifeng_download(url, config):
+	merge = config["merge"]
 	id = r1(r'/([0-9a-f]{8}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{12})\.shtml$', url)
 	if id:
 		return ifeng_download_by_id(id)

iqiyi.py

@@ -10,7 +10,8 @@ def real_url(url):
 	import json
 	return json.loads(get_html(url[:-3]+'hml?v='+str(int(time.time()) + 1921658928)))['l'] # XXX: what is 1921658928?
 
-def iqiyi_download(url, merge=True):
+def iqiyi_download(url, config):
+	merge = config["merge"]
 	html = get_html(url)
 	#title = r1(r'title\s*:\s*"([^"]+)"', html)
 	#title = unescape_html(title).decode('utf-8')

ku6.py

@@ -19,7 +19,8 @@ def ku6_download_by_id(id, title=None, output_dir='.', merge=True):
 	ext = {'f4v':'flv'}.get(ext, ext)
 	download_urls(urls, title, ext, total_size=size, merge=merge)
 
-def ku6_download(url, merge=True):
+def ku6_download(url, config):
+	merge = config["merge"]
 	id = r1(r'http://v.ku6.com/special/show_\d+/(.*)\.\.\.html', url)
 	ku6_download_by_id(id, merge=merge)
 

pptv.py

@@ -25,8 +25,9 @@ def pptv_download_by_id(id, merge=True):
 	assert rid.endswith('.mp4')
 	download_urls(urls, title, 'mp4', total_size=total_size, merge=merge)
 
-def pptv_download(url, merge=True):
+def pptv_download(url, config):
 	assert re.match(r'http://v.pptv.com/show/(\w+)\.html$', url)
+	merge = config["merge"]
 	html = get_html(url)
 	id = r1(r'webcfg\s*=\s*{"id":\s*(\d+)', html)
 	assert id

qq.py

@@ -5,8 +5,9 @@
 import re
 from common import *
 
-def qq_download_by_id(id, title, merge=True):
+def qq_download_by_id(id, title, config):
 	url = 'http://vsrc.store.qq.com/%s.flv' % id
 	assert title
+	merge = config["merge"]
 	download_urls([url], title, 'flv', total_size=None, merge=merge)
 

sohu.py

@@ -9,7 +9,8 @@ def real_url(host, prot, file, new):
 	start, _, host, key, _, _ = get_html(url).split('|')
 	return '%s%s?key=%s' % (start[:-1], new, key)
 
-def sohu_download(url, merge=True):
+def sohu_download(url, config):
+	merge = config["merge"]
 	vid = r1('vid="(\d+)"', get_html(url))
 	assert vid
 	import json

tudou.py

@@ -23,7 +23,8 @@ def tudou_download_by_id(id, title, merge=True):
 	iid = r1(r'iid\s*=\s*(\S+)', html)
 	tudou_download_by_iid(iid, title, merge=merge)
 
-def tudou_download(url, merge=True):
+def tudou_download(url, config):
+	merge = config["merge"]
 	html = get_decoded_html(url)
 	iid = r1(r'iid\s*[:=]\s*(\d+)', html)
 	assert iid
@@ -58,7 +59,9 @@ def parse_playlist(url):
 	url = 'http://www.tudou.com/playlist/service/getAlbumItems.html?aid='+aid
 	return [(atitle + '-' + x['title'], str(x['itemId'])) for x in json.loads(get_html(url))['message']]
 
-def tudou_download_playlist(url, create_dir=False, merge=True):
+def tudou_download_playlist(url, config):
+	merge = config["merge"]
+	create_dir = config["create_dir"]
 	if create_dir:
 		raise NotImplementedError('please report a bug so I can implement this')
 	videos = parse_playlist(url)

video_lixian.py

@@ -48,13 +48,13 @@ def url_to_module(url):
 	else:
 		raise NotImplementedError(url)
 
-def any_download(url, merge=True):
+def any_download(url, config):
 	m = url_to_module(url)
-	m.download(url, merge=merge)
+	m.download(url, config=config)
 
-def any_download_playlist(url, create_dir=False, merge=True):
+def any_download_playlist(url, config):
 	m = url_to_module(url)
-	m.download_playlist(url, create_dir=create_dir, merge=merge)
+	m.download_playlist(url, config=config)
 
 def main():
 	script_main('video_lixian', any_download, any_download_playlist)

w56.py

@@ -20,7 +20,8 @@ def w56_download_by_id(id, title=None, output_dir='.', merge=True):
 	assert ext in ('flv', 'mp4')
 	download_urls([url], title, str(ext), total_size=size, merge=merge)
 
-def w56_download(url, merge=True):
+def w56_download(url, config):
+	merge = config["merge"]
 	id = r1(r'http://www.56.com/u\d+/v_(\w+).html', url)
 	w56_download_by_id(id, merge=merge)
 

yinyuetai.py

@@ -30,7 +30,8 @@ def yinyuetai_download_by_id(id, title=None, merge=True):
 	ext, size = url_info(url)
 	download_urls([url], title, ext, total_size=size, merge=merge)
 
-def yinyuetai_download(url, merge=True):
+def yinyuetai_download(url, config):
+	merge = config["merge"]
 	id = r1(r'http://www.yinyuetai.com/video/(\d+)$', url)
 	assert id
 	html = get_html(url, 'utf-8')

youku.py

@@ -77,6 +77,9 @@ def parse_page(url):
 	page = get_html(url)
 	id2 = re.search(r"var\s+videoId2\s*=\s*'(\S+)'", page).group(1)
 	title = parse_video_title(url, page)
+	if type(title) == unicode:
+		title = title.encode(default_encoding)
+		title = title.replace('?', '-')
 	return id2, title
 
 def get_info(videoId2):
@@ -127,11 +130,9 @@ def youku_download_by_id(id2, title, output_dir='.', stream_type=None, merge=Tru
 	total_size = sum(sizes)
 	download_urls(urls, title, file_type_of_url(urls[0]), total_size, output_dir, merge=merge)
 
-def youku_download(url, output_dir='', stream_type=None, merge=True):
+def youku_download(url, config, output_dir='', stream_type=None):
+	merge = config["merge"]
 	id2, title = parse_page(url)
-	if type(title) == unicode:
-		title = title.encode(default_encoding)
-		title = title.replace('?', '-')
 	youku_download_by_id(id2, title, output_dir, merge=merge)
 
 def parse_playlist_videos(html):
@@ -167,7 +168,10 @@ def parse_vplaylist(url):
 	n = int(re.search(r'<span class="num">(\d+)</span>', get_html(url)).group(1))
 	return ['http://v.youku.com/v_playlist/f%so0p%s.html' % (id, i) for i in range(n)]
 
-def youku_download_playlist(url, create_dir=False, merge=True):
+def youku_download_playlist(url, config):
+	create_dir = config["create_dir"]
+	print("Collecting video IDs for the playlist...")
+
 	if re.match(r'http://www.youku.com/show_page/id_\w+.html', url):
 		url = find_video_id_from_show_page(url)
 	if re.match(r'http://www.youku.com/playlist_show/id_\d+(?:_ascending_\d_mode_pic(?:_page_\d+)?)?.html', url):
@@ -188,9 +192,61 @@ def youku_download_playlist(url, create_dir=False, merge=True):
 		if not os.path.exists(title):
 			os.makedirs(title)
 		output_dir = title
-	for i, id in enumerate(ids):
-		print 'Downloading %s of %s videos...' % (i + 1, len(ids))
-		youku_download(id, output_dir=output_dir, merge=merge)
+
+	ids_len = len(ids)
+	if not config["interactive"]:
+		for i, id in enumerate(ids):
+			print 'Downloading %s of %s videos...' % (i + 1, len(ids))
+			youku_download(id, config=config, output_dir=output_dir)
+	else:
+		ids_info = []
+		ids_map = {}
+		print("Collecting video titles...")
+
+		# download video title in threads
+		import threading
+		ids_map_lock = threading.Lock()
+
+		def get_title(idx, avid):
+			"""Download thread title and save it"""
+			id2, title = parse_page(avid)
+			vid_info = {"id":id2, "title": title}
+			ids_map_lock.acquire()
+			ids_map[avid] = vid_info
+			print("[%d/%d] %s: %s" % (idx+1, ids_len, id2, title))
+			ids_map_lock.release()
+
+		args_list = list(enumerate(ids))
+		args_list.reverse()
+		thread_list = set()
+		conns = 5 # number of cocurrent threads
+		while len(thread_list) > 0 or len(args_list) > 0:
+			# start some threads
+			while len(thread_list) < conns and len(args_list) > 0:
+				args = args_list.pop()
+				t = threading.Thread(target=get_title, args=args)
+				thread_list.add(t)
+				t.start()
+
+			# remove finished threads
+			t_done = []
+			for t1 in thread_list:
+				t1.join(.1)
+				if not t1.isAlive():
+					t_done.append(t1)
+			for t1 in t_done:
+				thread_list.remove(t1)
+
+		# restore ids order
+		for i in ids:
+			ids_info.append(ids_map[i])
+
+		selected_ids = select_playlist_info(ids_info)
+		selected_len = len(selected_ids)
+		for i, vid_info in enumerate(selected_ids):
+			print 'Downloading %s of %s videos...' % (i + 1, selected_len)
+			youku_download_by_id(vid_info["id"], vid_info["title"],
+					output_dir, merge=config["merge"])
 
 download = youku_download
 download_playlist = youku_download_playlist