sanitize_filename,
unescapeHTML,
)
+_NO_DEFAULT = object()
class InfoExtractor(object):
The dictionaries must include the following fields:
id: Video identifier.
- url: Final video URL.
title: Video title, unescaped.
- ext: Video filename extension.
- Instead of url and ext, formats can also specified.
+ Additionally, it must contain either a formats entry or url and ext:
+
+ formats: A list of dictionaries for each format available, it must
+ be ordered from worst to best quality. Potential fields:
+ * url Mandatory. The URL of the video file
+ * ext Will be calculated from url if missing
+ * format A human-readable description of the format
+ ("mp4 container with h264/opus").
+ Calculated from the format_id, width, height.
+ and format_note fields if missing.
+ * format_id A short description of the format
+ ("mp4_h264_opus" or "19")
+ * format_note Additional info about the format
+ ("3D" or "DASH video")
+ * width Width of the video, if known
+ * height Height of the video, if known
+ * abr Average audio bitrate in KBit/s
+ * acodec Name of the audio codec in use
+ * vbr Average video bitrate in KBit/s
+ * vcodec Name of the video codec in use
+ * filesize The number of bytes, if known in advance
+ * player_url SWF Player URL (used for rtmpdump).
+ url: Final video URL.
+ ext: Video filename extension.
+ format: The video format, defaults to ext (used for --get-format)
+ player_url: SWF Player URL (used for rtmpdump).
The following fields are optional:
- format: The video format, defaults to ext (used for --get-format)
thumbnails: A list of dictionaries (with the entries "resolution" and
"url") for the varying thumbnails
thumbnail: Full URL to a video thumbnail image.
upload_date: Video upload date (YYYYMMDD).
uploader_id: Nickname or id of the video uploader.
location: Physical location of the video.
- player_url: SWF Player URL (used for rtmpdump).
subtitles: The subtitle file contents as a dictionary in the format
{language: subtitles}.
+ duration: Length of the video in seconds, as an integer.
view_count: How many users have watched the video on the platform.
like_count: Number of positive ratings of the video
dislike_count: Number of negative ratings of the video
comment_count: Number of comments on the video
- urlhandle: [internal] The urlHandle to be used to download the file,
- like returned by urllib.request.urlopen
age_limit: Age restriction for the video, as an integer (years)
- formats: A list of dictionaries for each format available, it must
- be ordered from worst to best quality. Potential fields:
- * url Mandatory. The URL of the video file
- * ext Will be calculated from url if missing
- * format A human-readable description of the format
- ("mp4 container with h264/opus").
- Calculated from the format_id, width, height.
- and format_note fields if missing.
- * format_id A short description of the format
- ("mp4_h264_opus" or "19")
- * format_note Additional info about the format
- ("3D" or "DASH video")
- * width Width of the video, if known
- * height Height of the video, if known
- * abr Average audio bitrate in KBit/s
- * acodec Name of the audio codec in use
- * vbr Average video bitrate in KBit/s
- * vcodec Name of the video codec in use
- * filesize The number of bytes, if known in advance
webpage_url: The url to the video webpage, if given to youtube-dl it
should allow to get the same result again. (It will be set
by YoutubeDL if it's missing)
try:
return self._downloader.urlopen(url_or_request)
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+ if errnote is False:
+ return False
if errnote is None:
errnote = u'Unable to download webpage'
errmsg = u'%s: %s' % (errnote, compat_str(err))
self.to_screen(u'Logging in')
#Methods for following #608
- def url_result(self, url, ie=None, video_id=None):
+ @staticmethod
+ def url_result(url, ie=None, video_id=None):
"""Returns a url that points to a page that should be processed"""
#TODO: ie should be the class used for getting the info
video_info = {'_type': 'url',
if video_id is not None:
video_info['id'] = video_id
return video_info
- def playlist_result(self, entries, playlist_id=None, playlist_title=None):
+ @staticmethod
+ def playlist_result(entries, playlist_id=None, playlist_title=None):
"""Returns a playlist"""
video_info = {'_type': 'playlist',
'entries': entries}
video_info['title'] = playlist_title
return video_info
- def _search_regex(self, pattern, string, name, default=None, fatal=True, flags=0):
+ def _search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0):
"""
Perform a regex search on the given string, using a single or a list of
patterns returning the first matching group.
mobj = re.search(p, string, flags)
if mobj: break
- if sys.stderr.isatty() and os.name != 'nt':
+ if os.name != 'nt' and sys.stderr.isatty():
_name = u'\033[0;34m%s\033[0m' % name
else:
_name = name
if mobj:
# return the first matching group
return next(g for g in mobj.groups() if g is not None)
- elif default is not None:
+ elif default is not _NO_DEFAULT:
return default
elif fatal:
raise RegexNotFoundError(u'Unable to extract %s' % _name)
u'please report this issue on http://yt-dl.org/bug' % _name)
return None
- def _html_search_regex(self, pattern, string, name, default=None, fatal=True, flags=0):
+ def _html_search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0):
"""
Like _search_regex, but strips HTML tags and unescapes entities.
"""
projects / youtube-dl / blobdiff