import os
import random
import re
-import socket
-import ssl
import sys
import time
import math
from ..compat import (
compat_cookiejar_Cookie,
- compat_cookies,
+ compat_cookies_SimpleCookie,
compat_etree_Element,
compat_etree_fromstring,
compat_getpass,
js_to_json,
JSON_LD_RE,
mimetype2ext,
+ network_exceptions,
orderedSet,
parse_bitrate,
parse_codecs,
* player_url SWF Player URL (used for rtmpdump).
* protocol The protocol that will be used for the actual
download, lower-case.
- "http", "https", "rtsp", "rtmp", "rtmpe",
+ "http", "https", "rtsp", "rtmp", "rtmp_ffmpeg", "rtmpe",
"m3u8", "m3u8_native" or "http_dash_segments".
* fragment_base_url
Base URL for fragments. Each fragment's path
uploader: Full name of the video uploader.
license: License name the video is licensed under.
creator: The creator of the video.
+ release_timestamp: UNIX timestamp of the moment the video was released.
release_date: The date (YYYYMMDD) when the video was released.
- timestamp: UNIX timestamp of the moment the video became available.
+ timestamp: UNIX timestamp of the moment the video was uploaded
upload_date: Video upload date (YYYYMMDD).
If not explicitly set, calculated from timestamp.
uploader_id: Nickname or id of the video uploader.
* "data": The subtitles file contents
* "url": A URL pointing to the subtitles file
"ext" will be calculated from URL if missing
- automatic_captions: Like 'subtitles', used by the YoutubeIE for
- automatically generated captions
+ automatic_captions: Like 'subtitles'; contains automatically generated
+ captions instead of normal subtitles
duration: Length of the video in seconds, as an integer or float.
view_count: How many users have watched the video on the platform.
like_count: Number of positive ratings of the video
playable_in_embed: Whether this video is allowed to play in embedded
players on other sites. Can be True (=always allowed),
False (=never allowed), None (=unknown), or a string
- specifying the criteria for embedability (Eg: 'whitelist').
+ specifying the criteria for embedability (Eg: 'whitelist')
+ availability: Under what condition the video is available. One of
+ 'private', 'premium_only', 'subscriber_only', 'needs_auth',
+ 'unlisted' or 'public'. Use 'InfoExtractor._availability'
+ to set it
__post_extractor: A function to be called just before the metadata is
written to either disk, logger or console. The function
must return a dict which will be added to the info_dict.
ie_result = self._real_extract(url)
if self._x_forwarded_for_ip:
ie_result['__x_forwarded_for_ip'] = self._x_forwarded_for_ip
+ subtitles = ie_result.get('subtitles')
+ if (subtitles and 'live_chat' in subtitles
+ and 'no-live-chat' in self._downloader.params.get('compat_opts')):
+ del subtitles['live_chat']
return ie_result
except GeoRestrictedError as e:
if self.__maybe_fake_ip_and_retry(e.countries):
url_or_request = update_url_query(url_or_request, query)
if data is not None or headers:
url_or_request = sanitized_Request(url_or_request, data, headers)
- exceptions = [compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error]
- if hasattr(ssl, 'CertificateError'):
- exceptions.append(ssl.CertificateError)
try:
return self._downloader.urlopen(url_or_request)
- except tuple(exceptions) as err:
+ except network_exceptions as err:
if isinstance(err, compat_urllib_error.HTTPError):
if self.__can_accept_status_code(err, expected_status):
# Retain reference to error to prevent file object from
if fatal:
raise ExtractorError(errmsg, sys.exc_info()[2], cause=err)
else:
- self._downloader.report_warning(errmsg)
+ self.report_warning(errmsg)
return False
def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True, encoding=None, data=None, headers={}, query={}, expected_status=None):
"""Report attempt to log in."""
self.to_screen('Logging in')
- @staticmethod
- def raise_login_required(msg='This video is only available for registered users'):
+ def raise_login_required(
+ self, msg='This video is only available for registered users', metadata_available=False):
+ if metadata_available and self._downloader.params.get('ignore_no_formats_error'):
+ self.report_warning(msg)
raise ExtractorError(
- '%s. Use --username and --password or --netrc to provide account credentials.' % msg,
+ '%s. Use --cookies, --username and --password or --netrc to provide account credentials' % msg,
expected=True)
- @staticmethod
- def raise_geo_restricted(msg='This video is not available from your location due to geo restriction', countries=None):
- raise GeoRestrictedError(msg, countries=countries)
+ def raise_geo_restricted(
+ self, msg='This video is not available from your location due to geo restriction',
+ countries=None, metadata_available=False):
+ if metadata_available and self._downloader.params.get('ignore_no_formats_error'):
+ self.report_warning(msg)
+ else:
+ raise GeoRestrictedError(msg, countries=countries)
+
+ def raise_no_formats(self, msg, expected=False, video_id=None):
+ if expected and self._downloader.params.get('ignore_no_formats_error'):
+ self.report_warning(msg, video_id)
+ else:
+ raise ExtractorError(msg, expected=expected, video_id=video_id)
# Methods for following #608
@staticmethod
elif fatal:
raise RegexNotFoundError('Unable to extract %s' % _name)
else:
- self._downloader.report_warning('unable to extract %s' % _name + bug_reports_message())
+ self.report_warning('unable to extract %s' % _name + bug_reports_message())
return None
def _html_search_regex(self, pattern, string, name, default=NO_DEFAULT, fatal=True, flags=0, group=None):
raise netrc.NetrcParseError(
'No authenticators for %s' % netrc_machine)
except (IOError, netrc.NetrcParseError) as err:
- self._downloader.report_warning(
+ self.report_warning(
'parsing .netrc: %s' % error_to_compat_str(err))
return username, password
elif fatal:
raise RegexNotFoundError('Unable to extract JSON-LD')
else:
- self._downloader.report_warning('unable to extract JSON-LD %s' % bug_reports_message())
+ self.report_warning('unable to extract JSON-LD %s' % bug_reports_message())
return {}
def _json_ld(self, json_ld, video_id, fatal=True, expected_type=None):
def extract_video_object(e):
assert e['@type'] == 'VideoObject'
+ author = e.get('author')
info.update({
'url': url_or_none(e.get('contentUrl')),
'title': unescapeHTML(e.get('name')),
'thumbnail': url_or_none(e.get('thumbnailUrl') or e.get('thumbnailURL')),
'duration': parse_duration(e.get('duration')),
'timestamp': unified_timestamp(e.get('uploadDate')),
- 'uploader': str_or_none(e.get('author')),
+ # author can be an instance of 'Organization' or 'Person' types.
+ # both types can have 'name' property(inherited from 'Thing' type). [1]
+ # however some websites are using 'Text' type instead.
+ # 1. https://schema.org/VideoObject
+ 'uploader': author.get('name') if isinstance(author, dict) else author if isinstance(author, compat_str) else None,
'filesize': float_or_none(e.get('contentSize')),
'tbr': int_or_none(e.get('bitrate')),
'width': int_or_none(e.get('width')),
return self._hidden_inputs(form)
class FormatSort:
- regex = r' *((?P<reverse>\+)?(?P<field>[a-zA-Z0-9_]+)((?P<seperator>[~:])(?P<limit>.*?))?)? *$'
+ regex = r' *((?P<reverse>\+)?(?P<field>[a-zA-Z0-9_]+)((?P<separator>[~:])(?P<limit>.*?))?)? *$'
default = ('hidden', 'hasvid', 'ie_pref', 'lang', 'quality',
'res', 'fps', 'codec:vp9.2', 'size', 'br', 'asr',
- 'proto', 'ext', 'has_audio', 'source', 'format_id') # These must not be aliases
+ 'proto', 'ext', 'hasaud', 'source', 'format_id') # These must not be aliases
+ ytdl_default = ('hasaud', 'quality', 'tbr', 'filesize', 'vbr',
+ 'height', 'width', 'proto', 'vext', 'abr', 'aext',
+ 'fps', 'fs_approx', 'source', 'format_id')
settings = {
'vcodec': {'type': 'ordered', 'regex': True,
'ie_pref': {'priority': True, 'type': 'extractor'},
'hasvid': {'priority': True, 'field': 'vcodec', 'type': 'boolean', 'not_in_list': ('none',)},
'hasaud': {'field': 'acodec', 'type': 'boolean', 'not_in_list': ('none',)},
- 'lang': {'priority': True, 'convert': 'ignore', 'type': 'extractor', 'field': 'language_preference'},
- 'quality': {'convert': 'float_none', 'type': 'extractor'},
+ 'lang': {'priority': True, 'convert': 'ignore', 'field': 'language_preference'},
+ 'quality': {'convert': 'float_none', 'default': -1},
'filesize': {'convert': 'bytes'},
'fs_approx': {'convert': 'bytes', 'field': 'filesize_approx'},
'id': {'convert': 'string', 'field': 'format_id'},
'vbr': {'convert': 'float_none'},
'abr': {'convert': 'float_none'},
'asr': {'convert': 'float_none'},
- 'source': {'convert': 'ignore', 'type': 'extractor', 'field': 'source_preference'},
+ 'source': {'convert': 'ignore', 'field': 'source_preference'},
'codec': {'type': 'combined', 'field': ('vcodec', 'acodec')},
'br': {'type': 'combined', 'field': ('tbr', 'vbr', 'abr'), 'same_limit': True},
if self._get_field_setting(field, 'type') == 'alias':
field = self._get_field_setting(field, 'field')
reverse = match.group('reverse') is not None
- closest = match.group('seperator') == '~'
+ closest = match.group('separator') == '~'
limit_text = match.group('limit')
has_limit = limit_text is not None
else None)
def print_verbose_info(self, to_screen):
- to_screen('[debug] Sort order given by user: %s' % ','.join(self._sort_user))
+ if self._sort_user:
+ to_screen('[debug] Sort order given by user: %s' % ', '.join(self._sort_user))
if self._sort_extractor:
to_screen('[debug] Sort order given by extractor: %s' % ', '.join(self._sort_extractor))
to_screen('[debug] Formats sorted by: %s' % ', '.join(['%s%s%s' % (
value = self._resolve_field_value(field, value, True)
# try to convert to number
- val_num = float_or_none(value)
+ val_num = float_or_none(value, default=self._get_field_setting(field, 'default'))
is_num = self._get_field_setting(field, 'convert') != 'string' and val_num is not None
if is_num:
value = val_num
def _sort_formats(self, formats, field_preference=[]):
if not formats:
+ if self._downloader.params.get('ignore_no_formats_error'):
+ return
raise ExtractorError('No video formats found')
format_sort = self.FormatSort() # params and to_screen are taken from the downloader
format_sort.evaluate_params(self._downloader.params, field_preference)
'format_note': 'Quality selection URL',
}
- def _extract_m3u8_formats(self, m3u8_url, video_id, ext=None,
- entry_protocol='m3u8', preference=None, quality=None,
- m3u8_id=None, note=None, errnote=None,
- fatal=True, live=False, data=None, headers={},
- query={}):
+ def _extract_m3u8_formats(self, *args, **kwargs):
+ fmts, subs = self._extract_m3u8_formats_and_subtitles(*args, **kwargs)
+ if subs:
+ self.report_warning(bug_reports_message(
+ "Ignoring subtitle tracks found in the HLS manifest; "
+ "if any subtitle tracks are missing,"
+ ))
+ return fmts
+
+ def _extract_m3u8_formats_and_subtitles(
+ self, m3u8_url, video_id, ext=None, entry_protocol='m3u8',
+ preference=None, quality=None, m3u8_id=None, note=None,
+ errnote=None, fatal=True, live=False, data=None, headers={},
+ query={}):
+
res = self._download_webpage_handle(
m3u8_url, video_id,
note=note or 'Downloading m3u8 information',
fatal=fatal, data=data, headers=headers, query=query)
if res is False:
- return []
+ return [], {}
m3u8_doc, urlh = res
m3u8_url = urlh.geturl()
- return self._parse_m3u8_formats(
+ return self._parse_m3u8_formats_and_subtitles(
m3u8_doc, m3u8_url, ext=ext, entry_protocol=entry_protocol,
preference=preference, quality=quality, m3u8_id=m3u8_id,
note=note, errnote=errnote, fatal=fatal, live=live, data=data,
headers=headers, query=query, video_id=video_id)
- def _parse_m3u8_formats(self, m3u8_doc, m3u8_url, ext=None,
- entry_protocol='m3u8', preference=None, quality=None,
- m3u8_id=None, live=False, note=None, errnote=None,
- fatal=True, data=None, headers={}, query={}, video_id=None):
+ def _parse_m3u8_formats_and_subtitles(
+ self, m3u8_doc, m3u8_url, ext=None, entry_protocol='m3u8',
+ preference=None, quality=None, m3u8_id=None, live=False, note=None,
+ errnote=None, fatal=True, data=None, headers={}, query={},
+ video_id=None):
+
if '#EXT-X-FAXS-CM:' in m3u8_doc: # Adobe Flash Access
- return []
+ return [], {}
- if re.search(r'#EXT-X-SESSION-KEY:.*?URI="skd://', m3u8_doc): # Apple FairPlay
- return []
+ if (not self._downloader.params.get('allow_unplayable_formats')
+ and re.search(r'#EXT-X-SESSION-KEY:.*?URI="skd://', m3u8_doc)): # Apple FairPlay
+ return [], {}
formats = []
+ subtitles = {}
+
format_url = lambda u: (
u
if re.match(r'^https?://', u)
}
formats.append(f)
- return formats
+ return formats, subtitles
groups = {}
last_stream_inf = {}
if not (media_type and group_id and name):
return
groups.setdefault(group_id, []).append(media)
+ # <https://tools.ietf.org/html/rfc8216#section-4.3.4.1>
+ if media_type == 'SUBTITLES':
+ lang = media['LANGUAGE'] # XXX: normalise?
+ url = format_url(media['URI'])
+ sub_info = {
+ 'url': url,
+ 'ext': determine_ext(url),
+ }
+ if sub_info['ext'] == 'm3u8':
+ # Per RFC 8216 §3.1, the only possible subtitle format m3u8
+ # files may contain is WebVTT:
+ # <https://tools.ietf.org/html/rfc8216#section-3.1>
+ sub_info['ext'] = 'vtt'
+ sub_info['protocol'] = 'm3u8_native'
+ subtitles.setdefault(lang, []).append(sub_info)
if media_type not in ('VIDEO', 'AUDIO'):
return
media_url = media.get('URI')
formats.append(http_f)
last_stream_inf = {}
- return formats
+ return formats, subtitles
@staticmethod
def _xpath_ns(path, namespace=None):
})
return entries
- def _extract_mpd_formats(self, mpd_url, video_id, mpd_id=None, note=None, errnote=None, fatal=True, data=None, headers={}, query={}):
+ def _extract_mpd_formats(self, *args, **kwargs):
+ fmts, subs = self._extract_mpd_formats_and_subtitles(*args, **kwargs)
+ if subs:
+ self.report_warning(bug_reports_message(
+ "Ignoring subtitle tracks found in the DASH manifest; "
+ "if any subtitle tracks are missing,"
+ ))
+ return fmts
+
+ def _extract_mpd_formats_and_subtitles(
+ self, mpd_url, video_id, mpd_id=None, note=None, errnote=None,
+ fatal=True, data=None, headers={}, query={}):
res = self._download_xml_handle(
mpd_url, video_id,
note=note or 'Downloading MPD manifest',
errnote=errnote or 'Failed to download MPD manifest',
fatal=fatal, data=data, headers=headers, query=query)
if res is False:
- return []
+ return [], {}
mpd_doc, urlh = res
if mpd_doc is None:
- return []
+ return [], {}
mpd_base_url = base_url(urlh.geturl())
- return self._parse_mpd_formats(
+ return self._parse_mpd_formats_and_subtitles(
mpd_doc, mpd_id, mpd_base_url, mpd_url)
- def _parse_mpd_formats(self, mpd_doc, mpd_id=None, mpd_base_url='', mpd_url=None):
+ def _parse_mpd_formats(self, *args, **kwargs):
+ fmts, subs = self._parse_mpd_formats_and_subtitles(*args, **kwargs)
+ if subs:
+ self.report_warning(bug_reports_message(
+ "Ignoring subtitle tracks found in the DASH manifest; "
+ "if any subtitle tracks are missing,"
+ ))
+ return fmts
+
+ def _parse_mpd_formats_and_subtitles(
+ self, mpd_doc, mpd_id=None, mpd_base_url='', mpd_url=None):
"""
Parse formats from MPD manifest.
References:
http://standards.iso.org/ittf/PubliclyAvailableStandards/c065274_ISO_IEC_23009-1_2014.zip
2. https://en.wikipedia.org/wiki/Dynamic_Adaptive_Streaming_over_HTTP
"""
- if not self._downloader.params.get('dynamic_mpd'):
+ if not self._downloader.params.get('dynamic_mpd', True):
if mpd_doc.get('type') == 'dynamic':
- return []
+ return [], {}
namespace = self._search_regex(r'(?i)^{([^}]+)?}MPD$', mpd_doc.tag, 'namespace', default=None)
mpd_duration = parse_duration(mpd_doc.get('mediaPresentationDuration'))
formats = []
+ subtitles = {}
for period in mpd_doc.findall(_add_ns('Period')):
period_duration = parse_duration(period.get('duration')) or mpd_duration
period_ms_info = extract_multisegment_info(period, {
representation_attrib.update(representation.attrib)
# According to [1, 5.3.7.2, Table 9, page 41], @mimeType is mandatory
mime_type = representation_attrib['mimeType']
- content_type = mime_type.split('/')[0]
- if content_type == 'text':
- # TODO implement WebVTT downloading
- pass
- elif content_type in ('video', 'audio'):
+ content_type = representation_attrib.get('contentType', mime_type.split('/')[0])
+
+ if content_type in ('video', 'audio', 'text'):
base_url = ''
for element in (representation, adaptation_set, period, mpd_doc):
base_url_e = element.find(_add_ns('BaseURL'))
url_el = representation.find(_add_ns('BaseURL'))
filesize = int_or_none(url_el.attrib.get('{http://youtube.com/yt/2012/10/10}contentLength') if url_el is not None else None)
bandwidth = int_or_none(representation_attrib.get('bandwidth'))
- f = {
- 'format_id': '%s-%s' % (mpd_id, representation_id) if mpd_id else representation_id,
- 'manifest_url': mpd_url,
- 'ext': mimetype2ext(mime_type),
- 'width': int_or_none(representation_attrib.get('width')),
- 'height': int_or_none(representation_attrib.get('height')),
- 'tbr': float_or_none(bandwidth, 1000),
- 'asr': int_or_none(representation_attrib.get('audioSamplingRate')),
- 'fps': int_or_none(representation_attrib.get('frameRate')),
- 'language': lang if lang not in ('mul', 'und', 'zxx', 'mis') else None,
- 'format_note': 'DASH %s' % content_type,
- 'filesize': filesize,
- 'container': mimetype2ext(mime_type) + '_dash',
- }
- f.update(parse_codecs(representation_attrib.get('codecs')))
+ if content_type in ('video', 'audio'):
+ f = {
+ 'format_id': '%s-%s' % (mpd_id, representation_id) if mpd_id else representation_id,
+ 'manifest_url': mpd_url,
+ 'ext': mimetype2ext(mime_type),
+ 'width': int_or_none(representation_attrib.get('width')),
+ 'height': int_or_none(representation_attrib.get('height')),
+ 'tbr': float_or_none(bandwidth, 1000),
+ 'asr': int_or_none(representation_attrib.get('audioSamplingRate')),
+ 'fps': int_or_none(representation_attrib.get('frameRate')),
+ 'language': lang if lang not in ('mul', 'und', 'zxx', 'mis') else None,
+ 'format_note': 'DASH %s' % content_type,
+ 'filesize': filesize,
+ 'container': mimetype2ext(mime_type) + '_dash',
+ }
+ f.update(parse_codecs(representation_attrib.get('codecs')))
+ elif content_type == 'text':
+ f = {
+ 'ext': mimetype2ext(mime_type),
+ 'manifest_url': mpd_url,
+ 'filesize': filesize,
+ }
representation_ms_info = extract_multisegment_info(representation, adaption_set_ms_info)
def prepare_template(template_name, identifiers):
else:
# Assuming direct URL to unfragmented media.
f['url'] = base_url
- formats.append(f)
+ if content_type in ('video', 'audio'):
+ formats.append(f)
+ elif content_type == 'text':
+ subtitles.setdefault(lang or 'und', []).append(f)
else:
self.report_warning('Unknown MIME type %s in DASH manifest' % mime_type)
- return formats
-
- def _extract_ism_formats(self, ism_url, video_id, ism_id=None, note=None, errnote=None, fatal=True, data=None, headers={}, query={}):
+ return formats, subtitles
+
+ def _extract_ism_formats(self, *args, **kwargs):
+ fmts, subs = self._extract_ism_formats_and_subtitles(*args, **kwargs)
+ if subs:
+ self.report_warning(bug_reports_message(
+ "Ignoring subtitle tracks found in the ISM manifest; "
+ "if any subtitle tracks are missing,"
+ ))
+ return fmts
+
+ def _extract_ism_formats_and_subtitles(self, ism_url, video_id, ism_id=None, note=None, errnote=None, fatal=True, data=None, headers={}, query={}):
res = self._download_xml_handle(
ism_url, video_id,
note=note or 'Downloading ISM manifest',
errnote=errnote or 'Failed to download ISM manifest',
fatal=fatal, data=data, headers=headers, query=query)
if res is False:
- return []
+ return [], {}
ism_doc, urlh = res
if ism_doc is None:
- return []
+ return [], {}
- return self._parse_ism_formats(ism_doc, urlh.geturl(), ism_id)
+ return self._parse_ism_formats_and_subtitles(ism_doc, urlh.geturl(), ism_id)
- def _parse_ism_formats(self, ism_doc, ism_url, ism_id=None):
+ def _parse_ism_formats_and_subtitles(self, ism_doc, ism_url, ism_id=None):
"""
Parse formats from ISM manifest.
References:
https://msdn.microsoft.com/en-us/library/ff469518.aspx
"""
if ism_doc.get('IsLive') == 'TRUE':
- return []
+ return [], {}
if (not self._downloader.params.get('allow_unplayable_formats')
and ism_doc.find('Protection') is not None):
- return []
+ return [], {}
duration = int(ism_doc.attrib['Duration'])
timescale = int_or_none(ism_doc.get('TimeScale')) or 10000000
formats = []
+ subtitles = {}
for stream in ism_doc.findall('StreamIndex'):
stream_type = stream.get('Type')
- if stream_type not in ('video', 'audio'):
+ if stream_type not in ('video', 'audio', 'text'):
continue
url_pattern = stream.attrib['Url']
stream_timescale = int_or_none(stream.get('TimeScale')) or timescale
stream_name = stream.get('Name')
+ stream_language = stream.get('Language', 'und')
for track in stream.findall('QualityLevel'):
fourcc = track.get('FourCC', 'AACL' if track.get('AudioTag') == '255' else None)
# TODO: add support for WVC1 and WMAP
- if fourcc not in ('H264', 'AVC1', 'AACL'):
+ if fourcc not in ('H264', 'AVC1', 'AACL', 'TTML'):
self.report_warning('%s is not a supported codec' % fourcc)
continue
tbr = int(track.attrib['Bitrate']) // 1000
format_id.append(stream_name)
format_id.append(compat_str(tbr))
- formats.append({
- 'format_id': '-'.join(format_id),
- 'url': ism_url,
- 'manifest_url': ism_url,
- 'ext': 'ismv' if stream_type == 'video' else 'isma',
- 'width': width,
- 'height': height,
- 'tbr': tbr,
- 'asr': sampling_rate,
- 'vcodec': 'none' if stream_type == 'audio' else fourcc,
- 'acodec': 'none' if stream_type == 'video' else fourcc,
- 'protocol': 'ism',
- 'fragments': fragments,
- '_download_params': {
- 'duration': duration,
- 'timescale': stream_timescale,
- 'width': width or 0,
- 'height': height or 0,
- 'fourcc': fourcc,
- 'codec_private_data': track.get('CodecPrivateData'),
- 'sampling_rate': sampling_rate,
- 'channels': int_or_none(track.get('Channels', 2)),
- 'bits_per_sample': int_or_none(track.get('BitsPerSample', 16)),
- 'nal_unit_length_field': int_or_none(track.get('NALUnitLengthField', 4)),
- },
- })
- return formats
+ if stream_type == 'text':
+ subtitles.setdefault(stream_language, []).append({
+ 'ext': 'ismt',
+ 'protocol': 'ism',
+ 'url': ism_url,
+ 'manifest_url': ism_url,
+ 'fragments': fragments,
+ '_download_params': {
+ 'stream_type': stream_type,
+ 'duration': duration,
+ 'timescale': stream_timescale,
+ 'fourcc': fourcc,
+ 'language': stream_language,
+ 'codec_private_data': track.get('CodecPrivateData'),
+ }
+ })
+ elif stream_type in ('video', 'audio'):
+ formats.append({
+ 'format_id': '-'.join(format_id),
+ 'url': ism_url,
+ 'manifest_url': ism_url,
+ 'ext': 'ismv' if stream_type == 'video' else 'isma',
+ 'width': width,
+ 'height': height,
+ 'tbr': tbr,
+ 'asr': sampling_rate,
+ 'vcodec': 'none' if stream_type == 'audio' else fourcc,
+ 'acodec': 'none' if stream_type == 'video' else fourcc,
+ 'protocol': 'ism',
+ 'fragments': fragments,
+ '_download_params': {
+ 'stream_type': stream_type,
+ 'duration': duration,
+ 'timescale': stream_timescale,
+ 'width': width or 0,
+ 'height': height or 0,
+ 'fourcc': fourcc,
+ 'language': stream_language,
+ 'codec_private_data': track.get('CodecPrivateData'),
+ 'sampling_rate': sampling_rate,
+ 'channels': int_or_none(track.get('Channels', 2)),
+ 'bits_per_sample': int_or_none(track.get('BitsPerSample', 16)),
+ 'nal_unit_length_field': int_or_none(track.get('NALUnitLengthField', 4)),
+ },
+ })
+ return formats, subtitles
def _parse_html5_media_entries(self, base_url, webpage, video_id, m3u8_id=None, m3u8_entry_protocol='m3u8', mpd_id=None, preference=None, quality=None):
def absolute_url(item_url):
entries.append(media_info)
return entries
- def _extract_akamai_formats(self, manifest_url, video_id, hosts={}):
+ def _extract_akamai_formats(self, *args, **kwargs):
+ fmts, subs = self._extract_akamai_formats_and_subtitles(*args, **kwargs)
+ if subs:
+ self.report_warning(bug_reports_message(
+ "Ignoring subtitle tracks found in the manifests; "
+ "if any subtitle tracks are missing,"
+ ))
+ return fmts
+
+ def _extract_akamai_formats_and_subtitles(self, manifest_url, video_id, hosts={}):
signed = 'hdnea=' in manifest_url
if not signed:
# https://learn.akamai.com/en-us/webhelp/media-services-on-demand/stream-packaging-user-guide/GUID-BE6C0F73-1E06-483B-B0EA-57984B91B7F9.html
'', manifest_url).strip('?')
formats = []
+ subtitles = {}
hdcore_sign = 'hdcore=3.7.0'
f4m_url = re.sub(r'(https?://[^/]+)/i/', r'\1/z/', manifest_url).replace('/master.m3u8', '/manifest.f4m')
hls_host = hosts.get('hls')
if hls_host:
m3u8_url = re.sub(r'(https?://)[^/]+', r'\1' + hls_host, m3u8_url)
- m3u8_formats = self._extract_m3u8_formats(
+ m3u8_formats, m3u8_subtitles = self._extract_m3u8_formats_and_subtitles(
m3u8_url, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False)
formats.extend(m3u8_formats)
+ subtitles = self._merge_subtitles(subtitles, m3u8_subtitles)
http_host = hosts.get('http')
if http_host and m3u8_formats and not signed:
formats.append(http_f)
i += 1
- return formats
+ return formats, subtitles
def _extract_wowza_formats(self, url, video_id, m3u8_entry_protocol='m3u8_native', skip_protocols=[]):
query = compat_urlparse.urlparse(url).query
if fatal:
raise ExtractorError(msg)
else:
- self._downloader.report_warning(msg)
+ self.report_warning(msg)
return res
def _float(self, v, name, fatal=False, **kwargs):
if fatal:
raise ExtractorError(msg)
else:
- self._downloader.report_warning(msg)
+ self.report_warning(msg)
return res
def _set_cookie(self, domain, name, value, expire_time=None, port=None,
self._downloader.cookiejar.set_cookie(cookie)
def _get_cookies(self, url):
- """ Return a compat_cookies.SimpleCookie with the cookies for the url """
+ """ Return a compat_cookies_SimpleCookie with the cookies for the url """
req = sanitized_Request(url)
self._downloader.cookiejar.add_cookie_header(req)
- return compat_cookies.SimpleCookie(req.get_header('Cookie'))
+ return compat_cookies_SimpleCookie(req.get_header('Cookie'))
def _apply_first_set_cookie_header(self, url_handle, cookie):
"""
return ret
@classmethod
- def _merge_subtitles(cls, subtitle_dict1, subtitle_dict2):
- """ Merge two subtitle dictionaries, language by language. """
- ret = dict(subtitle_dict1)
- for lang in subtitle_dict2:
- ret[lang] = cls._merge_subtitle_items(subtitle_dict1.get(lang, []), subtitle_dict2[lang])
- return ret
+ def _merge_subtitles(cls, *dicts, **kwargs):
+ """ Merge subtitle dictionaries, language by language. """
+
+ target = (lambda target=None: target)(**kwargs)
+ # The above lambda extracts the keyword argument 'target' from kwargs
+ # while ensuring there are no stray ones. When Python 2 support
+ # is dropped, remove it and change the function signature to:
+ #
+ # def _merge_subtitles(cls, *dicts, target=None):
+
+ if target is None:
+ target = {}
+ for d in dicts:
+ for lang, subs in d.items():
+ target[lang] = cls._merge_subtitle_items(target.get(lang, []), subs)
+ return target
def extract_automatic_captions(self, *args, **kwargs):
if (self._downloader.params.get('writeautomaticsub', False)
def _generic_title(self, url):
return compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0])
+ @staticmethod
+ def _availability(is_private, needs_premium, needs_subscription, needs_auth, is_unlisted):
+ all_known = all(map(
+ lambda x: x is not None,
+ (is_private, needs_premium, needs_subscription, needs_auth, is_unlisted)))
+ return (
+ 'private' if is_private
+ else 'premium_only' if needs_premium
+ else 'subscriber_only' if needs_subscription
+ else 'needs_auth' if needs_auth
+ else 'unlisted' if is_unlisted
+ else 'public' if all_known
+ else None)
+
class SearchInfoExtractor(InfoExtractor):
"""
if n <= 0:
raise ExtractorError('invalid download number %s for query "%s"' % (n, query))
elif n > self._MAX_RESULTS:
- self._downloader.report_warning('%s returns max %i results (you requested %i)' % (self._SEARCH_KEY, self._MAX_RESULTS, n))
+ self.report_warning('%s returns max %i results (you requested %i)' % (self._SEARCH_KEY, self._MAX_RESULTS, n))
n = self._MAX_RESULTS
return self._get_n_results(query, n)