fix #2, #4: parse YouTube signature

This commit is contained in:
Mort Yao 2012-09-17 13:11:46 +02:00
parent 4cb24e07d2
commit 8389164081
2 changed files with 17 additions and 1 deletions

View File

@ -43,6 +43,9 @@ def r1_of(patterns, text):
if x: if x:
return x return x
def unicodize(text):
return re.sub(r'\\u([0-9A-Fa-f][0-9A-Fa-f][0-9A-Fa-f][0-9A-Fa-f])', lambda x: chr(int(x.group(0)[2:], 16)), text)
def escape_file_path(path): def escape_file_path(path):
path = path.replace('/', '-') path = path.replace('/', '-')
path = path.replace('\\', '-') path = path.replace('\\', '-')
@ -572,6 +575,8 @@ def script_main(script_name, download, download_playlist = None):
set_http_proxy(proxy) set_http_proxy(proxy)
for url in args: for url in args:
if url.startswith('https://'):
url = url[8:]
if not url.startswith('http://'): if not url.startswith('http://'):
url = 'http://' + url url = 'http://' + url

View File

@ -8,7 +8,17 @@ def youtube_download_by_id(id, title = None, output_dir = '.', merge = True, inf
try: try:
url = parse.parse_qs(parse.unquote(request.urlopen('http://www.youtube.com/get_video_info?&video_id=' + id).read().decode('utf-8')))['url_encoded_fmt_stream_map'][0][4:] url = parse.parse_qs(parse.unquote(request.urlopen('http://www.youtube.com/get_video_info?&video_id=' + id).read().decode('utf-8')))['url_encoded_fmt_stream_map'][0][4:]
except: except:
url = parse.parse_qs(parse.unquote(request.urlopen('http://www.youtube.com/watch?v=' + id).read().decode('utf-8')))['url_encoded_fmt_stream_map'][0][4:] html = request.urlopen('http://www.youtube.com/watch?v=' + id).read().decode('utf-8')
url = parse.parse_qs(parse.unquote(html))['url_encoded_fmt_stream_map'][0][4:]
if not url.startswith('http://'):
codec = r1(r'yt.preload.start\("http:\\/\\/([^\\]+)\\/crossdomain.xml"\)', html)
signature = r1(r'signature=([^\\]+)\\', html)
urls = parse.parse_qs(parse.unquote(html))['url']
for u in urls:
if u.startswith('http://' + codec):
url = "%s&signature=%s" % (u, signature)
break
type, ext, size = url_info(url) type, ext, size = url_info(url)
print_info(site_info, title, type, size) print_info(site_info, title, type, size)
@ -23,6 +33,7 @@ def youtube_download(url, output_dir = '.', merge = True, info_only = False):
except: except:
html = get_html(url, 'utf-8') html = get_html(url, 'utf-8')
title = r1(r'"title": "([^"]+)"', html) title = r1(r'"title": "([^"]+)"', html)
title = unicodize(title)
assert title assert title
title = parse.unquote(title) title = parse.unquote(title)
title = escape_file_path(title) title = escape_file_path(title)