Compare commits

..

8 Commits

Author SHA1 Message Date
Ricardo Garcia
d1580ed990 Fix NameError 2010-10-31 11:23:45 +01:00
Ricardo Garcia
eb0d2909a8 Document new -a option 2010-10-31 11:23:44 +01:00
Ricardo Garcia
ba72f8a5d1 Bump version and increase Firefox version number 2010-10-31 11:23:44 +01:00
Ricardo Garcia
c6fd0bb806 Add -a (--batch-file) option 2010-10-31 11:23:44 +01:00
Ricardo Garcia
72ac78b8b0 Fix for YouTube internationalization changes 2010-10-31 11:23:44 +01:00
Ricardo Garcia
240b737ebd Bump version number 2010-10-31 11:23:41 +01:00
Ricardo Garcia
27d98b6e25 Fix TypeError in decode() method and unordered playlist URLs 2010-10-31 11:23:41 +01:00
Ricardo Garcia
5487aea5d8 Improve documentation 2010-10-31 11:23:41 +01:00
2 changed files with 54 additions and 23 deletions

View File

@@ -96,7 +96,8 @@ is too old.</p>
<li>You can change the file name of the video using the -o option, like in
<em>youtube-dl -o vid.flv "http://www.youtube.com/watch?v=foobar"</em>.
Read the <em>Output template</em> section for more details on this.</li>
Read the <a href="#otpl">Output template</a> section for more details on
this.</li>
<li>Some videos require an account to be downloaded, mostly because they're
flagged as mature content. You can pass the program a username and password
@@ -130,15 +131,16 @@ literal title in the filename with the -l or --literal option.</li>
by using the -f or --format option. This makes it possible to download high
quality versions of the videos when available.</li>
<li><em>youtube-dl</em> can attempt to download the best quality version of
a video by using the -b or --best-quality option.</li>
<li>The -b or --best-quality option is an alias for -f 18.</li>
<li><em>youtube-dl</em> can attempt to download the mobile quality version of
a video by using the -m or --mobile-version option.</li>
<li>The -m or --mobile-version option is an alias for -f 17.</li>
<li>Normally, the program will stop on the first error, but you can tell it
to attempt to download every video with the -i or --ignore-errors option.</li>
<li>The -a or --batch-file option lets you specify a file to read URLs from.
The file must contain one URL per line.</li>
<li><em>youtube-dl</em> honors the <em>http_proxy</em> environment variable
if you want to use a proxy. Set it to something like
<em>http://proxy.example.com:8080</em>, and do not leave the <em>http://</em>
@@ -156,7 +158,7 @@ That's ok.</li>
</ul>
<h2>Download it</h2>
<h2 id="otpl">Download it</h2>
<p>Note that if you directly click on these hyperlinks, your web browser will
most likely display the program contents. It's usually better to
@@ -189,9 +191,9 @@ person who uploaded the video.</li>
<li><em>title</em>: The sequence will be replaced by the literal video
title.</li>
<li><em>stitle</em>: The sequence will be replaced by a simplified video
title.</li>
title, restricted to alphanumeric characters and dashes.</li>
<li><em>ext</em>: The sequence will be replaced by the appropriate
extension.</li>
extension (like <em>flv</em> or <em>mp4</em>).</li>
</ul>
<p>As you may have guessed, the default template is <em>%(id)s.%(ext)s</em>.

View File

@@ -18,7 +18,7 @@ import urllib
import urllib2
std_headers = {
'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.9.0.1) Gecko/2008070208 Firefox/3.0.1',
'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.9.0.5) Gecko/2008120122 Firefox/3.0.5',
'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
'Accept': 'text/xml,application/xml,application/xhtml+xml,text/html;q=0.9,text/plain;q=0.8,image/png,*/*;q=0.5',
'Accept-Language': 'en-us,en;q=0.5',
@@ -431,14 +431,19 @@ class YoutubeIE(InfoExtractor):
"""Information extractor for youtube.com."""
_VALID_URL = r'^((?:http://)?(?:\w+\.)?youtube\.com/(?:(?:v/)|(?:(?:watch(?:\.php)?)?\?(?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$'
_LOGIN_URL = 'http://uk.youtube.com/login?next=/'
_AGE_URL = 'http://uk.youtube.com/verify_age?next_url=/'
_LANG_URL = r'http://uk.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
_LOGIN_URL = 'http://www.youtube.com/signup?next=/&gl=US&hl=en'
_AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
_NETRC_MACHINE = 'youtube'
@staticmethod
def suitable(url):
return (re.match(YoutubeIE._VALID_URL, url) is not None)
def report_lang(self):
"""Report attempt to set language."""
self.to_stdout(u'[youtube] Setting language')
def report_login(self):
"""Report attempt to log in."""
self.to_stdout(u'[youtube] Logging in')
@@ -487,6 +492,15 @@ class YoutubeIE(InfoExtractor):
if username is None:
return
# Set language
request = urllib2.Request(self._LOGIN_URL, None, std_headers)
try:
self.report_lang()
urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self.to_stderr(u'WARNING: unable to set language: %s' % str(err))
return
# Log in
login_form = {
'current_form': 'loginForm',
@@ -537,7 +551,7 @@ class YoutubeIE(InfoExtractor):
video_extension = {'18': 'mp4', '17': '3gp'}.get(format_param, 'flv')
# Normalize URL, including format
normalized_url = 'http://uk.youtube.com/watch?v=%s' % video_id
normalized_url = 'http://www.youtube.com/watch?v=%s&gl=US&hl=en' % video_id
if format_param is not None:
normalized_url = '%s&fmt=%s' % (normalized_url, format_param)
request = urllib2.Request(normalized_url, None, std_headers)
@@ -554,7 +568,7 @@ class YoutubeIE(InfoExtractor):
if mobj is None:
self.to_stderr(u'ERROR: unable to extract "t" parameter')
return [None]
video_real_url = 'http://uk.youtube.com/get_video?video_id=%s&t=%s' % (video_id, mobj.group(1))
video_real_url = 'http://www.youtube.com/get_video?video_id=%s&t=%s' % (video_id, mobj.group(1))
if format_param is not None:
video_real_url = '%s&fmt=%s' % (video_real_url, format_param)
self.report_video_url(video_id, video_real_url)
@@ -655,7 +669,7 @@ class MetacafeIE(InfoExtractor):
# Check if video comes from YouTube
mobj2 = re.match(r'^yt-(.*)$', video_id)
if mobj2 is not None:
return self._youtube_ie.extract('http://uk.youtube.com/watch?v=%s' % mobj2.group(1))
return self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % mobj2.group(1))
simple_title = mobj.group(2).decode('utf-8')
video_extension = 'flv'
@@ -711,7 +725,7 @@ class YoutubePlaylistIE(InfoExtractor):
"""Information Extractor for YouTube playlists."""
_VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/view_play_list\?p=(.+)'
_TEMPLATE_URL = 'http://uk.youtube.com/view_play_list?p=%s&page=%s'
_TEMPLATE_URL = 'http://www.youtube.com/view_play_list?p=%s&page=%s&gl=US&hl=en'
_VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
_MORE_PAGES_INDICATOR = r'/view_play_list?p=%s&amp;page=%s'
_youtube_ie = None
@@ -753,10 +767,11 @@ class YoutubePlaylistIE(InfoExtractor):
return [None]
# Extract video identifiers
ids_in_page = set()
ids_in_page = []
for mobj in re.finditer(self._VIDEO_INDICATOR, page):
ids_in_page.add(mobj.group(1))
video_ids.extend(list(ids_in_page))
if mobj.group(1) not in ids_in_page:
ids_in_page.append(mobj.group(1))
video_ids.extend(ids_in_page)
if (self._MORE_PAGES_INDICATOR % (playlist_id, pagenum + 1)) not in page:
break
@@ -764,7 +779,7 @@ class YoutubePlaylistIE(InfoExtractor):
information = []
for id in video_ids:
information.extend(self._youtube_ie.extract('http://uk.youtube.com/watch?v=%s' % id))
information.extend(self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id))
return information
class PostProcessor(object):
@@ -837,7 +852,7 @@ if __name__ == '__main__':
# Parse command line
parser = optparse.OptionParser(
usage='Usage: %prog [options] url...',
version='2008.10.16',
version='2009.01.31',
conflict_handler='resolve',
)
parser.add_option('-h', '--help',
@@ -874,10 +889,21 @@ if __name__ == '__main__':
action='store_true', dest='ignoreerrors', help='continue on download errors', default=False)
parser.add_option('-r', '--rate-limit',
dest='ratelimit', metavar='L', help='download rate limit (e.g. 50k or 44.6m)')
parser.add_option('-a', '--batch-file',
dest='batchfile', metavar='F', help='file containing URLs to download')
(opts, args) = parser.parse_args()
# Batch file verification
batchurls = []
if opts.batchfile is not None:
try:
batchurls = [line.strip() for line in open(opts.batchfile, 'r')]
except IOError:
sys.exit(u'ERROR: batch file could not be read')
all_urls = batchurls + args
# Conflicting, missing and erroneous options
if len(args) < 1:
if len(all_urls) < 1:
sys.exit(u'ERROR: you must provide at least one URL')
if opts.usenetrc and (opts.username is not None or opts.password is not None):
sys.exit(u'ERROR: using .netrc conflicts with giving username/password')
@@ -901,6 +927,9 @@ if __name__ == '__main__':
youtube_pl_ie = YoutubePlaylistIE(youtube_ie)
# File downloader
charset = locale.getdefaultlocale()[1]
if charset is None:
charset = 'ascii'
fd = FileDownloader({
'usenetrc': opts.usenetrc,
'username': opts.username,
@@ -910,7 +939,7 @@ if __name__ == '__main__':
'forcetitle': opts.gettitle,
'simulate': (opts.simulate or opts.geturl or opts.gettitle),
'format': opts.format,
'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(locale.getdefaultlocale()[1]))
'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(charset))
or (opts.usetitle and u'%(stitle)s-%(id)s.%(ext)s')
or (opts.useliteral and u'%(title)s-%(id)s.%(ext)s')
or u'%(id)s.%(ext)s'),
@@ -920,7 +949,7 @@ if __name__ == '__main__':
fd.add_info_extractor(youtube_pl_ie)
fd.add_info_extractor(metacafe_ie)
fd.add_info_extractor(youtube_ie)
retcode = fd.download(args)
retcode = fd.download(all_urls)
sys.exit(retcode)
except DownloadError: