X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube-dl;h=377ceff588241ccdb37bb19f972648cc898d5873;hb=62a29bbf7bd0b0d9539aa903519f252671e4eebd;hp=103189b21f1c317e058e91fa3f8a02056f6c70f1;hpb=0f6b00b587e9b47919555f9c250b753419063b46;p=youtube-dl
diff --git a/youtube-dl b/youtube-dl
index 103189b21..377ceff58 100755
--- a/youtube-dl
+++ b/youtube-dl
@@ -4,10 +4,14 @@
# Author: Danny Colligan
# Author: Benjamin Johnson
# Author: Vasyl' Vavrychuk
+# Author: Witold Baryluk
+# Author: PaweÅ Paprota
+# Author: Gergely Imreh
# License: Public domain code
import cookielib
import ctypes
import datetime
+import email.utils
import gzip
import htmlentitydefs
import httplib
@@ -34,7 +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',
@@ -116,6 +120,14 @@ def sanitize_open(filename, open_mode):
stream = open(filename, open_mode)
return (stream, filename)
+def timeconvert(timestr):
+ """Convert RFC 2822 defined time string into system timestamp"""
+ timestamp = None
+ timetuple = email.utils.parsedate_tz(timestr)
+ if timetuple is not None:
+ timestamp = email.utils.mktime_tz(timetuple)
+ return timestamp
+
class DownloadError(Exception):
"""Download Error exception.
@@ -257,6 +269,7 @@ class FileDownloader(object):
forcetitle: Force printing title.
forcethumbnail: Force printing thumbnail URL.
forcedescription: Force printing description.
+ forcefilename: Force printing final filename.
simulate: Do not download the video files.
format: Video format code.
format_limit: Highest quality format to try.
@@ -272,6 +285,7 @@ class FileDownloader(object):
logtostderr: Log messages to stderr instead of stdout.
consoletitle: Display progress in console window's titlebar.
nopart: Do not use temporary .part files.
+ updatetime: Use the Last-modified header to set output file timestamps.
"""
params = None
@@ -449,6 +463,23 @@ class FileDownloader(object):
os.rename(old_filename, new_filename)
except (IOError, OSError), err:
self.trouble(u'ERROR: unable to rename file')
+
+ def try_utime(self, filename, last_modified_hdr):
+ """Try to set the last-modified time of the given file."""
+ if last_modified_hdr is None:
+ return
+ if not os.path.isfile(filename):
+ return
+ timestr = last_modified_hdr
+ if timestr is None:
+ return
+ filetime = timeconvert(timestr)
+ if filetime is None:
+ return
+ try:
+ os.utime(filename,(time.time(), filetime))
+ except:
+ pass
def report_destination(self, filename):
"""Report destination filename."""
@@ -493,8 +524,21 @@ class FileDownloader(object):
"""Increment the ordinal that assigns a number to each file."""
self._num_downloads += 1
+ def prepare_filename(self, info_dict):
+ """Generate the output filename."""
+ try:
+ template_dict = dict(info_dict)
+ template_dict['epoch'] = unicode(long(time.time()))
+ template_dict['autonumber'] = unicode('%05d' % self._num_downloads)
+ filename = self.params['outtmpl'] % template_dict
+ return filename
+ except (ValueError, KeyError), err:
+ self.trouble(u'ERROR: invalid system charset or erroneous output template')
+ return None
+
def process_info(self, info_dict):
"""Process a single dictionary returned by an InfoExtractor."""
+ filename = self.prepare_filename(info_dict)
# Do nothing else if in simulate mode
if self.params.get('simulate', False):
# Forced printings
@@ -506,16 +550,12 @@ class FileDownloader(object):
print info_dict['thumbnail'].encode(preferredencoding(), 'xmlcharrefreplace')
if self.params.get('forcedescription', False) and 'description' in info_dict:
print info_dict['description'].encode(preferredencoding(), 'xmlcharrefreplace')
+ if self.params.get('forcefilename', False) and filename is not None:
+ print filename.encode(preferredencoding(), 'xmlcharrefreplace')
return
- try:
- template_dict = dict(info_dict)
- template_dict['epoch'] = unicode(long(time.time()))
- template_dict['autonumber'] = unicode('%05d' % self._num_downloads)
- filename = self.params['outtmpl'] % template_dict
- except (ValueError, KeyError), err:
- self.trouble(u'ERROR: invalid system charset or erroneous output template')
+ if filename is None:
return
if self.params.get('nooverwrites', False) and os.path.exists(filename):
self.to_stderr(u'WARNING: file exists and will be skipped')
@@ -737,6 +777,11 @@ class FileDownloader(object):
if data_len is not None and byte_counter != data_len:
raise ContentTooShortError(byte_counter, long(data_len))
self.try_rename(tmpfilename, filename)
+
+ # Update file modification time
+ if self.params.get('updatetime', True):
+ self.try_utime(filename, data.info().get('last-modified', None))
+
return True
class InfoExtractor(object):
@@ -813,7 +858,7 @@ class InfoExtractor(object):
class YoutubeIE(InfoExtractor):
"""Information extractor for youtube.com."""
- _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?:(?:v/)|(?:(?: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'
@@ -1011,10 +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')
@@ -1034,7 +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:
@@ -1275,6 +1320,7 @@ class DailymotionIE(InfoExtractor):
# Retrieve video webpage to extract further information
request = urllib2.Request(url)
+ request.add_header('Cookie', 'family_filter=off')
try:
self.report_download_webpage(video_id)
webpage = urllib2.urlopen(request).read()
@@ -1284,25 +1330,29 @@ class DailymotionIE(InfoExtractor):
# Extract URL, uploader and title from webpage
self.report_extraction(video_id)
- mobj = re.search(r'(?i)addVariable\(\"video\"\s*,\s*\"([^\"]*)\"\)', webpage)
+ mobj = re.search(r'(?i)addVariable\(\"sequence\"\s*,\s*\"([^\"]+?)\"\)', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract media URL')
return
- mediaURL = urllib.unquote(mobj.group(1))
+ sequence = urllib.unquote(mobj.group(1))
+ mobj = re.search(r',\"sdURL\"\:\"([^\"]+?)\",', sequence)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract media URL')
+ return
+ mediaURL = urllib.unquote(mobj.group(1)).replace('\\', '')
# if needed add http://www.dailymotion.com/ if relative URL
video_url = mediaURL
- # ''
- mobj = re.search(r'(?im)
Dailymotion\s*[\-:]\s*(.+?)', webpage)
+ mobj = re.search(r'(?im)Dailymotion\s*-\s*(.+)\s*-\s*[^<]+?', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract title')
return
video_title = mobj.group(1).decode('utf-8')
video_title = sanitize_title(video_title)
- mobj = re.search(r'(?im).*?
(.+?)', webpage)
+ mobj = re.search(r'(?im)
[^<]+?]+?>([^<]+?)', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
return
@@ -2052,8 +2102,8 @@ 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
@@ -2080,14 +2130,26 @@ 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:
@@ -2116,9 +2178,11 @@ 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):
@@ -2129,9 +2193,10 @@ 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()
@@ -2143,34 +2208,63 @@ 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 = []
+ # 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))
- video_ids.extend(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))
+ 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
+
+ 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"""
@@ -2251,6 +2345,229 @@ 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'