X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube-dl;h=f3d7a3f61f5f8addf1f3c04214c6245b35147490;hb=44c636df8966a1ace617b276f19b5887aa66d612;hp=edd1d3f29ee273693819d0de2803103007bb2c1d;hpb=92743d423a7dfaf0f803deab14475e6343091f20;p=youtube-dl
diff --git a/youtube-dl b/youtube-dl
index edd1d3f29..f3d7a3f61 100755
--- a/youtube-dl
+++ b/youtube-dl
@@ -5,6 +5,8 @@
# Author: Benjamin Johnson
# Author: Vasyl' Vavrychuk
# Author: Witold Baryluk
+# Author: PaweÅ Paprota
+# Author: Gergely Imreh
# License: Public domain code
import cookielib
import ctypes
@@ -36,7 +38,7 @@ except ImportError:
from cgi import parse_qs
std_headers = {
- 'User-Agent': 'Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.2.12) Gecko/20101028 Firefox/3.6.12',
+ 'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:2.0b11) Gecko/20100101 Firefox/4.0b11',
'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
'Accept-Encoding': 'gzip, deflate',
@@ -856,7 +858,7 @@ class InfoExtractor(object):
class YoutubeIE(InfoExtractor):
"""Information extractor for youtube.com."""
- _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?:(?:(?:v|embed)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$'
+ _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$'
_LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
_LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en'
_AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
@@ -1054,10 +1056,10 @@ class YoutubeIE(InfoExtractor):
# upload date
upload_date = u'NA'
- mobj = re.search(r'id="eow-date".*?>(.*?)', video_webpage, re.DOTALL)
+ mobj = re.search(r'id="eow-date.*?>(.*?)', video_webpage, re.DOTALL)
if mobj is not None:
upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
- format_expressions = ['%d %B %Y', '%B %d %Y']
+ format_expressions = ['%d %B %Y', '%B %d %Y', '%b %d %Y']
for expression in format_expressions:
try:
upload_date = datetime.datetime.strptime(upload_date, expression).strftime('%Y%m%d')
@@ -1077,7 +1079,7 @@ class YoutubeIE(InfoExtractor):
# Decide which formats to download
req_format = self._downloader.params.get('format', None)
- if 'fmt_url_map' in video_info:
+ if 'fmt_url_map' in video_info and len(video_info['fmt_url_map']) >= 1 and ',' in video_info['fmt_url_map'][0]:
url_map = dict(tuple(pair.split('|')) for pair in video_info['fmt_url_map'][0].split(','))
format_limit = self._downloader.params.get('format_limit', None)
if format_limit is not None and format_limit in self._available_formats:
@@ -1722,7 +1724,7 @@ class VimeoIE(InfoExtractor):
"""Information extractor for vimeo.com."""
# _VALID_URL matches Vimeo URLs
- _VALID_URL = r'(?:http://)?vimeo\.com/([0-9]+)'
+ _VALID_URL = r'(?:https?://)?(?:(?:www|player).)?vimeo\.com/(?:groups/[^/]+/)?(?:videos?/)?([0-9]+)'
def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader)
@@ -1733,11 +1735,11 @@ class VimeoIE(InfoExtractor):
def report_download_webpage(self, video_id):
"""Report webpage download."""
- self._downloader.to_screen(u'[video.vimeo] %s: Downloading webpage' % video_id)
+ self._downloader.to_screen(u'[vimeo] %s: Downloading webpage' % video_id)
def report_extraction(self, video_id):
"""Report information extraction."""
- self._downloader.to_screen(u'[video.vimeo] %s: Extracting information' % video_id)
+ self._downloader.to_screen(u'[vimeo] %s: Extracting information' % video_id)
def _real_initialize(self):
return
@@ -1763,23 +1765,28 @@ class VimeoIE(InfoExtractor):
self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
return
- # Extract uploader and title from webpage
+ # Now we begin extracting as much information as we can from what we
+ # retrieved. First we extract the information common to all extractors,
+ # and latter we extract those that are Vimeo specific.
self.report_extraction(video_id)
- mobj = re.search(r'
(.*)', webpage)
+
+ # Extract title
+ mobj = re.search(r'(.*?)', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract video title')
return
video_title = mobj.group(1).decode('utf-8')
simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
- mobj = re.search(r'http://vimeo.com/(.*)', webpage)
+ # Extract uploader
+ mobj = re.search(r'http://vimeo.com/(.*?)', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract video uploader')
return
video_uploader = mobj.group(1).decode('utf-8')
# Extract video thumbnail
- mobj = re.search(r'(.*)', webpage)
+ mobj = re.search(r'(.*?)', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
return
@@ -1794,15 +1801,15 @@ class VimeoIE(InfoExtractor):
# if not video_description: video_description = 'No description available.'
video_description = 'Foo.'
- # Extract request signature
- mobj = re.search(r'(.*)', webpage)
+ # Vimeo specific: extract request signature
+ mobj = re.search(r'(.*?)', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract request signature')
return
sig = mobj.group(1).decode('utf-8')
- # Extract request signature expiration
- mobj = re.search(r'(.*)', webpage)
+ # Vimeo specific: Extract request signature expiration
+ mobj = re.search(r'(.*?)', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract request signature expiration')
return
@@ -2207,8 +2214,8 @@ class YahooSearchIE(InfoExtractor):
class YoutubePlaylistIE(InfoExtractor):
"""Information Extractor for YouTube playlists."""
- _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/(?:(?:view_play_list|my_playlists)\?.*?p=|user/.*?/user/|p/)([^&]+).*'
- _TEMPLATE_URL = 'http://www.youtube.com/view_play_list?p=%s&page=%s&gl=US&hl=en'
+ _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/(?:(?:view_play_list|my_playlists|artist)\?.*?(p|a)=|user/.*?/user/|p/|user/.*?#[pg]/c/)([0-9A-Za-z]+)(?:/.*?/([0-9A-Za-z_-]+))?.*'
+ _TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en'
_VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
_MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*'
_youtube_ie = None
@@ -2235,14 +2242,26 @@ class YoutubePlaylistIE(InfoExtractor):
self._downloader.trouble(u'ERROR: invalid url: %s' % url)
return
+ # Single video case
+ if mobj.group(3) is not None:
+ self._youtube_ie.extract(mobj.group(3))
+ return
+
# Download playlist pages
- playlist_id = mobj.group(1)
+ # prefix is 'p' as default for playlists but there are other types that need extra care
+ playlist_prefix = mobj.group(1)
+ if playlist_prefix == 'a':
+ playlist_access = 'artist'
+ else:
+ playlist_prefix = 'p'
+ playlist_access = 'view_play_list'
+ playlist_id = mobj.group(2)
video_ids = []
pagenum = 1
while True:
self.report_download_page(playlist_id, pagenum)
- request = urllib2.Request(self._TEMPLATE_URL % (playlist_id, pagenum))
+ request = urllib2.Request(self._TEMPLATE_URL % (playlist_access, playlist_prefix, playlist_id, pagenum))
try:
page = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
@@ -2271,9 +2290,11 @@ class YoutubePlaylistIE(InfoExtractor):
class YoutubeUserIE(InfoExtractor):
"""Information Extractor for YouTube users."""
- _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/user/(.*)'
+ _VALID_URL = r'(?:(?:(?:http://)?(?:\w+\.)?youtube.com/user/)|ytuser:)([A-Za-z0-9_-]+)'
_TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s'
- _VIDEO_INDICATOR = r'http://gdata.youtube.com/feeds/api/videos/(.*)' # XXX Fix this.
+ _GDATA_PAGE_SIZE = 50
+ _GDATA_URL = 'http://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d'
+ _VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
_youtube_ie = None
def __init__(self, youtube_ie, downloader=None):
@@ -2284,9 +2305,10 @@ class YoutubeUserIE(InfoExtractor):
def suitable(url):
return (re.match(YoutubeUserIE._VALID_URL, url) is not None)
- def report_download_page(self, username):
+ def report_download_page(self, username, start_index):
"""Report attempt to download user page."""
- self._downloader.to_screen(u'[youtube] user %s: Downloading page ' % (username))
+ self._downloader.to_screen(u'[youtube] user %s: Downloading video ids from %d to %d' %
+ (username, start_index, start_index + self._GDATA_PAGE_SIZE))
def _real_initialize(self):
self._youtube_ie.initialize()
@@ -2298,34 +2320,63 @@ class YoutubeUserIE(InfoExtractor):
self._downloader.trouble(u'ERROR: invalid url: %s' % url)
return
- # Download user page
username = mobj.group(1)
+
+ # Download video ids using YouTube Data API. Result size per
+ # query is limited (currently to 50 videos) so we need to query
+ # page by page until there are no video ids - it means we got
+ # all of them.
+
video_ids = []
- pagenum = 1
+ pagenum = 0
- self.report_download_page(username)
- request = urllib2.Request(self._TEMPLATE_URL % (username))
- try:
- page = urllib2.urlopen(request).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
- return
+ while True:
+ start_index = pagenum * self._GDATA_PAGE_SIZE + 1
+ self.report_download_page(username, start_index)
+
+ request = urllib2.Request(self._GDATA_URL % (username, self._GDATA_PAGE_SIZE, start_index))
+
+ try:
+ page = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+ return
+
+ # Extract video identifiers
+ ids_in_page = []
+
+ for mobj in re.finditer(self._VIDEO_INDICATOR, page):
+ if mobj.group(1) not in ids_in_page:
+ ids_in_page.append(mobj.group(1))
- # Extract video identifiers
- ids_in_page = []
+ video_ids.extend(ids_in_page)
+
+ # A little optimization - if current page is not
+ # "full", ie. does not contain PAGE_SIZE video ids then
+ # we can assume that this page is the last one - there
+ # are no more ids on further pages - no need to query
+ # again.
+
+ if len(ids_in_page) < self._GDATA_PAGE_SIZE:
+ break
- for mobj in re.finditer(self._VIDEO_INDICATOR, page):
- if mobj.group(1) not in ids_in_page:
- ids_in_page.append(mobj.group(1))
- video_ids.extend(ids_in_page)
+ pagenum += 1
+ all_ids_count = len(video_ids)
playliststart = self._downloader.params.get('playliststart', 1) - 1
playlistend = self._downloader.params.get('playlistend', -1)
- video_ids = video_ids[playliststart:playlistend]
- for id in video_ids:
- self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
- return
+ if playlistend == -1:
+ video_ids = video_ids[playliststart:]
+ else:
+ video_ids = video_ids[playliststart:playlistend]
+
+ self._downloader.to_screen("[youtube] user %s: Collected %d video ids (downloading %d of them)" %
+ (username, all_ids_count, len(video_ids)))
+
+ for video_id in video_ids:
+ self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % video_id)
+
class DepositFilesIE(InfoExtractor):
"""Information extractor for depositfiles.com"""
@@ -2406,6 +2457,229 @@ class DepositFilesIE(InfoExtractor):
except UnavailableVideoError, err:
self._downloader.trouble(u'ERROR: unable to download file')
+class FacebookIE(InfoExtractor):
+ """Information Extractor for Facebook"""
+
+ _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook.com/video/video.php\?(?:.*?)v=(?P\d+)(?:.*)'
+ _LOGIN_URL = 'https://login.facebook.com/login.php?m&next=http%3A%2F%2Fm.facebook.com%2Fhome.php&'
+ _NETRC_MACHINE = 'facebook'
+ _available_formats = ['highqual', 'lowqual']
+ _video_extensions = {
+ 'highqual': 'mp4',
+ 'lowqual': 'mp4',
+ }
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ @staticmethod
+ def suitable(url):
+ return (re.match(FacebookIE._VALID_URL, url) is not None)
+
+ def _reporter(self, message):
+ """Add header and report message."""
+ self._downloader.to_screen(u'[facebook] %s' % message)
+
+ def report_login(self):
+ """Report attempt to log in."""
+ self._reporter(u'Logging in')
+
+ def report_video_webpage_download(self, video_id):
+ """Report attempt to download video webpage."""
+ self._reporter(u'%s: Downloading video webpage' % video_id)
+
+ def report_information_extraction(self, video_id):
+ """Report attempt to extract video information."""
+ self._reporter(u'%s: Extracting video information' % video_id)
+
+ def _parse_page(self, video_webpage):
+ """Extract video information from page"""
+ # General data
+ data = {'title': r'class="video_title datawrap">(.*?)',
+ 'description': r'(.*?)
',
+ 'owner': r'\("video_owner_name", "(.*?)"\)',
+ 'upload_date': r'data-date="(.*?)"',
+ 'thumbnail': r'\("thumb_url", "(?P.*?)"\)',
+ }
+ video_info = {}
+ for piece in data.keys():
+ mobj = re.search(data[piece], video_webpage)
+ if mobj is not None:
+ video_info[piece] = urllib.unquote_plus(mobj.group(1).decode("unicode_escape"))
+
+ # Video urls
+ video_urls = {}
+ for fmt in self._available_formats:
+ mobj = re.search(r'\("%s_src\", "(.+?)"\)' % fmt, video_webpage)
+ if mobj is not None:
+ # URL is in a Javascript segment inside an escaped Unicode format within
+ # the generally utf-8 page
+ video_urls[fmt] = urllib.unquote_plus(mobj.group(1).decode("unicode_escape"))
+ video_info['video_urls'] = video_urls
+
+ return video_info
+
+ def _real_initialize(self):
+ if self._downloader is None:
+ return
+
+ useremail = None
+ password = None
+ downloader_params = self._downloader.params
+
+ # Attempt to use provided username and password or .netrc data
+ if downloader_params.get('username', None) is not None:
+ useremail = downloader_params['username']
+ password = downloader_params['password']
+ elif downloader_params.get('usenetrc', False):
+ try:
+ info = netrc.netrc().authenticators(self._NETRC_MACHINE)
+ if info is not None:
+ useremail = info[0]
+ password = info[2]
+ else:
+ raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
+ except (IOError, netrc.NetrcParseError), err:
+ self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % str(err))
+ return
+
+ if useremail is None:
+ return
+
+ # Log in
+ login_form = {
+ 'email': useremail,
+ 'pass': password,
+ 'login': 'Log+In'
+ }
+ request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form))
+ try:
+ self.report_login()
+ login_results = urllib2.urlopen(request).read()
+ if re.search(r'