X-Git-Url: http://git.cielonegro.org/gitweb.cgi?a=blobdiff_plain;f=youtube-dl;h=6b56f3f98f6b0e03c7d3b623ad3ff99591c2004c;hb=1c1821f8eb1b6c8f87e8038441343d887c8ef21f;hp=7262ce94d1f94d6a4cb8fe822b272f99db06b57d;hpb=a692ca7c4986cc6dd2d4c6d8091b1ed1ca0de7a7;p=youtube-dl.git

diff --git a/youtube-dl b/youtube-dl
index 7262ce94d..6b56f3f98 100755
--- a/youtube-dl
+++ b/youtube-dl
@@ -2,6 +2,7 @@
 # -*- coding: utf-8 -*-
 # Author: Ricardo Garcia Gonzalez
 # Author: Danny Colligan
+# Author: Benjamin Johnson
 # License: Public domain code
 import htmlentitydefs
 import httplib
@@ -13,11 +14,18 @@ import os.path
 import re
 import socket
 import string
+import subprocess
 import sys
 import time
 import urllib
 import urllib2
 
+# parse_qs was moved from the cgi module to the urlparse module recently.
+try:
+	from urlparse import parse_qs
+except ImportError:
+	from cgi import parse_qs
+
 std_headers = {
 	'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US; rv:1.9.1.2) Gecko/20090729 Firefox/3.5.2',
 	'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
@@ -308,10 +316,12 @@ class FileDownloader(object):
 		"""Process a single dictionary returned by an InfoExtractor."""
 		# Do nothing else if in simulate mode
 		if self.params.get('simulate', False):
-			try:
-				info_dict['url'] = self.verify_url(info_dict['url'].encode('utf-8')).decode('utf-8')
-			except (OSError, IOError, urllib2.URLError, httplib.HTTPException, socket.error), err:
-				raise UnavailableFormatError
+			# Verify URL if it's an HTTP one
+			if info_dict['url'].startswith('http'):
+				try:
+					info_dict['url'] = self.verify_url(info_dict['url'].encode('utf-8')).decode('utf-8')
+				except (OSError, IOError, urllib2.URLError, httplib.HTTPException, socket.error), err:
+					raise UnavailableFormatError
 
 			# Forced printings
 			if self.params.get('forcetitle', False):
@@ -390,7 +400,37 @@ class FileDownloader(object):
 			if info is None:
 				break
 	
+	def _download_with_rtmpdump(self, filename, url):
+		self.report_destination(filename)
+
+		# Check for rtmpdump first
+		try:
+			subprocess.call(['rtmpdump', '-h'], stdout=(file(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
+		except (OSError, IOError):
+			self.trouble(u'ERROR: RTMP download detected but "rtmpdump" could not be run')
+			return False
+
+		# Download using rtmpdump. rtmpdump returns exit code 2 when
+		# the connection was interrumpted and resuming appears to be
+		# possible. This is part of rtmpdump's normal usage, AFAIK.
+		basic_args = ['rtmpdump', '-q', '-r', url, '-o', filename]
+		retval = subprocess.call(basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)])
+		while retval == 2 or retval == 1:
+			self.to_stdout(u'\r[rtmpdump] %s bytes' % os.path.getsize(filename), skip_eol=True)
+			time.sleep(2.0) # This seems to be needed
+			retval = subprocess.call(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1])
+		if retval == 0:
+			self.to_stdout(u'\r[rtmpdump] %s bytes' % os.path.getsize(filename))
+			return True
+		else:
+			self.trouble('ERROR: rtmpdump exited with code %d' % retval)
+			return False
+
 	def _do_download(self, filename, url):
+		# Attempt to download using rtmpdump
+		if url.startswith('rtmp'):
+			return self._download_with_rtmpdump(filename, url)
+
 		stream = None
 		open_mode = 'wb'
 		basic_request = urllib2.Request(url, None, std_headers)
@@ -596,6 +636,10 @@ class YoutubeIE(InfoExtractor):
 		"""Report extracted video URL."""
 		self._downloader.to_stdout(u'[youtube] %s: Format %s not available' % (video_id, format))
 	
+	def report_rtmp_download(self):
+		"""Indicate the download will use the RTMP protocol."""
+		self._downloader.to_stdout(u'[youtube] RTMP download detected')
+	
 	def _real_initialize(self):
 		if self._downloader is None:
 			return
@@ -694,43 +738,45 @@ class YoutubeIE(InfoExtractor):
 			try:
 				self.report_video_info_webpage_download(video_id)
 				video_info_webpage = urllib2.urlopen(request).read()
+				video_info = parse_qs(video_info_webpage)
 			except (urllib2.URLError, httplib.HTTPException, socket.error), err:
 				self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err))
 				return
 			self.report_information_extraction(video_id)
 
 			# "t" param
-			mobj = re.search(r'(?m)&token=([^&]+)(?:&|$)', video_info_webpage)
-			if mobj is None:
+			if 'token' not in video_info:
 				# Attempt to see if YouTube has issued an error message
-				mobj = re.search(r'(?m)&reason=([^&]+)(?:&|$)', video_info_webpage)
-				if mobj is None:
+				if 'reason' not in video_info:
 					self._downloader.trouble(u'ERROR: unable to extract "t" parameter for unknown reason')
 					stream = open('reportme-ydl-%s.dat' % time.time(), 'wb')
 					stream.write(video_info_webpage)
 					stream.close()
 				else:
-					reason = urllib.unquote_plus(mobj.group(1))
+					reason = urllib.unquote_plus(video_info['reason'][0])
 					self._downloader.trouble(u'ERROR: YouTube said: %s' % reason.decode('utf-8'))
 				return
-			token = urllib.unquote(mobj.group(1))
+			token = urllib.unquote_plus(video_info['token'][0])
 			video_real_url = 'http://www.youtube.com/get_video?video_id=%s&t=%s&eurl=&el=detailpage&ps=default&gl=US&hl=en' % (video_id, token)
 			if format_param is not None:
 				video_real_url = '%s&fmt=%s' % (video_real_url, format_param)
 
+			# Check possible RTMP download
+			if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
+				self.report_rtmp_download()
+				video_real_url = video_info['conn'][0]
+
 			# uploader
-			mobj = re.search(r'(?m)&author=([^&]+)(?:&|$)', video_info_webpage)
-			if mobj is None:
+			if 'author' not in video_info:
 				self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
 				return
-			video_uploader = urllib.unquote(mobj.group(1))
+			video_uploader = urllib.unquote_plus(video_info['author'][0])
 
 			# title
-			mobj = re.search(r'(?m)&title=([^&]*)(?:&|$)', video_info_webpage)
-			if mobj is None:
+			if 'title' not in video_info:
 				self._downloader.trouble(u'ERROR: unable to extract video title')
 				return
-			video_title = urllib.unquote_plus(mobj.group(1))
+			video_title = urllib.unquote_plus(video_info['title'][0])
 			video_title = video_title.decode('utf-8')
 			video_title = re.sub(ur'(?u)&(.+?);', self.htmlentity_transform, video_title)
 			video_title = video_title.replace(os.sep, u'%')
@@ -894,6 +940,159 @@ class MetacafeIE(InfoExtractor):
 			self._downloader.trouble(u'ERROR: format not available for video')
 
 
+class GoogleIE(InfoExtractor):
+	"""Information extractor for video.google.com."""
+
+	_VALID_URL = r'(?:http://)?video\.google\.com/videoplay\?docid=([^\&]+).*'
+
+	def __init__(self, downloader=None):
+		InfoExtractor.__init__(self, downloader)
+
+	@staticmethod
+	def suitable(url):
+		return (re.match(GoogleIE._VALID_URL, url) is not None)
+
+	def report_download_webpage(self, video_id):
+		"""Report webpage download."""
+		self._downloader.to_stdout(u'[video.google] %s: Downloading webpage' % video_id)
+
+	def report_extraction(self, video_id):
+		"""Report information extraction."""
+		self._downloader.to_stdout(u'[video.google] %s: Extracting information' % video_id)
+
+	def _real_initialize(self):
+		return
+
+	def _real_extract(self, url):
+		# Extract id from URL
+		mobj = re.match(self._VALID_URL, url)
+		if mobj is None:
+			self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+			return
+
+		video_id = mobj.group(1)
+
+		video_extension = 'mp4'
+
+		# Retrieve video webpage to extract further information
+		request = urllib2.Request('http://video.google.com/videoplay?docid=%s' % video_id)
+		try:
+			self.report_download_webpage(video_id)
+			webpage = urllib2.urlopen(request).read()
+		except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+			self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+			return
+
+		# Extract URL, uploader, and title from webpage
+		self.report_extraction(video_id)
+		mobj = re.search(r"download_url:'(.*)'", webpage)
+		if mobj is None:
+			self._downloader.trouble(u'ERROR: unable to extract media URL')
+			return
+		mediaURL = urllib.unquote(mobj.group(1))
+		mediaURL = mediaURL.replace('\\x3d', '\x3d')
+		mediaURL = mediaURL.replace('\\x26', '\x26')
+
+		video_url = mediaURL
+
+		mobj = re.search(r'<title>(.*)</title>', webpage)
+		if mobj is None:
+			self._downloader.trouble(u'ERROR: unable to extract title')
+			return
+		video_title = mobj.group(1).decode('utf-8')
+
+		# Google Video doesn't show uploader nicknames?
+		video_uploader = 'uploader'
+
+		try:
+			# Process video information
+			self._downloader.process_info({
+				'id':		video_id.decode('utf-8'),
+				'url':		video_url.decode('utf-8'),
+				'uploader':	video_uploader.decode('utf-8'),
+				'title':	video_title.decode('utf-8'),
+				'stitle':	video_title.decode('utf-8'),
+				'ext':		video_extension.decode('utf-8'),
+			})
+		except UnavailableFormatError:
+			self._downloader.trouble(u'ERROR: format not available for video')
+
+
+class PhotobucketIE(InfoExtractor):
+	"""Information extractor for photobucket.com."""
+
+	_VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)'
+
+	def __init__(self, downloader=None):
+		InfoExtractor.__init__(self, downloader)
+
+	@staticmethod
+	def suitable(url):
+		return (re.match(PhotobucketIE._VALID_URL, url) is not None)
+
+	def report_download_webpage(self, video_id):
+		"""Report webpage download."""
+		self._downloader.to_stdout(u'[photobucket] %s: Downloading webpage' % video_id)
+
+	def report_extraction(self, video_id):
+		"""Report information extraction."""
+		self._downloader.to_stdout(u'[photobucket] %s: Extracting information' % video_id)
+
+	def _real_initialize(self):
+		return
+
+	def _real_extract(self, url):
+		# Extract id from URL
+		mobj = re.match(self._VALID_URL, url)
+		if mobj is None:
+			self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+			return
+
+		video_id = mobj.group(1)
+
+		video_extension = 'flv'
+
+		# Retrieve video webpage to extract further information
+		request = urllib2.Request(url)
+		try:
+			self.report_download_webpage(video_id)
+			webpage = urllib2.urlopen(request).read()
+		except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+			self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+			return
+
+		# Extract URL, uploader, and title from webpage
+		self.report_extraction(video_id)
+		mobj = re.search(r'<link rel="video_src" href=".*\?file=([^"]+)" />', webpage)
+		if mobj is None:
+			self._downloader.trouble(u'ERROR: unable to extract media URL')
+			return
+		mediaURL = urllib.unquote(mobj.group(1))
+
+		video_url = mediaURL
+
+		mobj = re.search(r'<title>(.*) video by (.*) - Photobucket</title>', webpage)
+		if mobj is None:
+			self._downloader.trouble(u'ERROR: unable to extract title')
+			return
+		video_title = mobj.group(1).decode('utf-8')
+
+		video_uploader = mobj.group(2).decode('utf-8')
+
+		try:
+			# Process video information
+			self._downloader.process_info({
+				'id':		video_id.decode('utf-8'),
+				'url':		video_url.decode('utf-8'),
+				'uploader':	video_uploader.decode('utf-8'),
+				'title':	video_title.decode('utf-8'),
+				'stitle':	video_title.decode('utf-8'),
+				'ext':		video_extension.decode('utf-8'),
+			})
+		except UnavailableFormatError:
+			self._downloader.trouble(u'ERROR: format not available for video')
+
+
 class YoutubeSearchIE(InfoExtractor):
 	"""Information Extractor for YouTube search queries."""
 	_VALID_QUERY = r'ytsearch(\d+|all)?:[\s\S]+'
@@ -1048,7 +1247,7 @@ class YoutubeUserIE(InfoExtractor):
 
 	_VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/user/(.*)'
 	_TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s'
-	_VIDEO_INDICATOR = r'http://gdata.youtube.com/feeds/api/videos/(.*)'
+	_VIDEO_INDICATOR = r'http://gdata.youtube.com/feeds/api/videos/(.*)' # XXX Fix this.
 	_youtube_ie = None
 
 	def __init__(self, youtube_ie, downloader=None):
@@ -1061,7 +1260,7 @@ class YoutubeUserIE(InfoExtractor):
 
 	def report_download_page(self, username):
 		"""Report attempt to download user page."""
-		self._downloader.to_stdout(u'[youtube] USR %s: Downloading page ' % (username))
+		self._downloader.to_stdout(u'[youtube] user %s: Downloading page ' % (username))
 
 	def _real_initialize(self):
 		self._youtube_ie.initialize()
@@ -1090,7 +1289,6 @@ class YoutubeUserIE(InfoExtractor):
 		ids_in_page = []
 
 		for mobj in re.finditer(self._VIDEO_INDICATOR, page):
-			print mobj.group(1)
 			if mobj.group(1) not in ids_in_page:
 				ids_in_page.append(mobj.group(1))
 		video_ids.extend(ids_in_page)
@@ -1176,7 +1374,7 @@ if __name__ == '__main__':
 		# Parse command line
 		parser = optparse.OptionParser(
 			usage='Usage: %prog [options] url...',
-			version='2009.12.26',
+			version='2010.01.06',
 			conflict_handler='resolve',
 		)
 
@@ -1273,6 +1471,8 @@ if __name__ == '__main__':
 		youtube_pl_ie = YoutubePlaylistIE(youtube_ie)
 		youtube_user_ie = YoutubeUserIE(youtube_ie)
 		youtube_search_ie = YoutubeSearchIE(youtube_ie)
+		google_ie = GoogleIE()
+		photobucket_ie = PhotobucketIE()
 
 		# File downloader
 		fd = FileDownloader({
@@ -1298,6 +1498,8 @@ if __name__ == '__main__':
 		fd.add_info_extractor(youtube_user_ie)
 		fd.add_info_extractor(metacafe_ie)
 		fd.add_info_extractor(youtube_ie)
+		fd.add_info_extractor(google_ie)
+		fd.add_info_extractor(photobucket_ie)
 
 		# Update version
 		if opts.update_self: