X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2FInfoExtractors.py;h=9df521d0233d806a83e3f5abf648f2e3a22b690f;hb=fe4d68e1967cc39cc00a06c3e2e722d51b8e1419;hp=9e5ea7c61870f19ae30cea7670867584226123f8;hpb=aa85963987b610864979cfbcacfa7636a3972309;p=youtube-dl

diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py
index 9e5ea7c61..9df521d02 100644
--- a/youtube_dl/InfoExtractors.py
+++ b/youtube_dl/InfoExtractors.py
@@ -102,6 +102,7 @@ class YoutubeIE(InfoExtractor):
 	                     (?:https?://)?                                       # http(s):// (optional)
 	                     (?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/|
 	                     	tube\.majestyc\.net/)                             # the various hostnames, with wildcard subdomains
+	                     (?:.*?\#/)?                                          # handle anchor (#/) redirect urls
 	                     (?!view_play_list|my_playlists|artist|playlist)      # ignore playlist URLs
 	                     (?:                                                  # the various things that can precede the ID:
 	                         (?:(?:v|embed|e)/)                               # v/ or embed/ or e/
@@ -413,6 +414,12 @@ class YoutubeIE(InfoExtractor):
 			except Trouble as trouble:
 				self._downloader.trouble(trouble[0])
 
+		if 'length_seconds' not in video_info:
+			self._downloader.trouble(u'WARNING: unable to extract video duration')
+			video_duration = ''
+		else:
+			video_duration = urllib.unquote_plus(video_info['length_seconds'][0])
+
 		# token
 		video_token = urllib.unquote_plus(video_info['token'][0])
 
@@ -479,7 +486,8 @@ class YoutubeIE(InfoExtractor):
 				'thumbnail':	video_thumbnail.decode('utf-8'),
 				'description':	video_description,
 				'player_url':	player_url,
-				'subtitles':	video_subtitles
+				'subtitles':	video_subtitles,
+				'duration':		video_duration
 			})
 		return results
 
@@ -658,15 +666,21 @@ class DailymotionIE(InfoExtractor):
 			self._downloader.trouble(u'ERROR: unable to extract media URL')
 			return
 		flashvars = urllib.unquote(mobj.group(1))
-		if 'hqURL' in flashvars: max_quality = 'hqURL'
-		elif 'sdURL' in flashvars: max_quality = 'sdURL'
-		else: max_quality = 'ldURL'
+
+		for key in ['hd1080URL', 'hd720URL', 'hqURL', 'sdURL', 'ldURL', 'video_url']:
+			if key in flashvars:
+				max_quality = key
+				self._downloader.to_screen(u'[dailymotion] Using %s' % key)
+				break
+		else:
+			self._downloader.trouble(u'ERROR: unable to extract video URL')
+			return
+
 		mobj = re.search(r'"' + max_quality + r'":"(.+?)"', flashvars)
 		if mobj is None:
-			mobj = re.search(r'"video_url":"(.*?)",', flashvars)
-		if mobj is None:
-			self._downloader.trouble(u'ERROR: unable to extract media URL')
+			self._downloader.trouble(u'ERROR: unable to extract video URL')
 			return
+
 		video_url = urllib.unquote(mobj.group(1)).replace('\\/', '/')
 
 		# TODO: support choosing qualities
@@ -677,11 +691,12 @@ class DailymotionIE(InfoExtractor):
 			return
 		video_title = unescapeHTML(mobj.group('title').decode('utf-8'))
 
-		mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a></span>', webpage)
+		video_uploader = u'NA'
+		mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a>', webpage)
 		if mobj is None:
-			self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
-			return
-		video_uploader = mobj.group(1)
+			self._downloader.trouble(u'WARNING: unable to extract uploader nickname')
+		else:
+			video_uploader = mobj.group(1)
 
 		video_upload_date = u'NA'
 		mobj = re.search(r'<div class="[^"]*uploaded_cont[^"]*" title="[^"]*">([0-9]{2})-([0-9]{2})-([0-9]{4})</div>', webpage)
@@ -1501,9 +1516,9 @@ class YahooSearchIE(InfoExtractor):
 class YoutubePlaylistIE(InfoExtractor):
 	"""Information Extractor for YouTube playlists."""
 
-	_VALID_URL = r'(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:course|view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)(?:PL)?([0-9A-Za-z-_]+)(?:/.*?/([0-9A-Za-z_-]+))?.*'
+	_VALID_URL = r'(?:(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:course|view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)(?:PL|EC)?|PL|EC)([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_TEMPLATE = r'/watch\?v=(.+?)&amp;list=.*?%s'
+	_VIDEO_INDICATOR_TEMPLATE = r'/watch\?v=(.+?)&amp;([^&"]+&amp;)*list=.*?%s'
 	_MORE_PAGES_INDICATOR = r'yt-uix-pager-next'
 	IE_NAME = u'youtube:playlist'
 
@@ -1571,6 +1586,56 @@ class YoutubePlaylistIE(InfoExtractor):
 		return
 
 
+class YoutubeChannelIE(InfoExtractor):
+	"""Information Extractor for YouTube channels."""
+
+	_VALID_URL = r"^(?:https?://)?(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/([0-9A-Za-z_-]+)(?:/.*)?$"
+	_TEMPLATE_URL = 'http://www.youtube.com/channel/%s/videos?sort=da&flow=list&view=0&page=%s&gl=US&hl=en'
+	_MORE_PAGES_INDICATOR = r'yt-uix-button-content">Next' # TODO
+	IE_NAME = u'youtube:channel'
+
+	def report_download_page(self, channel_id, pagenum):
+		"""Report attempt to download channel page with given number."""
+		self._downloader.to_screen(u'[youtube] Channel %s: Downloading page #%s' % (channel_id, pagenum))
+
+	def _real_extract(self, url):
+		# Extract channel id
+		mobj = re.match(self._VALID_URL, url)
+		if mobj is None:
+			self._downloader.trouble(u'ERROR: invalid url: %s' % url)
+			return
+
+		# Download channel pages
+		channel_id = mobj.group(1)
+		video_ids = []
+		pagenum = 1
+
+		while True:
+			self.report_download_page(channel_id, pagenum)
+			url = self._TEMPLATE_URL % (channel_id, pagenum)
+			request = urllib2.Request(url)
+			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(r'href="/watch\?v=([0-9A-Za-z_-]+)&', page):
+				if mobj.group(1) not in ids_in_page:
+					ids_in_page.append(mobj.group(1))
+			video_ids.extend(ids_in_page)
+
+			if re.search(self._MORE_PAGES_INDICATOR, page) is None:
+				break
+			pagenum = pagenum + 1
+
+		for id in video_ids:
+			self._downloader.download(['http://www.youtube.com/watch?v=%s' % id])
+		return
+
+
 class YoutubeUserIE(InfoExtractor):
 	"""Information Extractor for YouTube users."""
 
@@ -3174,3 +3239,127 @@ class XNXXIE(InfoExtractor):
 				'player_url': None}
 
 		return [info]
+
+
+class GooglePlusIE(InfoExtractor):
+	"""Information extractor for plus.google.com."""
+
+	_VALID_URL = r'(?:https://)?plus\.google\.com/(?:\w+/)*?(\d+)/posts/(\w+)'
+	IE_NAME = u'plus.google'
+
+	def __init__(self, downloader=None):
+		InfoExtractor.__init__(self, downloader)
+
+	def report_extract_entry(self, url):
+		"""Report downloading extry"""
+		self._downloader.to_screen(u'[plus.google] Downloading entry: %s' % url.decode('utf-8'))
+
+	def report_date(self, upload_date):
+		"""Report downloading extry"""
+		self._downloader.to_screen(u'[plus.google] Entry date: %s' % upload_date)
+
+	def report_uploader(self, uploader):
+		"""Report downloading extry"""
+		self._downloader.to_screen(u'[plus.google] Uploader: %s' % uploader.decode('utf-8'))
+
+	def report_title(self, video_title):
+		"""Report downloading extry"""
+		self._downloader.to_screen(u'[plus.google] Title: %s' % video_title.decode('utf-8'))
+
+	def report_extract_vid_page(self, video_page):
+		"""Report information extraction."""
+		self._downloader.to_screen(u'[plus.google] Extracting video page: %s' % video_page.decode('utf-8'))
+
+	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
+
+		post_url = mobj.group(0)
+		video_id = mobj.group(2)
+
+		video_extension = 'flv'
+
+		# Step 1, Retrieve post webpage to extract further information
+		self.report_extract_entry(post_url)
+		request = urllib2.Request(post_url)
+		try:
+			webpage = urllib2.urlopen(request).read()
+		except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+			self._downloader.trouble(u'ERROR: Unable to retrieve entry webpage: %s' % str(err))
+			return
+
+		# Extract update date
+		upload_date = u'NA'
+		pattern = 'title="Timestamp">(.*?)</a>'
+		mobj = re.search(pattern, webpage)
+		if mobj:
+			upload_date = mobj.group(1)
+			# Convert timestring to a format suitable for filename
+			upload_date = datetime.datetime.strptime(upload_date, "%Y-%m-%d")
+			upload_date = upload_date.strftime('%Y%m%d')
+		self.report_date(upload_date)
+
+		# Extract uploader
+		uploader = u'NA'
+		pattern = r'rel\="author".*?>(.*?)</a>'
+		mobj = re.search(pattern, webpage)
+		if mobj:
+			uploader = mobj.group(1)
+		self.report_uploader(uploader)
+
+		# Extract title
+		# Get the first line for title
+		video_title = u'NA'
+		pattern = r'<meta name\=\"Description\" content\=\"(.*?)[\n<"]'
+		mobj = re.search(pattern, webpage)
+		if mobj:
+			video_title = mobj.group(1)
+		self.report_title(video_title)
+
+		# Step 2, Stimulate clicking the image box to launch video
+		pattern = '"(https\://plus\.google\.com/photos/.*?)",,"image/jpeg","video"\]'
+		mobj = re.search(pattern, webpage)
+		if mobj is None:
+			self._downloader.trouble(u'ERROR: unable to extract video page URL')
+
+		video_page = mobj.group(1)
+		request = urllib2.Request(video_page)
+		try:
+			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
+		self.report_extract_vid_page(video_page)
+
+
+		# Extract video links on video page
+		"""Extract video links of all sizes"""
+		pattern = '\d+,\d+,(\d+),"(http\://redirector\.googlevideo\.com.*?)"'
+		mobj = re.findall(pattern, webpage)
+		if len(mobj) == 0:
+			self._downloader.trouble(u'ERROR: unable to extract video links')
+
+		# Sort in resolution
+		links = sorted(mobj)
+
+		# Choose the lowest of the sort, i.e. highest resolution
+		video_url = links[-1]
+		# Only get the url. The resolution part in the tuple has no use anymore
+		video_url = video_url[-1]
+		# Treat escaped \u0026 style hex
+		video_url = unicode(video_url, "unicode_escape")
+
+
+		return [{
+			'id':		video_id.decode('utf-8'),
+			'url':		video_url,
+			'uploader':	uploader.decode('utf-8'),
+			'upload_date':	upload_date.decode('utf-8'),
+			'title':	video_title.decode('utf-8'),
+			'ext':		video_extension.decode('utf-8'),
+			'format':	u'NA',
+			'player_url':	None,
+		}]