class YoutubeIE(InfoExtractor):
"""Information extractor for youtube.com."""
- _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/|tube\.majestyc\.net/)(?!view_play_list|my_playlists|artist|playlist)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))?)?([0-9A-Za-z_-]+)(?(1).+)?$'
+ _VALID_URL = r"""^
+ (
+ (?:https?://)? # http(s):// (optional)
+ (?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/|
+ tube\.majestyc\.net/) # the various hostnames, with wildcard subdomains
+ (?!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/
+ |(?: # or the v= param in all its forms
+ (?:watch(?:_popup)?(?:\.php)?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
+ (?:\?|\#!?) # the params delimiter ? or # or #!
+ (?:.+&)? # any other preceding param (like /?s=tuff&v=xxxx)
+ v=
+ )
+ )? # optional -> youtube.com/xxxx is OK
+ )? # all until now is optional -> you can pass the naked ID
+ ([0-9A-Za-z_-]+) # here is it! the YouTube video ID
+ (?(1).+)? # if we found the ID, everything can follow
+ $"""
_LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
_LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en'
_AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
}
IE_NAME = u'youtube'
+ def suitable(self, url):
+ """Receives a URL and returns True if suitable for this IE."""
+ return re.match(self._VALID_URL, url, re.VERBOSE) is not None
+
def report_lang(self):
"""Report attempt to set language."""
self._downloader.to_screen(u'[youtube] Setting language')
url = 'http://www.youtube.com/' + urllib.unquote(mobj.group(1)).lstrip('/')
# Extract video id from URL
- mobj = re.match(self._VALID_URL, url)
+ mobj = re.match(self._VALID_URL, url, re.VERBOSE)
if mobj is None:
self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
return
url_data_strs = video_info['url_encoded_fmt_stream_map'][0].split(',')
url_data = [parse_qs(uds) for uds in url_data_strs]
url_data = filter(lambda ud: 'itag' in ud and 'url' in ud, url_data)
- url_map = dict((ud['itag'][0], ud['url'][0]) for ud in url_data)
+ url_map = dict((ud['itag'][0], ud['url'][0] + '&signature=' + ud['sig'][0]) for ud in url_data)
format_limit = self._downloader.params.get('format_limit', None)
available_formats = self._available_formats_prefer_free if self._downloader.params.get('prefer_free_formats', False) else self._available_formats
class DailymotionIE(InfoExtractor):
"""Information Extractor for Dailymotion"""
- _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^_/]+)_([^/]+)'
+ _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^/]+)'
IE_NAME = u'dailymotion'
def __init__(self, downloader=None):
self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
return
- video_id = mobj.group(1)
+ video_id = mobj.group(1).split('_')[0].split('?')[0]
- video_extension = 'flv'
+ video_extension = 'mp4'
# Retrieve video webpage to extract further information
request = urllib2.Request(url)
# Extract URL, uploader and title from webpage
self.report_extraction(video_id)
- mobj = re.search(r'(?i)addVariable\(\"sequence\"\s*,\s*\"([^\"]+?)\"\)', webpage)
+ mobj = re.search(r'\s*var flashvars = (.*)', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract media URL')
return
- sequence = urllib.unquote(mobj.group(1))
- mobj = re.search(r',\"sdURL\"\:\"([^\"]+?)\",', sequence)
+ flashvars = urllib.unquote(mobj.group(1))
+ if 'hqURL' in flashvars: max_quality = 'hqURL'
+ elif 'sdURL' in flashvars: max_quality = 'sdURL'
+ else: max_quality = 'ldURL'
+ 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')
return
- mediaURL = urllib.unquote(mobj.group(1)).replace('\\', '')
-
- # if needed add http://www.dailymotion.com/ if relative URL
+ video_url = urllib.unquote(mobj.group(1)).replace('\\/', '/')
- video_url = mediaURL
+ # TODO: support choosing qualities
mobj = re.search(r'<meta property="og:title" content="(?P<title>[^"]*)" />', webpage)
if mobj is None:
return
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)
+ 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': u'NA',
+ 'upload_date': video_upload_date,
'title': video_title,
'ext': video_extension.decode('utf-8'),
'format': u'NA',
_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&'
+ _VIDEO_INDICATOR_TEMPLATE = r'/watch\?v=(.+?)&list=.*?%s'
_MORE_PAGES_INDICATOR = r'yt-uix-pager-next'
IE_NAME = u'youtube:playlist'
"""Report information extraction"""
self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
- def extract_video_url(self, webpage):
- "Extract the url for the video from the webpage"
-
- result = re.search(self.VIDEO_URL_RE, webpage)
- if result is None:
- self._downloader.trouble(u'ERROR: unable to extract video url')
- return urllib.unquote(result.group(1).decode('utf-8'))
-
- def extract_video_title(self, webpage):
- "Extract the title for the video from the webpage"
-
- result = re.search(self.VIDEO_TITLE_RE, webpage)
- if result is None:
- self._downloader.trouble(u'ERROR: unable to extract video title')
- return result.group(1).decode('utf-8')
-
- def extract_video_thumbnail(self, webpage):
- "Extract the thumbnail for the video from the webpage"
-
- result = re.search(self.VIDEO_THUMB_RE, webpage)
- if result is None:
- self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
- return result.group(1).decode('utf-8')
-
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % err)
return
+ result = re.search(self.VIDEO_URL_RE, webpage)
+ if result is None:
+ self._downloader.trouble(u'ERROR: unable to extract video url')
+ return
+ video_url = urllib.unquote(result.group(1).decode('utf-8'))
+
+ result = re.search(self.VIDEO_TITLE_RE, webpage)
+ if result is None:
+ self._downloader.trouble(u'ERROR: unable to extract video title')
+ return
+ video_title = result.group(1).decode('utf-8')
+
+ result = re.search(self.VIDEO_THUMB_RE, webpage)
+ if result is None:
+ self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
+ return
+ video_thumbnail = result.group(1).decode('utf-8')
+
info = {'id': video_id,
- 'url': self.extract_video_url(webpage),
+ 'url': video_url,
'uploader': None,
'upload_date': None,
- 'title': self.extract_video_title(webpage),
+ 'title': video_title,
'ext': 'flv',
'format': 'flv',
- 'thumbnail': self.extract_video_thumbnail(webpage),
+ 'thumbnail': video_thumbnail,
'description': None,
'player_url': None}
- return [info]
\ No newline at end of file
+ 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,
+ }]
projects / youtube-dl / blobdiff