0x2620/python-ox
2
1
Fork 0
Code Issues Pull requests Releases Wiki Activity

fix ox.web.youtube

Browse source
This commit is contained in:
j 2014-09-28 21:57:45 +02:00
parent 14ea6a0f7d
commit ff0d776b09
1 changed files with 34 additions and 18 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

38
ox/web/youtube.py
View file

@ -38,11 +38,27 @@ def video_url(youtubeId, format='mp4', timeout=cache_timeout):
fmt=35 fmt=35
elif format == 'webm': elif format == 'webm':
streams = videos(youtubeId, 'webm') streams = videos(youtubeId, 'webm')
return streams[max(streams.keys())]['stream_url'] return streams[max(streams.keys())]['url']
streams = videos(youtubeId) streams = videos(youtubeId)
if str(fmt) in streams: if str(fmt) in streams:
return streams[str(fmt)]['stream_url'] return streams[str(fmt)]['url']
def get_video_info(id):
eurl = get_url(id)
data = read_url(eurl)
t = re.compile('\W[\'"]?t[\'"]?: ?[\'"](.+?)[\'"]').findall(data)
if t:
t = t[0]
else:
raise IOError
url = "http://www.youtube.com/get_video_info?&video_id=%s&el=$el&ps=default&eurl=%s&hl=en_US&t=%s" % (id, quote(eurl), quote(t))
data = read_url(url)
info = {}
for part in data.split('&'):
key, value = part.split('=')
info[key] = unquote_plus(value).replace('+', ' ')
return info
def find(query, max_results=10, offset=1, orderBy='relevance'): def find(query, max_results=10, offset=1, orderBy='relevance'):
query = quote(query) query = quote(query)
@ -121,19 +137,18 @@ def videos(id, format=''):
'webm': 'video/webm', 'webm': 'video/webm',
'mp4': 'video/mp4' 'mp4': 'video/mp4'
}.get(format) }.get(format)
url = "http://www.youtube.com/watch?v=%s" % id info = get_video_info(id)
data = read_url(url) stream_map = info['url_encoded_fmt_stream_map']
match = re.compile('"url_encoded_fmt_stream_map": "(.*?)"').findall(data)
streams = {} streams = {}
if match: for x in stream_map.split(','):
for x in match[0].split(','):
stream = {} stream = {}
for s in x.split('\\u0026'): #for s in x.split('\\u0026'):
for s in x.split('&'):
key, value = s.split('=') key, value = s.split('=')
value = unquote_plus(value) value = unquote_plus(value)
stream[key] = value stream[key] = value
if 'url' in stream and 'sig' in stream: if 'url' in stream and 'sig' in stream:
stream['stream_url'] = '%s&signature=%s' % (stream['url'], stream['sig']) stream['url'] = '%s&signature=%s' % (stream['url'], stream['sig'])
if not stream_type or stream['type'].startswith(stream_type): if not stream_type or stream['type'].startswith(stream_type):
streams[stream['itag']] = stream streams[stream['itag']] = stream
return streams return streams
@ -173,7 +188,9 @@ def download_webm(id, filename):
streams[stream['itag']] = stream streams[stream['itag']] = stream
if streams: if streams:
s = max(streams.keys()) s = max(streams.keys())
url = '%s&signature=%s' % (streams[s]['url'], streams[s]['sig']) url = streams[s]['url']
if 'sig' in streams[s]:
url += 'signature=' + streams[s]['sig']
else: else:
return None return None
@ -198,4 +215,3 @@ def get_config(id):
if match: if match:
config = json.load(match[0]) config = json.load(match[0])
return config return config