[^<]+?]+?>([^<]+?) ', webpage)
+ if mobj is None:
+ # lookin for official user
+ mobj_official = re.search(r']+?>([^<]+?) ', webpage)
+ if mobj_official is None:
+ self._downloader.trouble(u'WARNING: unable to extract uploader nickname')
+ else:
+ video_uploader = mobj_official.group(1)
+ else:
+ video_uploader = mobj.group(1)
+
+ video_upload_date = None
+ mobj = re.search(r'([0-9]{2})-([0-9]{2})-([0-9]{4})
', webpage)
+ if mobj is not None:
+ video_upload_date = mobj.group(3) + mobj.group(2) + mobj.group(1)
+
+ return [{
+ 'id': video_id.decode('utf-8'),
+ 'url': video_url.decode('utf-8'),
+ 'uploader': video_uploader.decode('utf-8'),
+ 'upload_date': video_upload_date,
+ 'title': video_title,
+ 'ext': video_extension.decode('utf-8'),
+ }]
class GoogleIE(InfoExtractor):
- """Information extractor for video.google.com."""
-
- _VALID_URL = r'(?:http://)?video\.google\.(?:com(?:\.au)?|co\.(?:uk|jp|kr|cr)|ca|de|es|fr|it|nl|pl)/videoplay\?docid=([^\&]+).*'
- IE_NAME = u'video.google'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_webpage(self, video_id):
- """Report webpage download."""
- self._downloader.to_screen(u'[video.google] %s: Downloading webpage' % video_id)
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[video.google] %s: Extracting information' % video_id)
-
- 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
-
- # At this point we have a new video
- self._downloader.increment_downloads()
- 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&hl=en&oe=utf-8' % 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:
- video_extension = 'flv'
- mobj = re.search(r"(?i)videoUrl\\x3d(.+?)\\x26", 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'(.*) ', 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)
- simple_title = simplify_title(video_title)
-
- # Extract video description
- mobj = re.search(r'([^<]*) ', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video description')
- return
- video_description = mobj.group(1).decode('utf-8')
- if not video_description:
- video_description = 'No description available.'
-
- # Extract video thumbnail
- if self._downloader.params.get('forcethumbnail', False):
- request = urllib2.Request('http://video.google.com/videosearch?q=%s+site:video.google.com&hl=en' % abs(int(video_id)))
- 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
- mobj = re.search(r' ', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
- return
- video_thumbnail = mobj.group(1)
- else: # we need something to pass to process_info
- video_thumbnail = ''
-
- try:
- # Process video information
- self._downloader.process_info({
- 'id': video_id.decode('utf-8'),
- 'url': video_url.decode('utf-8'),
- 'uploader': u'NA',
- 'upload_date': u'NA',
- 'title': video_title,
- 'stitle': simple_title,
- 'ext': video_extension.decode('utf-8'),
- 'format': u'NA',
- 'player_url': None,
- })
- except UnavailableVideoError:
- self._downloader.trouble(u'\nERROR: unable to download video')
+ """Information extractor for video.google.com."""
+
+ _VALID_URL = r'(?:http://)?video\.google\.(?:com(?:\.au)?|co\.(?:uk|jp|kr|cr)|ca|de|es|fr|it|nl|pl)/videoplay\?docid=([^\&]+).*'
+ IE_NAME = u'video.google'
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ def report_download_webpage(self, video_id):
+ """Report webpage download."""
+ self._downloader.to_screen(u'[video.google] %s: Downloading webpage' % video_id)
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[video.google] %s: Extracting information' % video_id)
+
+ 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 = compat_urllib_request.Request('http://video.google.com/videoplay?docid=%s&hl=en&oe=utf-8' % video_id)
+ try:
+ self.report_download_webpage(video_id)
+ webpage = compat_urllib_request.urlopen(request).read()
+ except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+ self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_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:
+ video_extension = 'flv'
+ mobj = re.search(r"(?i)videoUrl\\x3d(.+?)\\x26", webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract media URL')
+ return
+ mediaURL = compat_urllib_parse.unquote(mobj.group(1))
+ mediaURL = mediaURL.replace('\\x3d', '\x3d')
+ mediaURL = mediaURL.replace('\\x26', '\x26')
+
+ video_url = mediaURL
+
+ mobj = re.search(r'(.*) ', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract title')
+ return
+ video_title = mobj.group(1).decode('utf-8')
+
+ # Extract video description
+ mobj = re.search(r'([^<]*) ', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video description')
+ return
+ video_description = mobj.group(1).decode('utf-8')
+ if not video_description:
+ video_description = 'No description available.'
+
+ # Extract video thumbnail
+ if self._downloader.params.get('forcethumbnail', False):
+ request = compat_urllib_request.Request('http://video.google.com/videosearch?q=%s+site:video.google.com&hl=en' % abs(int(video_id)))
+ try:
+ webpage = compat_urllib_request.urlopen(request).read()
+ except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+ self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
+ return
+ mobj = re.search(r' ', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
+ return
+ video_thumbnail = mobj.group(1)
+ else: # we need something to pass to process_info
+ video_thumbnail = ''
+
+ return [{
+ 'id': video_id.decode('utf-8'),
+ 'url': video_url.decode('utf-8'),
+ 'uploader': None,
+ 'upload_date': None,
+ 'title': video_title,
+ 'ext': video_extension.decode('utf-8'),
+ }]
class PhotobucketIE(InfoExtractor):
- """Information extractor for photobucket.com."""
-
- _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)'
- IE_NAME = u'photobucket'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_webpage(self, video_id):
- """Report webpage download."""
- self._downloader.to_screen(u'[photobucket] %s: Downloading webpage' % video_id)
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[photobucket] %s: Extracting information' % video_id)
-
- 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
-
- # At this point we have a new video
- self._downloader.increment_downloads()
- 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' ', 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'(.*) video by (.*) - Photobucket ', 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)
- simple_title = simplify_title(video_title)
-
- 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,
- 'upload_date': u'NA',
- 'title': video_title,
- 'stitle': simple_title,
- 'ext': video_extension.decode('utf-8'),
- 'format': u'NA',
- 'player_url': None,
- })
- except UnavailableVideoError:
- self._downloader.trouble(u'\nERROR: unable to download video')
+ """Information extractor for photobucket.com."""
+
+ _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)'
+ IE_NAME = u'photobucket'
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ def report_download_webpage(self, video_id):
+ """Report webpage download."""
+ self._downloader.to_screen(u'[photobucket] %s: Downloading webpage' % video_id)
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[photobucket] %s: Extracting information' % video_id)
+
+ 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 = compat_urllib_request.Request(url)
+ try:
+ self.report_download_webpage(video_id)
+ webpage = compat_urllib_request.urlopen(request).read()
+ except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+ self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
+ return
+
+ # Extract URL, uploader, and title from webpage
+ self.report_extraction(video_id)
+ mobj = re.search(r' ', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract media URL')
+ return
+ mediaURL = compat_urllib_parse.unquote(mobj.group(1))
+
+ video_url = mediaURL
+
+ mobj = re.search(r'(.*) video by (.*) - Photobucket ', 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')
+
+ return [{
+ 'id': video_id.decode('utf-8'),
+ 'url': video_url.decode('utf-8'),
+ 'uploader': video_uploader,
+ 'upload_date': None,
+ 'title': video_title,
+ 'ext': video_extension.decode('utf-8'),
+ }]
class YahooIE(InfoExtractor):
- """Information extractor for video.yahoo.com."""
-
- # _VALID_URL matches all Yahoo! Video URLs
- # _VPAGE_URL matches only the extractable '/watch/' URLs
- _VALID_URL = r'(?:http://)?(?:[a-z]+\.)?video\.yahoo\.com/(?:watch|network)/([0-9]+)(?:/|\?v=)([0-9]+)(?:[#\?].*)?'
- _VPAGE_URL = r'(?:http://)?video\.yahoo\.com/watch/([0-9]+)/([0-9]+)(?:[#\?].*)?'
- IE_NAME = u'video.yahoo'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_webpage(self, video_id):
- """Report webpage download."""
- self._downloader.to_screen(u'[video.yahoo] %s: Downloading webpage' % video_id)
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[video.yahoo] %s: Extracting information' % video_id)
-
- def _real_extract(self, url, new_video=True):
- # 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
-
- # At this point we have a new video
- self._downloader.increment_downloads()
- video_id = mobj.group(2)
- video_extension = 'flv'
-
- # Rewrite valid but non-extractable URLs as
- # extractable English language /watch/ URLs
- if re.match(self._VPAGE_URL, url) is None:
- request = urllib2.Request(url)
- 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
-
- mobj = re.search(r'\("id", "([0-9]+)"\);', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: Unable to extract id field')
- return
- yahoo_id = mobj.group(1)
-
- mobj = re.search(r'\("vid", "([0-9]+)"\);', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: Unable to extract vid field')
- return
- yahoo_vid = mobj.group(1)
-
- url = 'http://video.yahoo.com/watch/%s/%s' % (yahoo_vid, yahoo_id)
- return self._real_extract(url, new_video=False)
-
- # 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 uploader and title from webpage
- self.report_extraction(video_id)
- 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 = simplify_title(video_title)
-
- mobj = re.search(r'', 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)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
- return
- video_thumbnail = mobj.group(1).decode('utf-8')
-
- # Extract video description
- mobj = re.search(r' ', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video description')
- return
- video_description = mobj.group(1).decode('utf-8')
- if not video_description:
- video_description = 'No description available.'
-
- # Extract video height and width
- mobj = re.search(r' ', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video height')
- return
- yv_video_height = mobj.group(1)
-
- mobj = re.search(r' ', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video width')
- return
- yv_video_width = mobj.group(1)
-
- # Retrieve video playlist to extract media URL
- # I'm not completely sure what all these options are, but we
- # seem to need most of them, otherwise the server sends a 401.
- yv_lg = 'R0xx6idZnW2zlrKP8xxAIR' # not sure what this represents
- yv_bitrate = '700' # according to Wikipedia this is hard-coded
- request = urllib2.Request('http://cosmos.bcst.yahoo.com/up/yep/process/getPlaylistFOP.php?node_id=' + video_id +
- '&tech=flash&mode=playlist&lg=' + yv_lg + '&bitrate=' + yv_bitrate + '&vidH=' + yv_video_height +
- '&vidW=' + yv_video_width + '&swf=as3&rd=video.yahoo.com&tk=null&adsupported=v1,v2,&eventid=1301797')
- 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 media URL from playlist XML
- 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')
+
+ mobj = re.search(r'', 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)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
+ return
+ video_thumbnail = mobj.group(1).decode('utf-8')
+
+ # Extract video description
+ mobj = re.search(r' ', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video description')
+ return
+ video_description = mobj.group(1).decode('utf-8')
+ if not video_description:
+ video_description = 'No description available.'
+
+ # Extract video height and width
+ mobj = re.search(r' ', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video height')
+ return
+ yv_video_height = mobj.group(1)
+
+ mobj = re.search(r' ', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video width')
+ return
+ yv_video_width = mobj.group(1)
+
+ # Retrieve video playlist to extract media URL
+ # I'm not completely sure what all these options are, but we
+ # seem to need most of them, otherwise the server sends a 401.
+ yv_lg = 'R0xx6idZnW2zlrKP8xxAIR' # not sure what this represents
+ yv_bitrate = '700' # according to Wikipedia this is hard-coded
+ request = compat_urllib_request.Request('http://cosmos.bcst.yahoo.com/up/yep/process/getPlaylistFOP.php?node_id=' + video_id +
+ '&tech=flash&mode=playlist&lg=' + yv_lg + '&bitrate=' + yv_bitrate + '&vidH=' + yv_video_height +
+ '&vidW=' + yv_video_width + '&swf=as3&rd=video.yahoo.com&tk=null&adsupported=v1,v2,&eventid=1301797')
+ try:
+ self.report_download_webpage(video_id)
+ webpage = compat_urllib_request.urlopen(request).read()
+ except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+ self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
+ return
+
+ # Extract media URL from playlist XML
+ mobj = re.search(r' ', webpage, re.MULTILINE)
- if mobj is not None:
- video_description = mobj.group(1)
- else:
- html_parser = lxml.etree.HTMLParser()
- vwebpage_doc = lxml.etree.parse(StringIO.StringIO(webpage), html_parser)
- video_description = u''.join(vwebpage_doc.xpath('id("description")//text()')).strip()
- # TODO use another parser
-
- # Extract upload date
- video_upload_date = u'NA'
- mobj = re.search(r'[^:]*: (.*?)( \([^\(]*\))? ', webpage)
- if mobj is not None:
- video_upload_date = mobj.group(1)
-
- # Vimeo specific: extract request signature and timestamp
- sig = config['request']['signature']
- timestamp = config['request']['timestamp']
-
- # Vimeo specific: extract video codec and quality information
- # TODO bind to format param
- codecs = [('h264', 'mp4'), ('vp8', 'flv'), ('vp6', 'flv')]
- for codec in codecs:
- if codec[0] in config["video"]["files"]:
- video_codec = codec[0]
- video_extension = codec[1]
- if 'hd' in config["video"]["files"][codec[0]]: quality = 'hd'
- else: quality = 'sd'
- break
- else:
- self._downloader.trouble(u'ERROR: no known codec found')
- return
-
- video_url = "http://player.vimeo.com/play_redirect?clip_id=%s&sig=%s&time=%s&quality=%s&codecs=%s&type=moogaloop_local&embed_location=" \
- %(video_id, sig, timestamp, quality, video_codec.upper())
-
- try:
- # Process video information
- self._downloader.process_info({
- 'id': video_id,
- 'url': video_url,
- 'uploader': video_uploader,
- 'upload_date': video_upload_date,
- 'title': video_title,
- 'stitle': simple_title,
- 'ext': video_extension,
- 'thumbnail': video_thumbnail,
- 'description': video_description,
- 'player_url': None,
- })
- except UnavailableVideoError:
- self._downloader.trouble(u'ERROR: unable to download video')
+ """Information extractor for vimeo.com."""
+
+ # _VALID_URL matches Vimeo URLs
+ _VALID_URL = r'(?:https?://)?(?:(?:www|player).)?vimeo\.com/(?:(?:groups|album)/[^/]+/)?(?:videos?/)?([0-9]+)'
+ IE_NAME = u'vimeo'
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ def report_download_webpage(self, video_id):
+ """Report webpage download."""
+ 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'[vimeo] %s: Extracting information' % video_id)
+
+ def _real_extract(self, url, new_video=True):
+ # 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)
+
+ # Retrieve video webpage to extract further information
+ request = compat_urllib_request.Request(url, None, std_headers)
+ try:
+ self.report_download_webpage(video_id)
+ webpage = compat_urllib_request.urlopen(request).read()
+ except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+ self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
+ return
+
+ # 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)
+
+ # Extract the config JSON
+ config = webpage.split(' = {config:')[1].split(',assets:')[0]
+ try:
+ config = json.loads(config)
+ except:
+ self._downloader.trouble(u'ERROR: unable to extract info section')
+ return
+
+ # Extract title
+ video_title = config["video"]["title"]
+
+ # Extract uploader
+ video_uploader = config["video"]["owner"]["name"]
+
+ # Extract video thumbnail
+ video_thumbnail = config["video"]["thumbnail"]
+
+ # Extract video description
+ video_description = get_element_by_id("description", webpage.decode('utf8'))
+ if video_description: video_description = clean_html(video_description)
+ else: video_description = ''
+
+ # Extract upload date
+ video_upload_date = None
+ mobj = re.search(r'[^:]*: (.*?)( \([^\(]*\))? ', webpage)
+ if mobj is not None:
+ video_upload_date = mobj.group(1)
+
+ # Vimeo specific: extract request signature and timestamp
+ sig = config['request']['signature']
+ timestamp = config['request']['timestamp']
+
+ # Vimeo specific: extract video codec and quality information
+ # First consider quality, then codecs, then take everything
+ # TODO bind to format param
+ codecs = [('h264', 'mp4'), ('vp8', 'flv'), ('vp6', 'flv')]
+ files = { 'hd': [], 'sd': [], 'other': []}
+ for codec_name, codec_extension in codecs:
+ if codec_name in config["video"]["files"]:
+ if 'hd' in config["video"]["files"][codec_name]:
+ files['hd'].append((codec_name, codec_extension, 'hd'))
+ elif 'sd' in config["video"]["files"][codec_name]:
+ files['sd'].append((codec_name, codec_extension, 'sd'))
+ else:
+ files['other'].append((codec_name, codec_extension, config["video"]["files"][codec_name][0]))
+
+ for quality in ('hd', 'sd', 'other'):
+ if len(files[quality]) > 0:
+ video_quality = files[quality][0][2]
+ video_codec = files[quality][0][0]
+ video_extension = files[quality][0][1]
+ self._downloader.to_screen(u'[vimeo] %s: Downloading %s file at %s quality' % (video_id, video_codec.upper(), video_quality))
+ break
+ else:
+ self._downloader.trouble(u'ERROR: no known codec found')
+ return
+
+ video_url = "http://player.vimeo.com/play_redirect?clip_id=%s&sig=%s&time=%s&quality=%s&codecs=%s&type=moogaloop_local&embed_location=" \
+ %(video_id, sig, timestamp, video_quality, video_codec.upper())
+
+ return [{
+ 'id': video_id,
+ 'url': video_url,
+ 'uploader': video_uploader,
+ 'upload_date': video_upload_date,
+ 'title': video_title,
+ 'ext': video_extension,
+ 'thumbnail': video_thumbnail,
+ 'description': video_description,
+ }]
+
+
+class ArteTvIE(InfoExtractor):
+ """arte.tv information extractor."""
+
+ _VALID_URL = r'(?:http://)?videos\.arte\.tv/(?:fr|de)/videos/.*'
+ _LIVE_URL = r'index-[0-9]+\.html$'
+
+ IE_NAME = u'arte.tv'
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ def report_download_webpage(self, video_id):
+ """Report webpage download."""
+ self._downloader.to_screen(u'[arte.tv] %s: Downloading webpage' % video_id)
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[arte.tv] %s: Extracting information' % video_id)
+
+ def fetch_webpage(self, url):
+ self._downloader.increment_downloads()
+ request = compat_urllib_request.Request(url)
+ try:
+ self.report_download_webpage(url)
+ webpage = compat_urllib_request.urlopen(request).read()
+ except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+ self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
+ return
+ except ValueError as err:
+ self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+ return
+ return webpage
+
+ def grep_webpage(self, url, regex, regexFlags, matchTuples):
+ page = self.fetch_webpage(url)
+ mobj = re.search(regex, page, regexFlags)
+ info = {}
+
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+ return
+
+ for (i, key, err) in matchTuples:
+ if mobj.group(i) is None:
+ self._downloader.trouble(err)
+ return
+ else:
+ info[key] = mobj.group(i)
+
+ return info
+
+ def extractLiveStream(self, url):
+ video_lang = url.split('/')[-4]
+ info = self.grep_webpage(
+ url,
+ r'src="(.*?/videothek_js.*?\.js)',
+ 0,
+ [
+ (1, 'url', u'ERROR: Invalid URL: %s' % url)
+ ]
+ )
+ http_host = url.split('/')[2]
+ next_url = 'http://%s%s' % (http_host, compat_urllib_parse.unquote(info.get('url')))
+ info = self.grep_webpage(
+ next_url,
+ r'(s_artestras_scst_geoFRDE_' + video_lang + '.*?)\'.*?' +
+ '(http://.*?\.swf).*?' +
+ '(rtmp://.*?)\'',
+ re.DOTALL,
+ [
+ (1, 'path', u'ERROR: could not extract video path: %s' % url),
+ (2, 'player', u'ERROR: could not extract video player: %s' % url),
+ (3, 'url', u'ERROR: could not extract video url: %s' % url)
+ ]
+ )
+ video_url = u'%s/%s' % (info.get('url'), info.get('path'))
+
+ def extractPlus7Stream(self, url):
+ video_lang = url.split('/')[-3]
+ info = self.grep_webpage(
+ url,
+ r'param name="movie".*?videorefFileUrl=(http[^\'"&]*)',
+ 0,
+ [
+ (1, 'url', u'ERROR: Invalid URL: %s' % url)
+ ]
+ )
+ next_url = compat_urllib_parse.unquote(info.get('url'))
+ info = self.grep_webpage(
+ next_url,
+ r' tag: %s' % url)
+ ]
+ )
+ next_url = compat_urllib_parse.unquote(info.get('url'))
+
+ info = self.grep_webpage(
+ next_url,
+ r'.*?' +
+ '(.*?) .*?' +
+ '(.*?) .*?' +
+ '(.*?) ',
+ re.DOTALL,
+ [
+ (1, 'id', u'ERROR: could not extract video id: %s' % url),
+ (2, 'title', u'ERROR: could not extract video title: %s' % url),
+ (3, 'date', u'ERROR: could not extract video date: %s' % url),
+ (4, 'url', u'ERROR: could not extract video url: %s' % url)
+ ]
+ )
+
+ return {
+ 'id': info.get('id'),
+ 'url': compat_urllib_parse.unquote(info.get('url')),
+ 'uploader': u'arte.tv',
+ 'upload_date': info.get('date'),
+ 'title': info.get('title'),
+ 'ext': u'mp4',
+ 'format': u'NA',
+ 'player_url': None,
+ }
+
+ def _real_extract(self, url):
+ video_id = url.split('/')[-1]
+ self.report_extraction(video_id)
+
+ if re.search(self._LIVE_URL, video_id) is not None:
+ self.extractLiveStream(url)
+ return
+ else:
+ info = self.extractPlus7Stream(url)
+
+ return [info]
class GenericIE(InfoExtractor):
- """Generic last-resort information extractor."""
-
- _VALID_URL = r'.*'
- IE_NAME = u'generic'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_webpage(self, video_id):
- """Report webpage download."""
- self._downloader.to_screen(u'WARNING: Falling back on generic information extractor.')
- self._downloader.to_screen(u'[generic] %s: Downloading webpage' % video_id)
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[generic] %s: Extracting information' % video_id)
-
- def report_following_redirect(self, new_url):
- """Report information extraction."""
- self._downloader.to_screen(u'[redirect] Following redirect to %s' % new_url)
-
- def _test_redirect(self, url):
- """Check if it is a redirect, like url shorteners, in case restart chain."""
- class HeadRequest(urllib2.Request):
- def get_method(self):
- return "HEAD"
-
- class HEADRedirectHandler(urllib2.HTTPRedirectHandler):
- """
- Subclass the HTTPRedirectHandler to make it use our
- HeadRequest also on the redirected URL
- """
- def redirect_request(self, req, fp, code, msg, headers, newurl):
- if code in (301, 302, 303, 307):
- newurl = newurl.replace(' ', '%20')
- newheaders = dict((k,v) for k,v in req.headers.items()
- if k.lower() not in ("content-length", "content-type"))
- return HeadRequest(newurl,
- headers=newheaders,
- origin_req_host=req.get_origin_req_host(),
- unverifiable=True)
- else:
- raise urllib2.HTTPError(req.get_full_url(), code, msg, headers, fp)
-
- class HTTPMethodFallback(urllib2.BaseHandler):
- """
- Fallback to GET if HEAD is not allowed (405 HTTP error)
- """
- def http_error_405(self, req, fp, code, msg, headers):
- fp.read()
- fp.close()
-
- newheaders = dict((k,v) for k,v in req.headers.items()
- if k.lower() not in ("content-length", "content-type"))
- return self.parent.open(urllib2.Request(req.get_full_url(),
- headers=newheaders,
- origin_req_host=req.get_origin_req_host(),
- unverifiable=True))
-
- # Build our opener
- opener = urllib2.OpenerDirector()
- for handler in [urllib2.HTTPHandler, urllib2.HTTPDefaultErrorHandler,
- HTTPMethodFallback, HEADRedirectHandler,
- urllib2.HTTPErrorProcessor, urllib2.HTTPSHandler]:
- opener.add_handler(handler())
-
- response = opener.open(HeadRequest(url))
- new_url = response.geturl()
-
- if url == new_url: return False
-
- self.report_following_redirect(new_url)
- self._downloader.download([new_url])
- return True
-
- def _real_extract(self, url):
- if self._test_redirect(url): return
-
- # At this point we have a new video
- self._downloader.increment_downloads()
-
- video_id = url.split('/')[-1]
- 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
- except ValueError, err:
- # since this is the last-resort InfoExtractor, if
- # this error is thrown, it'll be thrown here
- self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
- return
-
- self.report_extraction(video_id)
- # Start with something easy: JW Player in SWFObject
- mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
- if mobj is None:
- # Broaden the search a little bit
- mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
- return
-
- # It's possible that one of the regexes
- # matched, but returned an empty group:
- if mobj.group(1) is None:
- self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
- return
-
- video_url = urllib.unquote(mobj.group(1))
- video_id = os.path.basename(video_url)
-
- # here's a fun little line of code for you:
- video_extension = os.path.splitext(video_id)[1][1:]
- video_id = os.path.splitext(video_id)[0]
-
- # it's tempting to parse this further, but you would
- # have to take into account all the variations like
- # Video Title - Site Name
- # Site Name | Video Title
- # Video Title - Tagline | Site Name
- # and so on and so forth; it's just not practical
- mobj = re.search(r'(.*) ', 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)
- simple_title = simplify_title(video_title)
-
- # video uploader is domain name
- mobj = re.match(r'(?:https?://)?([^/]*)/.*', url)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract title')
- return
- video_uploader = mobj.group(1).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,
- 'upload_date': u'NA',
- 'title': video_title,
- 'stitle': simple_title,
- 'ext': video_extension.decode('utf-8'),
- 'format': u'NA',
- 'player_url': None,
- })
- except UnavailableVideoError, err:
- self._downloader.trouble(u'\nERROR: unable to download video')
+ """Generic last-resort information extractor."""
+
+ _VALID_URL = r'.*'
+ IE_NAME = u'generic'
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ def report_download_webpage(self, video_id):
+ """Report webpage download."""
+ self._downloader.to_screen(u'WARNING: Falling back on generic information extractor.')
+ self._downloader.to_screen(u'[generic] %s: Downloading webpage' % video_id)
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[generic] %s: Extracting information' % video_id)
+
+ def report_following_redirect(self, new_url):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[redirect] Following redirect to %s' % new_url)
+
+ def _test_redirect(self, url):
+ """Check if it is a redirect, like url shorteners, in case restart chain."""
+ class HeadRequest(compat_urllib_request.Request):
+ def get_method(self):
+ return "HEAD"
+
+ class HEADRedirectHandler(compat_urllib_request.HTTPRedirectHandler):
+ """
+ Subclass the HTTPRedirectHandler to make it use our
+ HeadRequest also on the redirected URL
+ """
+ def redirect_request(self, req, fp, code, msg, headers, newurl):
+ if code in (301, 302, 303, 307):
+ newurl = newurl.replace(' ', '%20')
+ newheaders = dict((k,v) for k,v in req.headers.items()
+ if k.lower() not in ("content-length", "content-type"))
+ return HeadRequest(newurl,
+ headers=newheaders,
+ origin_req_host=req.get_origin_req_host(),
+ unverifiable=True)
+ else:
+ raise compat_urllib_error.HTTPError(req.get_full_url(), code, msg, headers, fp)
+
+ class HTTPMethodFallback(compat_urllib_request.BaseHandler):
+ """
+ Fallback to GET if HEAD is not allowed (405 HTTP error)
+ """
+ def http_error_405(self, req, fp, code, msg, headers):
+ fp.read()
+ fp.close()
+
+ newheaders = dict((k,v) for k,v in req.headers.items()
+ if k.lower() not in ("content-length", "content-type"))
+ return self.parent.open(compat_urllib_request.Request(req.get_full_url(),
+ headers=newheaders,
+ origin_req_host=req.get_origin_req_host(),
+ unverifiable=True))
+
+ # Build our opener
+ opener = compat_urllib_request.OpenerDirector()
+ for handler in [compat_urllib_request.HTTPHandler, compat_urllib_request.HTTPDefaultErrorHandler,
+ HTTPMethodFallback, HEADRedirectHandler,
+ compat_urllib_error.HTTPErrorProcessor, compat_urllib_request.HTTPSHandler]:
+ opener.add_handler(handler())
+
+ response = opener.open(HeadRequest(url))
+ new_url = response.geturl()
+
+ if url == new_url:
+ return False
+
+ self.report_following_redirect(new_url)
+ self._downloader.download([new_url])
+ return True
+
+ def _real_extract(self, url):
+ if self._test_redirect(url): return
+
+ video_id = url.split('/')[-1]
+ request = compat_urllib_request.Request(url)
+ try:
+ self.report_download_webpage(video_id)
+ webpage = compat_urllib_request.urlopen(request).read()
+ except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+ self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
+ return
+ except ValueError as err:
+ # since this is the last-resort InfoExtractor, if
+ # this error is thrown, it'll be thrown here
+ self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+ return
+
+ self.report_extraction(video_id)
+ # Start with something easy: JW Player in SWFObject
+ mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
+ if mobj is None:
+ # Broaden the search a little bit
+ mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+ return
+
+ # It's possible that one of the regexes
+ # matched, but returned an empty group:
+ if mobj.group(1) is None:
+ self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+ return
+
+ video_url = compat_urllib_parse.unquote(mobj.group(1))
+ video_id = os.path.basename(video_url)
+
+ # here's a fun little line of code for you:
+ video_extension = os.path.splitext(video_id)[1][1:]
+ video_id = os.path.splitext(video_id)[0]
+
+ # it's tempting to parse this further, but you would
+ # have to take into account all the variations like
+ # Video Title - Site Name
+ # Site Name | Video Title
+ # Video Title - Tagline | Site Name
+ # and so on and so forth; it's just not practical
+ mobj = re.search(r'(.*) ', 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 is domain name
+ mobj = re.match(r'(?:https?://)?([^/]*)/.*', url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract title')
+ return
+ video_uploader = mobj.group(1).decode('utf-8')
+
+ return [{
+ 'id': video_id.decode('utf-8'),
+ 'url': video_url.decode('utf-8'),
+ 'uploader': video_uploader,
+ 'upload_date': None,
+ 'title': video_title,
+ 'ext': video_extension.decode('utf-8'),
+ }]
class YoutubeSearchIE(InfoExtractor):
- """Information Extractor for YouTube search queries."""
- _VALID_URL = r'ytsearch(\d+|all)?:[\s\S]+'
- _API_URL = 'https://gdata.youtube.com/feeds/api/videos?q=%s&start-index=%i&max-results=50&v=2&alt=jsonc'
- _youtube_ie = None
- _max_youtube_results = 1000
- IE_NAME = u'youtube:search'
-
- def __init__(self, youtube_ie, downloader=None):
- InfoExtractor.__init__(self, downloader)
- self._youtube_ie = youtube_ie
-
- def report_download_page(self, query, pagenum):
- """Report attempt to download playlist page with given number."""
- query = query.decode(preferredencoding())
- self._downloader.to_screen(u'[youtube] query "%s": Downloading page %s' % (query, pagenum))
-
- def _real_initialize(self):
- self._youtube_ie.initialize()
-
- def _real_extract(self, query):
- mobj = re.match(self._VALID_URL, query)
- if mobj is None:
- self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
- return
-
- prefix, query = query.split(':')
- prefix = prefix[8:]
- query = query.encode('utf-8')
- if prefix == '':
- self._download_n_results(query, 1)
- return
- elif prefix == 'all':
- self._download_n_results(query, self._max_youtube_results)
- return
- else:
- try:
- n = long(prefix)
- if n <= 0:
- self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
- return
- elif n > self._max_youtube_results:
- self._downloader.to_stderr(u'WARNING: ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n))
- n = self._max_youtube_results
- self._download_n_results(query, n)
- return
- except ValueError: # parsing prefix as integer fails
- self._download_n_results(query, 1)
- return
-
- def _download_n_results(self, query, n):
- """Downloads a specified number of results for a query"""
-
- video_ids = []
- pagenum = 0
- limit = n
-
- while (50 * pagenum) < limit:
- self.report_download_page(query, pagenum+1)
- result_url = self._API_URL % (urllib.quote_plus(query), (50*pagenum)+1)
- request = urllib2.Request(result_url)
- try:
- data = urllib2.urlopen(request).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download API page: %s' % str(err))
- return
- api_response = json.loads(data)['data']
-
- new_ids = list(video['id'] for video in api_response['items'])
- video_ids += new_ids
-
- limit = min(n, api_response['totalItems'])
- pagenum += 1
-
- if len(video_ids) > n:
- video_ids = video_ids[:n]
- for id in video_ids:
- self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
- return
+ """Information Extractor for YouTube search queries."""
+ _VALID_URL = r'ytsearch(\d+|all)?:[\s\S]+'
+ _API_URL = 'https://gdata.youtube.com/feeds/api/videos?q=%s&start-index=%i&max-results=50&v=2&alt=jsonc'
+ _max_youtube_results = 1000
+ IE_NAME = u'youtube:search'
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ def report_download_page(self, query, pagenum):
+ """Report attempt to download search page with given number."""
+ query = query.decode(preferredencoding())
+ self._downloader.to_screen(u'[youtube] query "%s": Downloading page %s' % (query, pagenum))
+
+ def _real_extract(self, query):
+ mobj = re.match(self._VALID_URL, query)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
+ return
+
+ prefix, query = query.split(':')
+ prefix = prefix[8:]
+ query = query.encode('utf-8')
+ if prefix == '':
+ self._download_n_results(query, 1)
+ return
+ elif prefix == 'all':
+ self._download_n_results(query, self._max_youtube_results)
+ return
+ else:
+ try:
+ n = int(prefix)
+ if n <= 0:
+ self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
+ return
+ elif n > self._max_youtube_results:
+ self._downloader.to_stderr(u'WARNING: ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n))
+ n = self._max_youtube_results
+ self._download_n_results(query, n)
+ return
+ except ValueError: # parsing prefix as integer fails
+ self._download_n_results(query, 1)
+ return
+
+ def _download_n_results(self, query, n):
+ """Downloads a specified number of results for a query"""
+
+ video_ids = []
+ pagenum = 0
+ limit = n
+
+ while (50 * pagenum) < limit:
+ self.report_download_page(query, pagenum+1)
+ result_url = self._API_URL % (compat_urllib_parse.quote_plus(query), (50*pagenum)+1)
+ request = compat_urllib_request.Request(result_url)
+ try:
+ data = compat_urllib_request.urlopen(request).read()
+ except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+ self._downloader.trouble(u'ERROR: unable to download API page: %s' % compat_str(err))
+ return
+ api_response = json.loads(data)['data']
+
+ new_ids = list(video['id'] for video in api_response['items'])
+ video_ids += new_ids
+
+ limit = min(n, api_response['totalItems'])
+ pagenum += 1
+
+ if len(video_ids) > n:
+ video_ids = video_ids[:n]
+ for id in video_ids:
+ self._downloader.download(['http://www.youtube.com/watch?v=%s' % id])
+ return
class GoogleSearchIE(InfoExtractor):
- """Information Extractor for Google Video search queries."""
- _VALID_URL = r'gvsearch(\d+|all)?:[\s\S]+'
- _TEMPLATE_URL = 'http://video.google.com/videosearch?q=%s+site:video.google.com&start=%s&hl=en'
- _VIDEO_INDICATOR = r' self._max_google_results:
- self._downloader.to_stderr(u'WARNING: gvsearch returns max %i results (you requested %i)' % (self._max_google_results, n))
- n = self._max_google_results
- self._download_n_results(query, n)
- return
- except ValueError: # parsing prefix as integer fails
- self._download_n_results(query, 1)
- return
-
- def _download_n_results(self, query, n):
- """Downloads a specified number of results for a query"""
-
- video_ids = []
- pagenum = 0
-
- while True:
- self.report_download_page(query, pagenum)
- result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum*10)
- request = urllib2.Request(result_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
- for mobj in re.finditer(self._VIDEO_INDICATOR, page):
- video_id = mobj.group(1)
- if video_id not in video_ids:
- video_ids.append(video_id)
- if len(video_ids) == n:
- # Specified n videos reached
- for id in video_ids:
- self._google_ie.extract('http://video.google.com/videoplay?docid=%s' % id)
- return
-
- if re.search(self._MORE_PAGES_INDICATOR, page) is None:
- for id in video_ids:
- self._google_ie.extract('http://video.google.com/videoplay?docid=%s' % id)
- return
-
- pagenum = pagenum + 1
+ """Information Extractor for Google Video search queries."""
+ _VALID_URL = r'gvsearch(\d+|all)?:[\s\S]+'
+ _TEMPLATE_URL = 'http://video.google.com/videosearch?q=%s+site:video.google.com&start=%s&hl=en'
+ _VIDEO_INDICATOR = r' self._max_google_results:
+ self._downloader.to_stderr(u'WARNING: gvsearch returns max %i results (you requested %i)' % (self._max_google_results, n))
+ n = self._max_google_results
+ self._download_n_results(query, n)
+ return
+ except ValueError: # parsing prefix as integer fails
+ self._download_n_results(query, 1)
+ return
+
+ def _download_n_results(self, query, n):
+ """Downloads a specified number of results for a query"""
+
+ video_ids = []
+ pagenum = 0
+
+ while True:
+ self.report_download_page(query, pagenum)
+ result_url = self._TEMPLATE_URL % (compat_urllib_parse.quote_plus(query), pagenum*10)
+ request = compat_urllib_request.Request(result_url)
+ try:
+ page = compat_urllib_request.urlopen(request).read()
+ except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
+ return
+
+ # Extract video identifiers
+ for mobj in re.finditer(self._VIDEO_INDICATOR, page):
+ video_id = mobj.group(1)
+ if video_id not in video_ids:
+ video_ids.append(video_id)
+ if len(video_ids) == n:
+ # Specified n videos reached
+ for id in video_ids:
+ self._downloader.download(['http://video.google.com/videoplay?docid=%s' % id])
+ return
+
+ if re.search(self._MORE_PAGES_INDICATOR, page) is None:
+ for id in video_ids:
+ self._downloader.download(['http://video.google.com/videoplay?docid=%s' % id])
+ return
+
+ pagenum = pagenum + 1
class YahooSearchIE(InfoExtractor):
- """Information Extractor for Yahoo! Video search queries."""
- _VALID_URL = r'yvsearch(\d+|all)?:[\s\S]+'
- _TEMPLATE_URL = 'http://video.yahoo.com/search/?p=%s&o=%s'
- _VIDEO_INDICATOR = r'href="http://video\.yahoo\.com/watch/([0-9]+/[0-9]+)"'
- _MORE_PAGES_INDICATOR = r'\s*Next'
- _yahoo_ie = None
- _max_yahoo_results = 1000
- IE_NAME = u'video.yahoo:search'
-
- def __init__(self, yahoo_ie, downloader=None):
- InfoExtractor.__init__(self, downloader)
- self._yahoo_ie = yahoo_ie
-
- def report_download_page(self, query, pagenum):
- """Report attempt to download playlist page with given number."""
- query = query.decode(preferredencoding())
- self._downloader.to_screen(u'[video.yahoo] query "%s": Downloading page %s' % (query, pagenum))
-
- def _real_initialize(self):
- self._yahoo_ie.initialize()
-
- def _real_extract(self, query):
- mobj = re.match(self._VALID_URL, query)
- if mobj is None:
- self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
- return
-
- prefix, query = query.split(':')
- prefix = prefix[8:]
- query = query.encode('utf-8')
- if prefix == '':
- self._download_n_results(query, 1)
- return
- elif prefix == 'all':
- self._download_n_results(query, self._max_yahoo_results)
- return
- else:
- try:
- n = long(prefix)
- if n <= 0:
- self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
- return
- elif n > self._max_yahoo_results:
- self._downloader.to_stderr(u'WARNING: yvsearch returns max %i results (you requested %i)' % (self._max_yahoo_results, n))
- n = self._max_yahoo_results
- self._download_n_results(query, n)
- return
- except ValueError: # parsing prefix as integer fails
- self._download_n_results(query, 1)
- return
-
- def _download_n_results(self, query, n):
- """Downloads a specified number of results for a query"""
-
- video_ids = []
- already_seen = set()
- pagenum = 1
-
- while True:
- self.report_download_page(query, pagenum)
- result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
- request = urllib2.Request(result_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
- for mobj in re.finditer(self._VIDEO_INDICATOR, page):
- video_id = mobj.group(1)
- if video_id not in already_seen:
- video_ids.append(video_id)
- already_seen.add(video_id)
- if len(video_ids) == n:
- # Specified n videos reached
- for id in video_ids:
- self._yahoo_ie.extract('http://video.yahoo.com/watch/%s' % id)
- return
-
- if re.search(self._MORE_PAGES_INDICATOR, page) is None:
- for id in video_ids:
- self._yahoo_ie.extract('http://video.yahoo.com/watch/%s' % id)
- return
-
- pagenum = pagenum + 1
+ """Information Extractor for Yahoo! Video search queries."""
+ _VALID_URL = r'yvsearch(\d+|all)?:[\s\S]+'
+ _TEMPLATE_URL = 'http://video.yahoo.com/search/?p=%s&o=%s'
+ _VIDEO_INDICATOR = r'href="http://video\.yahoo\.com/watch/([0-9]+/[0-9]+)"'
+ _MORE_PAGES_INDICATOR = r'\s*Next'
+ _max_yahoo_results = 1000
+ IE_NAME = u'video.yahoo:search'
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ def report_download_page(self, query, pagenum):
+ """Report attempt to download playlist page with given number."""
+ query = query.decode(preferredencoding())
+ self._downloader.to_screen(u'[video.yahoo] query "%s": Downloading page %s' % (query, pagenum))
+
+ def _real_extract(self, query):
+ mobj = re.match(self._VALID_URL, query)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
+ return
+
+ prefix, query = query.split(':')
+ prefix = prefix[8:]
+ query = query.encode('utf-8')
+ if prefix == '':
+ self._download_n_results(query, 1)
+ return
+ elif prefix == 'all':
+ self._download_n_results(query, self._max_yahoo_results)
+ return
+ else:
+ try:
+ n = int(prefix)
+ if n <= 0:
+ self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
+ return
+ elif n > self._max_yahoo_results:
+ self._downloader.to_stderr(u'WARNING: yvsearch returns max %i results (you requested %i)' % (self._max_yahoo_results, n))
+ n = self._max_yahoo_results
+ self._download_n_results(query, n)
+ return
+ except ValueError: # parsing prefix as integer fails
+ self._download_n_results(query, 1)
+ return
+
+ def _download_n_results(self, query, n):
+ """Downloads a specified number of results for a query"""
+
+ video_ids = []
+ already_seen = set()
+ pagenum = 1
+
+ while True:
+ self.report_download_page(query, pagenum)
+ result_url = self._TEMPLATE_URL % (compat_urllib_parse.quote_plus(query), pagenum)
+ request = compat_urllib_request.Request(result_url)
+ try:
+ page = compat_urllib_request.urlopen(request).read()
+ except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
+ return
+
+ # Extract video identifiers
+ for mobj in re.finditer(self._VIDEO_INDICATOR, page):
+ video_id = mobj.group(1)
+ if video_id not in already_seen:
+ video_ids.append(video_id)
+ already_seen.add(video_id)
+ if len(video_ids) == n:
+ # Specified n videos reached
+ for id in video_ids:
+ self._downloader.download(['http://video.yahoo.com/watch/%s' % id])
+ return
+
+ if re.search(self._MORE_PAGES_INDICATOR, page) is None:
+ for id in video_ids:
+ self._downloader.download(['http://video.yahoo.com/watch/%s' % id])
+ return
+
+ pagenum = pagenum + 1
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_-]+))?.*'
- _TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en'
- _VIDEO_INDICATOR_TEMPLATE = r'/watch\?v=(.+?)&list=PL%s&'
- _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s* '
- _youtube_ie = None
- IE_NAME = u'youtube:playlist'
-
- def __init__(self, youtube_ie, downloader=None):
- InfoExtractor.__init__(self, downloader)
- self._youtube_ie = youtube_ie
-
- def report_download_page(self, playlist_id, pagenum):
- """Report attempt to download playlist page with given number."""
- self._downloader.to_screen(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum))
-
- def _real_initialize(self):
- self._youtube_ie.initialize()
-
- def _real_extract(self, url):
- # Extract playlist id
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- 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
- # 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)
- url = self._TEMPLATE_URL % (playlist_access, playlist_prefix, playlist_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(self._VIDEO_INDICATOR_TEMPLATE % playlist_id, 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
-
- playliststart = self._downloader.params.get('playliststart', 1) - 1
- playlistend = self._downloader.params.get('playlistend', -1)
- if playlistend == -1:
- video_ids = video_ids[playliststart:]
- else:
- video_ids = video_ids[playliststart:playlistend]
-
- for id in video_ids:
- self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
- return
+ """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|EC)?|PL|EC)([0-9A-Za-z-_]{10,})(?:/.*?/([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=(.+?)&([^&"]+&)*list=.*?%s'
+ _MORE_PAGES_INDICATOR = r'yt-uix-pager-next'
+ IE_NAME = u'youtube:playlist'
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ def report_download_page(self, playlist_id, pagenum):
+ """Report attempt to download playlist page with given number."""
+ self._downloader.to_screen(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum))
+
+ def _real_extract(self, url):
+ # Extract playlist id
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid url: %s' % url)
+ return
+
+ # Single video case
+ if mobj.group(3) is not None:
+ self._downloader.download([mobj.group(3)])
+ return
+
+ # Download playlist pages
+ # 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)
+ url = self._TEMPLATE_URL % (playlist_access, playlist_prefix, playlist_id, pagenum)
+ request = compat_urllib_request.Request(url)
+ try:
+ page = compat_urllib_request.urlopen(request).read()
+ except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
+ return
+
+ # Extract video identifiers
+ ids_in_page = []
+ for mobj in re.finditer(self._VIDEO_INDICATOR_TEMPLATE % playlist_id, 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
+
+ playliststart = self._downloader.params.get('playliststart', 1) - 1
+ playlistend = self._downloader.params.get('playlistend', -1)
+ if playlistend == -1:
+ video_ids = video_ids[playliststart:]
+ else:
+ video_ids = video_ids[playliststart:playlistend]
+
+ for id in video_ids:
+ self._downloader.download(['http://www.youtube.com/watch?v=%s' % id])
+ 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 = compat_urllib_request.Request(url)
+ try:
+ page = compat_urllib_request.urlopen(request).read()
+ except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_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."""
+ """Information Extractor for YouTube users."""
+
+ _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/user/)|ytuser:)([A-Za-z0-9_-]+)'
+ _TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s'
+ _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=(.+?)[\<&]'
+ IE_NAME = u'youtube:user'
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ def report_download_page(self, username, start_index):
+ """Report attempt to download user page."""
+ 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_extract(self, url):
+ # Extract username
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid url: %s' % url)
+ return
+
+ 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.
- _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/user/)|ytuser:)([A-Za-z0-9_-]+)'
- _TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s'
- _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
- IE_NAME = u'youtube:user'
+ video_ids = []
+ pagenum = 0
- def __init__(self, youtube_ie, downloader=None):
- InfoExtractor.__init__(self, downloader)
- self._youtube_ie = youtube_ie
+ while True:
+ start_index = pagenum * self._GDATA_PAGE_SIZE + 1
+ self.report_download_page(username, start_index)
- def report_download_page(self, username, start_index):
- """Report attempt to download user page."""
- self._downloader.to_screen(u'[youtube] user %s: Downloading video ids from %d to %d' %
- (username, start_index, start_index + self._GDATA_PAGE_SIZE))
+ request = compat_urllib_request.Request(self._GDATA_URL % (username, self._GDATA_PAGE_SIZE, start_index))
- def _real_initialize(self):
- self._youtube_ie.initialize()
+ try:
+ page = compat_urllib_request.urlopen(request).read()
+ except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
+ return
- def _real_extract(self, url):
- # Extract username
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- self._downloader.trouble(u'ERROR: invalid url: %s' % url)
- return
+ # Extract video identifiers
+ ids_in_page = []
- username = mobj.group(1)
+ 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))
- # 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.extend(ids_in_page)
- video_ids = []
- pagenum = 0
+ # 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.
- while True:
- start_index = pagenum * self._GDATA_PAGE_SIZE + 1
- self.report_download_page(username, start_index)
+ if len(ids_in_page) < self._GDATA_PAGE_SIZE:
+ break
- request = urllib2.Request(self._GDATA_URL % (username, self._GDATA_PAGE_SIZE, start_index))
+ pagenum += 1
- 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
+ all_ids_count = len(video_ids)
+ playliststart = self._downloader.params.get('playliststart', 1) - 1
+ playlistend = self._downloader.params.get('playlistend', -1)
- # Extract video identifiers
- ids_in_page = []
+ if playlistend == -1:
+ video_ids = video_ids[playliststart:]
+ else:
+ video_ids = video_ids[playliststart:playlistend]
- 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))
+ self._downloader.to_screen(u"[youtube] user %s: Collected %d video ids (downloading %d of them)" %
+ (username, all_ids_count, len(video_ids)))
- video_ids.extend(ids_in_page)
+ for video_id in video_ids:
+ self._downloader.download(['http://www.youtube.com/watch?v=%s' % video_id])
- # 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
+class BlipTVUserIE(InfoExtractor):
+ """Information Extractor for blip.tv users."""
- pagenum += 1
+ _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?blip\.tv/)|bliptvuser:)([^/]+)/*$'
+ _PAGE_SIZE = 12
+ IE_NAME = u'blip.tv:user'
- all_ids_count = len(video_ids)
- playliststart = self._downloader.params.get('playliststart', 1) - 1
- playlistend = self._downloader.params.get('playlistend', -1)
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
- if playlistend == -1:
- video_ids = video_ids[playliststart:]
- else:
- video_ids = video_ids[playliststart:playlistend]
+ def report_download_page(self, username, pagenum):
+ """Report attempt to download user page."""
+ self._downloader.to_screen(u'[%s] user %s: Downloading video ids from page %d' %
+ (self.IE_NAME, username, pagenum))
- self._downloader.to_screen(u"[youtube] user %s: Collected %d video ids (downloading %d of them)" %
- (username, all_ids_count, len(video_ids)))
+ def _real_extract(self, url):
+ # Extract username
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid url: %s' % url)
+ return
- for video_id in video_ids:
- self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % video_id)
+ username = mobj.group(1)
+
+ page_base = 'http://m.blip.tv/pr/show_get_full_episode_list?users_id=%s&lite=0&esi=1'
+
+ request = compat_urllib_request.Request(url)
+
+ try:
+ page = compat_urllib_request.urlopen(request).read().decode('utf-8')
+ mobj = re.search(r'data-users-id="([^"]+)"', page)
+ page_base = page_base % mobj.group(1)
+ except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+ self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
+ return
+
+
+ # Download video ids using BlipTV Ajax calls. Result size per
+ # query is limited (currently to 12 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
+
+ while True:
+ self.report_download_page(username, pagenum)
+
+ request = compat_urllib_request.Request( page_base + "&page=" + str(pagenum) )
+
+ try:
+ page = compat_urllib_request.urlopen(request).read().decode('utf-8')
+ except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as 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="/([^"]+)"', page):
+ if mobj.group(1) not in ids_in_page:
+ ids_in_page.append(unescapeHTML(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._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)
+
+ if playlistend == -1:
+ video_ids = video_ids[playliststart:]
+ else:
+ video_ids = video_ids[playliststart:playlistend]
+
+ self._downloader.to_screen(u"[%s] user %s: Collected %d video ids (downloading %d of them)" %
+ (self.IE_NAME, username, all_ids_count, len(video_ids)))
+
+ for video_id in video_ids:
+ self._downloader.download([u'http://blip.tv/'+video_id])
class DepositFilesIE(InfoExtractor):
- """Information extractor for depositfiles.com"""
-
- _VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles\.com/(?:../(?#locale))?files/(.+)'
- IE_NAME = u'DepositFiles'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_webpage(self, file_id):
- """Report webpage download."""
- self._downloader.to_screen(u'[DepositFiles] %s: Downloading webpage' % file_id)
-
- def report_extraction(self, file_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[DepositFiles] %s: Extracting information' % file_id)
-
- def _real_extract(self, url):
- # At this point we have a new file
- self._downloader.increment_downloads()
-
- file_id = url.split('/')[-1]
- # Rebuild url in english locale
- url = 'http://depositfiles.com/en/files/' + file_id
-
- # Retrieve file webpage with 'Free download' button pressed
- free_download_indication = { 'gateway_result' : '1' }
- request = urllib2.Request(url, urllib.urlencode(free_download_indication))
- try:
- self.report_download_webpage(file_id)
- webpage = urllib2.urlopen(request).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: Unable to retrieve file webpage: %s' % str(err))
- return
-
- # Search for the real file URL
- mobj = re.search(r'