1
0
mirror of https://github.com/l1ving/youtube-dl synced 2025-01-24 09:32:52 +08:00

Merge remote-tracking branch 'upstream/master'

This commit is contained in:
Petr Novak 2 2017-12-19 12:05:47 +01:00
commit d4be9c663e
28 changed files with 482 additions and 300 deletions

View File

@ -6,8 +6,8 @@
---
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.12.10*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.12.10**
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.12.14*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.12.14**
### Before submitting an *issue* make sure you have:
- [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
@ -35,7 +35,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl
[debug] User config: []
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
[debug] youtube-dl version 2017.12.10
[debug] youtube-dl version 2017.12.14
[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
[debug] Proxy map: {}

View File

@ -1,3 +1,23 @@
version 2017.12.14
Core
* [postprocessor/xattr] Clarify NO_SPACE message (#14970)
* [downloader/http] Return actual download result from real_download (#14971)
Extractors
+ [itv] Extract more subtitles and duration
* [itv] Improve extraction (#14944)
+ [byutv] Add support for geo restricted videos
* [byutv] Fix extraction (#14966, #14967)
+ [bbccouk] Fix extraction for 320k HLS streams
+ [toutv] Add support for special video URLs (#14179)
* [discovery] Fix free videos extraction (#14157, #14954)
* [tvnow] Fix extraction (#7831)
+ [nickelodeon:br] Add support for nickelodeon brazil websites (#14893)
* [nick] Improve extraction (#14876)
* [tbs] Fix extraction (#13658)
version 2017.12.10
Core

View File

@ -539,6 +539,8 @@ The basic usage is not to set any template arguments when downloading a single f
- `playlist_index` (numeric): Index of the video in the playlist padded with leading zeros according to the total length of the playlist
- `playlist_id` (string): Playlist identifier
- `playlist_title` (string): Playlist title
- `playlist_uploader` (string): Full name of the playlist uploader
- `playlist_uploader_id` (string): Nickname or id of the playlist uploader
Available for the video that belongs to some logical chapter or section:

View File

@ -122,7 +122,6 @@
- **bt:vestlendingen**: Bergens Tidende - Vestlendingen
- **BuzzFeed**
- **BYUtv**
- **BYUtvEvent**
- **Camdemy**
- **CamdemyFolder**
- **CamWithHer**
@ -538,6 +537,7 @@
- **nhl.com:videocenter:category**: NHL videocenter category
- **nick.com**
- **nick.de**
- **nickelodeon:br**
- **nickelodeonru**
- **nicknight**
- **niconico**: ニコニコ動画
@ -556,8 +556,6 @@
- **nowness**
- **nowness:playlist**
- **nowness:series**
- **NowTV** (Currently broken)
- **NowTVList**
- **nowvideo**: NowVideo
- **Noz**
- **npo**: npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl
@ -794,7 +792,7 @@
- **tagesschau:player**
- **Tass**
- **TastyTrade**
- **TBS** (Currently broken)
- **TBS**
- **TDSLifeway**
- **teachertube**: teachertube.com videos
- **teachertube:user:collection**: teachertube.com user and collection videos
@ -865,6 +863,8 @@
- **tvland.com**
- **TVN24**
- **TVNoe**
- **TVNow**
- **TVNowList**
- **tvp**: Telewizja Polska
- **tvp:embed**: Telewizja Polska
- **tvp:series**

View File

@ -343,6 +343,7 @@ class TestUtil(unittest.TestCase):
self.assertEqual(unified_timestamp('Feb 7, 2016 at 6:35 pm'), 1454870100)
self.assertEqual(unified_timestamp('2017-03-30T17:52:41Q'), 1490896361)
self.assertEqual(unified_timestamp('Sep 11, 2013 | 5:49 AM'), 1378878540)
self.assertEqual(unified_timestamp('December 15, 2017 at 7:49 am'), 1513324140)
def test_determine_ext(self):
self.assertEqual(determine_ext('http://example.com/foo/bar.mp4/?download'), 'mp4')

View File

@ -975,6 +975,8 @@ class YoutubeDL(object):
'playlist': playlist,
'playlist_id': ie_result.get('id'),
'playlist_title': ie_result.get('title'),
'playlist_uploader': ie_result.get('uploader'),
'playlist_uploader_id': ie_result.get('uploader_id'),
'playlist_index': i + playliststart,
'extractor': ie_result['extractor'],
'webpage_url': ie_result['webpage_url'],

View File

@ -112,7 +112,7 @@ class FragmentFD(FileDownloader):
if self.__do_ytdl_file(ctx):
self._write_ytdl_file(ctx)
if not self.params.get('keep_fragments', False):
os.remove(ctx['fragment_filename_sanitized'])
os.remove(encodeFilename(ctx['fragment_filename_sanitized']))
del ctx['fragment_filename_sanitized']
def _prepare_frag_download(self, ctx):

View File

@ -284,8 +284,7 @@ class HttpFD(FileDownloader):
while count <= retries:
try:
establish_connection()
download()
return True
return download()
except RetryDownload as e:
count += 1
if count <= retries:

View File

@ -228,10 +228,19 @@ class AfreecaTVIE(InfoExtractor):
r'^(\d{8})_', key, 'upload date', default=None)
file_duration = int_or_none(file_element.get('duration'))
format_id = key if key else '%s_%s' % (video_id, file_num)
formats = self._extract_m3u8_formats(
file_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls',
note='Downloading part %d m3u8 information' % file_num)
if determine_ext(file_url) == 'm3u8':
formats = self._extract_m3u8_formats(
file_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls',
note='Downloading part %d m3u8 information' % file_num)
else:
formats = [{
'url': file_url,
'format_id': 'http',
}]
if not formats:
continue
self._sort_formats(formats)
file_info = common_entry.copy()
file_info.update({
'id': format_id,

View File

@ -0,0 +1,78 @@
# coding: utf-8
from __future__ import unicode_literals
import datetime
import hashlib
import hmac
from .common import InfoExtractor
from ..compat import compat_urllib_parse_urlencode
class AWSIE(InfoExtractor):
_AWS_ALGORITHM = 'AWS4-HMAC-SHA256'
_AWS_REGION = 'us-east-1'
def _aws_execute_api(self, aws_dict, video_id, query=None):
query = query or {}
amz_date = datetime.datetime.utcnow().strftime('%Y%m%dT%H%M%SZ')
date = amz_date[:8]
headers = {
'Accept': 'application/json',
'Host': self._AWS_PROXY_HOST,
'X-Amz-Date': amz_date,
}
session_token = aws_dict.get('session_token')
if session_token:
headers['X-Amz-Security-Token'] = session_token
headers['X-Api-Key'] = self._AWS_API_KEY
def aws_hash(s):
return hashlib.sha256(s.encode('utf-8')).hexdigest()
# Task 1: http://docs.aws.amazon.com/general/latest/gr/sigv4-create-canonical-request.html
canonical_querystring = compat_urllib_parse_urlencode(query)
canonical_headers = ''
for header_name, header_value in headers.items():
canonical_headers += '%s:%s\n' % (header_name.lower(), header_value)
signed_headers = ';'.join([header.lower() for header in headers.keys()])
canonical_request = '\n'.join([
'GET',
aws_dict['uri'],
canonical_querystring,
canonical_headers,
signed_headers,
aws_hash('')
])
# Task 2: http://docs.aws.amazon.com/general/latest/gr/sigv4-create-string-to-sign.html
credential_scope_list = [date, self._AWS_REGION, 'execute-api', 'aws4_request']
credential_scope = '/'.join(credential_scope_list)
string_to_sign = '\n'.join([self._AWS_ALGORITHM, amz_date, credential_scope, aws_hash(canonical_request)])
# Task 3: http://docs.aws.amazon.com/general/latest/gr/sigv4-calculate-signature.html
def aws_hmac(key, msg):
return hmac.new(key, msg.encode('utf-8'), hashlib.sha256)
def aws_hmac_digest(key, msg):
return aws_hmac(key, msg).digest()
def aws_hmac_hexdigest(key, msg):
return aws_hmac(key, msg).hexdigest()
k_signing = ('AWS4' + aws_dict['secret_key']).encode('utf-8')
for value in credential_scope_list:
k_signing = aws_hmac_digest(k_signing, value)
signature = aws_hmac_hexdigest(k_signing, string_to_sign)
# Task 4: http://docs.aws.amazon.com/general/latest/gr/sigv4-add-signature-to-request.html
headers['Authorization'] = ', '.join([
'%s Credential=%s/%s' % (self._AWS_ALGORITHM, aws_dict['access_key'], credential_scope),
'SignedHeaders=%s' % signed_headers,
'Signature=%s' % signature,
])
return self._download_json(
'https://%s%s%s' % (self._AWS_PROXY_HOST, aws_dict['uri'], '?' + canonical_querystring if canonical_querystring else ''),
video_id, headers=headers)

View File

@ -3,20 +3,19 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import ExtractorError
class BYUtvIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?byutv\.org/watch/(?!event/)(?P<id>[0-9a-f-]+)(?:/(?P<display_id>[^/?#&]+))?'
_VALID_URL = r'https?://(?:www\.)?byutv\.org/(?:watch|player)/(?!event/)(?P<id>[0-9a-f-]+)(?:/(?P<display_id>[^/?#&]+))?'
_TESTS = [{
'url': 'http://www.byutv.org/watch/6587b9a3-89d2-42a6-a7f7-fd2f81840a7d/studio-c-season-5-episode-5',
'info_dict': {
'id': '6587b9a3-89d2-42a6-a7f7-fd2f81840a7d',
'id': 'ZvanRocTpW-G5_yZFeltTAMv6jxOU9KH',
'display_id': 'studio-c-season-5-episode-5',
'ext': 'mp4',
'title': 'Season 5 Episode 5',
'description': 'md5:e07269172baff037f8e8bf9956bc9747',
'thumbnail': r're:^https?://.*\.jpg$',
'description': 'md5:1d31dc18ef4f075b28f6a65937d22c65',
'thumbnail': r're:^https?://.*',
'duration': 1486.486,
},
'params': {
@ -26,6 +25,9 @@ class BYUtvIE(InfoExtractor):
}, {
'url': 'http://www.byutv.org/watch/6587b9a3-89d2-42a6-a7f7-fd2f81840a7d',
'only_matching': True,
}, {
'url': 'https://www.byutv.org/player/27741493-dc83-40b0-8420-e7ae38a2ae98/byu-football-toledo-vs-byu-93016?listid=4fe0fee5-0d3c-4a29-b725-e4948627f472&listindex=0&q=toledo',
'only_matching': True,
}]
def _real_extract(self, url):
@ -33,16 +35,16 @@ class BYUtvIE(InfoExtractor):
video_id = mobj.group('id')
display_id = mobj.group('display_id') or video_id
webpage = self._download_webpage(url, display_id)
episode_code = self._search_regex(
r'(?s)episode:(.*?\}),\s*\n', webpage, 'episode information')
ep = self._parse_json(
episode_code, display_id, transform_source=lambda s:
re.sub(r'(\n\s+)([a-zA-Z]+):\s+\'(.*?)\'', r'\1"\2": "\3"', s))
if ep['providerType'] != 'Ooyala':
raise ExtractorError('Unsupported provider %s' % ep['provider'])
ep = self._download_json(
'https://api.byutv.org/api3/catalog/getvideosforcontent', video_id,
query={
'contentid': video_id,
'channel': 'byutv',
'x-byutv-context': 'web$US',
}, headers={
'x-byutv-context': 'web$US',
'x-byutv-platformkey': 'xsaaw9c7y5',
})['ooyalaVOD']
return {
'_type': 'url_transparent',
@ -50,44 +52,7 @@ class BYUtvIE(InfoExtractor):
'url': 'ooyala:%s' % ep['providerId'],
'id': video_id,
'display_id': display_id,
'title': ep['title'],
'title': ep.get('title'),
'description': ep.get('description'),
'thumbnail': ep.get('imageThumbnail'),
}
class BYUtvEventIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?byutv\.org/watch/event/(?P<id>[0-9a-f-]+)'
_TEST = {
'url': 'http://www.byutv.org/watch/event/29941b9b-8bf6-48d2-aebf-7a87add9e34b',
'info_dict': {
'id': '29941b9b-8bf6-48d2-aebf-7a87add9e34b',
'ext': 'mp4',
'title': 'Toledo vs. BYU (9/30/16)',
},
'params': {
'skip_download': True,
},
'add_ie': ['Ooyala'],
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
ooyala_id = self._search_regex(
r'providerId\s*:\s*(["\'])(?P<id>(?:(?!\1).)+)\1',
webpage, 'ooyala id', group='id')
title = self._search_regex(
r'class=["\']description["\'][^>]*>\s*<h1>([^<]+)</h1>', webpage,
'title').strip()
return {
'_type': 'url_transparent',
'ie_key': 'Ooyala',
'url': 'ooyala:%s' % ooyala_id,
'id': video_id,
'title': title,
}

View File

@ -91,12 +91,10 @@ class CBSLocalIE(AnvatoIE):
info_dict = self._extract_anvato_videos(webpage, display_id)
time_str = self._html_search_regex(
r'class="entry-date">([^<]+)<', webpage, 'released date', default=None)
if time_str:
timestamp = unified_timestamp(time_str)
else:
timestamp = parse_iso8601(self._html_search_meta('uploadDate', webpage))
timestamp = unified_timestamp(self._html_search_regex(
r'class="(?:entry|post)-date"[^>]*>([^<]+)', webpage,
'released date', default=None)) or parse_iso8601(
self._html_search_meta('uploadDate', webpage))
info_dict.update({
'display_id': display_id,

View File

@ -301,8 +301,9 @@ class InfoExtractor(object):
There must be a key "entries", which is a list, an iterable, or a PagedList
object, each element of which is a valid dictionary by this specification.
Additionally, playlists can have "title", "description" and "id" attributes
with the same semantics as videos (see above).
Additionally, playlists can have "id", "title", "description", "uploader",
"uploader_id", "uploader_url" attributes with the same semantics as videos
(see above).
_type "multi_video" indicates that there are multiple videos that

View File

@ -392,7 +392,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
'Downloading subtitles for ' + sub_name, data={
'subtitle_script_id': sub_id,
})
if not sub_doc:
if sub_doc is None:
continue
sid = sub_doc.get('id')
iv = xpath_text(sub_doc, 'iv', 'subtitle iv')
@ -479,9 +479,9 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
'video_quality': stream_quality,
'current_page': url,
})
if streamdata:
if streamdata is not None:
stream_info = streamdata.find('./{default}preload/stream_info')
if stream_info:
if stream_info is not None:
stream_infos.append(stream_info)
stream_info = self._call_rpc_api(
'VideoEncode_GetStreamInfo', video_id,
@ -490,7 +490,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
'video_format': stream_format,
'video_encode_quality': stream_quality,
})
if stream_info:
if stream_info is not None:
stream_infos.append(stream_info)
for stream_info in stream_infos:
video_encode_id = xpath_text(stream_info, './video_encode_id')

View File

@ -4,13 +4,14 @@ import re
from .common import InfoExtractor
from ..utils import (
int_or_none,
unescapeHTML,
find_xpath_attr,
smuggle_url,
determine_ext,
ExtractorError,
extract_attributes,
find_xpath_attr,
get_element_by_class,
int_or_none,
smuggle_url,
unescapeHTML,
)
from .senateisvp import SenateISVPIE
from .ustream import UstreamIE
@ -68,6 +69,10 @@ class CSpanIE(InfoExtractor):
'uploader': 'HouseCommittee',
'uploader_id': '12987475',
},
}, {
# Audio Only
'url': 'https://www.c-span.org/video/?437336-1/judiciary-antitrust-competition-policy-consumer-rights',
'only_matching': True,
}]
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/%s_%s/index.html?videoId=%s'
@ -111,7 +116,15 @@ class CSpanIE(InfoExtractor):
title = self._og_search_title(webpage)
surl = smuggle_url(senate_isvp_url, {'force_title': title})
return self.url_result(surl, 'SenateISVP', video_id, title)
video_id = self._search_regex(
r'jwsetup\.clipprog\s*=\s*(\d+);',
webpage, 'jwsetup program id', default=None)
if video_id:
video_type = 'program'
if video_type is None or video_id is None:
error_message = get_element_by_class('VLplayer-error-message', webpage)
if error_message:
raise ExtractorError(error_message)
raise ExtractorError('unable to find video id and type')
def get_text_attr(d, attr):
@ -138,7 +151,7 @@ class CSpanIE(InfoExtractor):
entries = []
for partnum, f in enumerate(files):
formats = []
for quality in f['qualities']:
for quality in f.get('qualities', []):
formats.append({
'format_id': '%s-%sp' % (get_text_attr(quality, 'bitrate'), get_text_attr(quality, 'height')),
'url': unescapeHTML(get_text_attr(quality, 'file')),

View File

@ -5,6 +5,7 @@ import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
determine_ext,
extract_attributes,
ExtractorError,
int_or_none,
@ -73,7 +74,11 @@ class DiscoveryGoBaseIE(InfoExtractor):
not subtitle_url.startswith('http')):
continue
lang = caption.get('fileLang', 'en')
subtitles.setdefault(lang, []).append({'url': subtitle_url})
ext = determine_ext(subtitle_url)
subtitles.setdefault(lang, []).append({
'url': subtitle_url,
'ext': 'ttml' if ext == 'xml' else ext,
})
return {
'id': video_id,

View File

@ -10,6 +10,7 @@ from ..utils import (
compat_str,
determine_ext,
ExtractorError,
update_url_query,
)
@ -108,9 +109,16 @@ class DisneyIE(InfoExtractor):
continue
tbr = int_or_none(flavor.get('bitrate'))
if tbr == 99999:
formats.extend(self._extract_m3u8_formats(
# wrong ks(Kaltura Signature) causes 404 Error
flavor_url = update_url_query(flavor_url, {'ks': ''})
m3u8_formats = self._extract_m3u8_formats(
flavor_url, video_id, 'mp4',
m3u8_id=flavor_format, fatal=False))
m3u8_id=flavor_format, fatal=False)
for f in m3u8_formats:
# Apple FairPlay
if '/fpshls/' in f['url']:
continue
formats.append(f)
continue
format_id = []
if flavor_format:

View File

@ -138,10 +138,7 @@ from .brightcove import (
BrightcoveNewIE,
)
from .buzzfeed import BuzzFeedIE
from .byutv import (
BYUtvIE,
BYUtvEventIE,
)
from .byutv import BYUtvIE
from .c56 import C56IE
from .camdemy import (
CamdemyIE,
@ -934,7 +931,10 @@ from .seznamzpravy import (
SeznamZpravyIE,
SeznamZpravyArticleIE,
)
from .shahid import ShahidIE
from .shahid import (
ShahidIE,
ShahidShowIE,
)
from .shared import (
SharedIE,
VivoIE,

View File

@ -26,7 +26,7 @@ from ..utils import (
class ITVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?itv\.com/hub/[^/]+/(?P<id>[0-9a-zA-Z]+)'
_GEO_COUNTRIES = ['GB']
_TEST = {
_TESTS = [{
'url': 'http://www.itv.com/hub/mr-bean-animated-series/2a2936a0053',
'info_dict': {
'id': '2a2936a0053',
@ -37,7 +37,11 @@ class ITVIE(InfoExtractor):
# rtmp download
'skip_download': True,
},
}
}, {
# unavailable via data-playlist-url
'url': 'https://www.itv.com/hub/through-the-keyhole/2a2271a0033',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
@ -101,6 +105,18 @@ class ITVIE(InfoExtractor):
'Content-Type': 'text/xml; charset=utf-8',
'SOAPAction': 'http://tempuri.org/PlaylistService/GetPlaylist',
})
info = self._search_json_ld(webpage, video_id, default={})
formats = []
subtitles = {}
def extract_subtitle(sub_url):
ext = determine_ext(sub_url, 'ttml')
subtitles.setdefault('en', []).append({
'url': sub_url,
'ext': 'ttml' if ext == 'xml' else ext,
})
resp_env = self._download_xml(
params['data-playlist-url'], video_id,
headers=headers, data=etree.tostring(req_env))
@ -111,37 +127,55 @@ class ITVIE(InfoExtractor):
if fault_code == 'InvalidGeoRegion':
self.raise_geo_restricted(
msg=fault_string, countries=self._GEO_COUNTRIES)
raise ExtractorError('%s said: %s' % (self.IE_NAME, fault_string))
title = xpath_text(playlist, 'EpisodeTitle', fatal=True)
video_element = xpath_element(playlist, 'VideoEntries/Video', fatal=True)
media_files = xpath_element(video_element, 'MediaFiles', fatal=True)
rtmp_url = media_files.attrib['base']
elif fault_code != 'InvalidEntity':
raise ExtractorError(
'%s said: %s' % (self.IE_NAME, fault_string), expected=True)
info.update({
'title': self._og_search_title(webpage),
'episode_title': params.get('data-video-episode'),
'series': params.get('data-video-title'),
})
else:
title = xpath_text(playlist, 'EpisodeTitle', default=None)
info.update({
'title': title,
'episode_title': title,
'episode_number': int_or_none(xpath_text(playlist, 'EpisodeNumber')),
'series': xpath_text(playlist, 'ProgrammeTitle'),
'duration': parse_duration(xpath_text(playlist, 'Duration')),
})
video_element = xpath_element(playlist, 'VideoEntries/Video', fatal=True)
media_files = xpath_element(video_element, 'MediaFiles', fatal=True)
rtmp_url = media_files.attrib['base']
formats = []
for media_file in media_files.findall('MediaFile'):
play_path = xpath_text(media_file, 'URL')
if not play_path:
continue
tbr = int_or_none(media_file.get('bitrate'), 1000)
f = {
'format_id': 'rtmp' + ('-%d' % tbr if tbr else ''),
'play_path': play_path,
# Providing this swfVfy allows to avoid truncated downloads
'player_url': 'http://www.itv.com/mercury/Mercury_VideoPlayer.swf',
'page_url': url,
'tbr': tbr,
'ext': 'flv',
}
app = self._search_regex(
'rtmpe?://[^/]+/(.+)$', rtmp_url, 'app', default=None)
if app:
f.update({
'url': rtmp_url.split('?', 1)[0],
'app': app,
})
else:
f['url'] = rtmp_url
formats.append(f)
for media_file in media_files.findall('MediaFile'):
play_path = xpath_text(media_file, 'URL')
if not play_path:
continue
tbr = int_or_none(media_file.get('bitrate'), 1000)
f = {
'format_id': 'rtmp' + ('-%d' % tbr if tbr else ''),
'play_path': play_path,
# Providing this swfVfy allows to avoid truncated downloads
'player_url': 'http://www.itv.com/mercury/Mercury_VideoPlayer.swf',
'page_url': url,
'tbr': tbr,
'ext': 'flv',
}
app = self._search_regex(
'rtmpe?://[^/]+/(.+)$', rtmp_url, 'app', default=None)
if app:
f.update({
'url': rtmp_url.split('?', 1)[0],
'app': app,
})
else:
f['url'] = rtmp_url
formats.append(f)
for caption_url in video_element.findall('ClosedCaptioningURIs/URL'):
if caption_url.text:
extract_subtitle(caption_url.text)
ios_playlist_url = params.get('data-video-playlist') or params.get('data-video-id')
hmac = params.get('data-video-hmac')
@ -198,27 +232,22 @@ class ITVIE(InfoExtractor):
formats.append({
'url': href,
})
subs = video_data.get('Subtitles')
if isinstance(subs, list):
for sub in subs:
if not isinstance(sub, dict):
continue
href = sub.get('Href')
if isinstance(href, compat_str):
extract_subtitle(href)
if not info.get('duration'):
info['duration'] = parse_duration(video_data.get('Duration'))
self._sort_formats(formats)
subtitles = {}
for caption_url in video_element.findall('ClosedCaptioningURIs/URL'):
if not caption_url.text:
continue
ext = determine_ext(caption_url.text, 'ttml')
subtitles.setdefault('en', []).append({
'url': caption_url.text,
'ext': 'ttml' if ext == 'xml' else ext,
})
info = self._search_json_ld(webpage, video_id, default={})
info.update({
'id': video_id,
'title': title,
'formats': formats,
'subtitles': subtitles,
'episode_title': title,
'episode_number': int_or_none(xpath_text(playlist, 'EpisodeNumber')),
'series': xpath_text(playlist, 'ProgrammeTitle'),
'duartion': parse_duration(xpath_text(playlist, 'Duration')),
})
return info

View File

@ -13,8 +13,15 @@ from ..utils import (
class MailRuIE(InfoExtractor):
IE_NAME = 'mailru'
IE_DESC = 'Видео@Mail.Ru'
_VALID_URL = r'https?://(?:(?:www|m)\.)?my\.mail\.ru/(?:video/.*#video=/?(?P<idv1>(?:[^/]+/){3}\d+)|(?:(?P<idv2prefix>(?:[^/]+/){2})video/(?P<idv2suffix>[^/]+/\d+))\.html)'
_VALID_URL = r'''(?x)
https?://
(?:(?:www|m)\.)?my\.mail\.ru/
(?:
video/.*\#video=/?(?P<idv1>(?:[^/]+/){3}\d+)|
(?:(?P<idv2prefix>(?:[^/]+/){2})video/(?P<idv2suffix>[^/]+/\d+))\.html|
(?:video/embed|\+/video/meta)/(?P<metaid>\d+)
)
'''
_TESTS = [
{
'url': 'http://my.mail.ru/video/top#video=/mail/sonypicturesrus/75/76',
@ -23,7 +30,7 @@ class MailRuIE(InfoExtractor):
'id': '46301138_76',
'ext': 'mp4',
'title': 'Новый Человек-Паук. Высокое напряжение. Восстание Электро',
'timestamp': 1393232740,
'timestamp': 1393235077,
'upload_date': '20140224',
'uploader': 'sonypicturesrus',
'uploader_id': 'sonypicturesrus@mail.ru',
@ -40,7 +47,7 @@ class MailRuIE(InfoExtractor):
'title': 'Samsung Galaxy S5 Hammer Smash Fail Battery Explosion',
'timestamp': 1397039888,
'upload_date': '20140409',
'uploader': 'hitech@corp.mail.ru',
'uploader': 'hitech',
'uploader_id': 'hitech@corp.mail.ru',
'duration': 245,
},
@ -65,28 +72,42 @@ class MailRuIE(InfoExtractor):
{
'url': 'http://m.my.mail.ru/mail/3sktvtr/video/_myvideo/138.html',
'only_matching': True,
},
{
'url': 'https://my.mail.ru/video/embed/7949340477499637815',
'only_matching': True,
},
{
'url': 'http://my.mail.ru/+/video/meta/7949340477499637815',
'only_matching': True,
}
]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('idv1')
meta_id = mobj.group('metaid')
if not video_id:
video_id = mobj.group('idv2prefix') + mobj.group('idv2suffix')
webpage = self._download_webpage(url, video_id)
video_id = None
if meta_id:
meta_url = 'https://my.mail.ru/+/video/meta/%s' % meta_id
else:
video_id = mobj.group('idv1')
if not video_id:
video_id = mobj.group('idv2prefix') + mobj.group('idv2suffix')
webpage = self._download_webpage(url, video_id)
page_config = self._parse_json(self._search_regex(
r'(?s)<script[^>]+class="sp-video__page-config"[^>]*>(.+?)</script>',
webpage, 'page config', default='{}'), video_id, fatal=False)
if page_config:
meta_url = page_config.get('metaUrl') or page_config.get('video', {}).get('metaUrl')
else:
meta_url = None
video_data = None
page_config = self._parse_json(self._search_regex(
r'(?s)<script[^>]+class="sp-video__page-config"[^>]*>(.+?)</script>',
webpage, 'page config', default='{}'), video_id, fatal=False)
if page_config:
meta_url = page_config.get('metaUrl') or page_config.get('video', {}).get('metaUrl')
if meta_url:
video_data = self._download_json(
meta_url, video_id, 'Downloading video meta JSON', fatal=False)
if meta_url:
video_data = self._download_json(
meta_url, video_id or meta_id, 'Downloading video meta JSON',
fatal=not video_id)
# Fallback old approach
if not video_data:

View File

@ -1,13 +1,11 @@
# coding: utf-8
from __future__ import unicode_literals
import datetime
import json
import hashlib
import hmac
import re
from .common import InfoExtractor
from .aws import AWSIE
from .anvato import AnvatoIE
from ..utils import (
smuggle_url,
@ -16,7 +14,7 @@ from ..utils import (
)
class ScrippsNetworksWatchIE(InfoExtractor):
class ScrippsNetworksWatchIE(AWSIE):
IE_NAME = 'scrippsnetworks:watch'
_VALID_URL = r'''(?x)
https?://
@ -64,44 +62,27 @@ class ScrippsNetworksWatchIE(InfoExtractor):
'travelchannel': 'trav',
'geniuskitchen': 'genius',
}
_SNI_HOST = 'web.api.video.snidigital.com'
_AWS_REGION = 'us-east-1'
_AWS_IDENTITY_ID_JSON = json.dumps({
'IdentityId': '%s:7655847c-0ae7-4d9b-80d6-56c062927eb3' % _AWS_REGION
})
_AWS_USER_AGENT = 'aws-sdk-js/2.80.0 callback'
_AWS_API_KEY = 'E7wSQmq0qK6xPrF13WmzKiHo4BQ7tip4pQcSXVl1'
_AWS_SERVICE = 'execute-api'
_AWS_REQUEST = 'aws4_request'
_AWS_SIGNED_HEADERS = ';'.join([
'host', 'x-amz-date', 'x-amz-security-token', 'x-api-key'])
_AWS_CANONICAL_REQUEST_TEMPLATE = '''GET
%(uri)s
_AWS_PROXY_HOST = 'web.api.video.snidigital.com'
host:%(host)s
x-amz-date:%(date)s
x-amz-security-token:%(token)s
x-api-key:%(key)s
%(signed_headers)s
%(payload_hash)s'''
_AWS_USER_AGENT = 'aws-sdk-js/2.80.0 callback'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
site_id, video_id = mobj.group('site', 'id')
def aws_hash(s):
return hashlib.sha256(s.encode('utf-8')).hexdigest()
aws_identity_id_json = json.dumps({
'IdentityId': '%s:7655847c-0ae7-4d9b-80d6-56c062927eb3' % self._AWS_REGION
}).encode('utf-8')
token = self._download_json(
'https://cognito-identity.us-east-1.amazonaws.com/', video_id,
data=self._AWS_IDENTITY_ID_JSON.encode('utf-8'),
'https://cognito-identity.%s.amazonaws.com/' % self._AWS_REGION, video_id,
data=aws_identity_id_json,
headers={
'Accept': '*/*',
'Content-Type': 'application/x-amz-json-1.1',
'Referer': url,
'X-Amz-Content-Sha256': aws_hash(self._AWS_IDENTITY_ID_JSON),
'X-Amz-Content-Sha256': hashlib.sha256(aws_identity_id_json).hexdigest(),
'X-Amz-Target': 'AWSCognitoIdentityService.GetOpenIdToken',
'X-Amz-User-Agent': self._AWS_USER_AGENT,
})['Token']
@ -124,64 +105,12 @@ x-api-key:%(key)s
sts, './/{https://sts.amazonaws.com/doc/2011-06-15/}%s' % key,
fatal=True)
access_key_id = get('AccessKeyId')
secret_access_key = get('SecretAccessKey')
session_token = get('SessionToken')
# Task 1: http://docs.aws.amazon.com/general/latest/gr/sigv4-create-canonical-request.html
uri = '/1/web/brands/%s/episodes/scrid/%s' % (self._SNI_TABLE[site_id], video_id)
datetime_now = datetime.datetime.utcnow().strftime('%Y%m%dT%H%M%SZ')
date = datetime_now[:8]
canonical_string = self._AWS_CANONICAL_REQUEST_TEMPLATE % {
'uri': uri,
'host': self._SNI_HOST,
'date': datetime_now,
'token': session_token,
'key': self._AWS_API_KEY,
'signed_headers': self._AWS_SIGNED_HEADERS,
'payload_hash': aws_hash(''),
}
# Task 2: http://docs.aws.amazon.com/general/latest/gr/sigv4-create-string-to-sign.html
credential_string = '/'.join([date, self._AWS_REGION, self._AWS_SERVICE, self._AWS_REQUEST])
string_to_sign = '\n'.join([
'AWS4-HMAC-SHA256', datetime_now, credential_string,
aws_hash(canonical_string)])
# Task 3: http://docs.aws.amazon.com/general/latest/gr/sigv4-calculate-signature.html
def aws_hmac(key, msg):
return hmac.new(key, msg.encode('utf-8'), hashlib.sha256)
def aws_hmac_digest(key, msg):
return aws_hmac(key, msg).digest()
def aws_hmac_hexdigest(key, msg):
return aws_hmac(key, msg).hexdigest()
k_secret = 'AWS4' + secret_access_key
k_date = aws_hmac_digest(k_secret.encode('utf-8'), date)
k_region = aws_hmac_digest(k_date, self._AWS_REGION)
k_service = aws_hmac_digest(k_region, self._AWS_SERVICE)
k_signing = aws_hmac_digest(k_service, self._AWS_REQUEST)
signature = aws_hmac_hexdigest(k_signing, string_to_sign)
auth_header = ', '.join([
'AWS4-HMAC-SHA256 Credential=%s' % '/'.join(
[access_key_id, date, self._AWS_REGION, self._AWS_SERVICE, self._AWS_REQUEST]),
'SignedHeaders=%s' % self._AWS_SIGNED_HEADERS,
'Signature=%s' % signature,
])
mcp_id = self._download_json(
'https://%s%s' % (self._SNI_HOST, uri), video_id, headers={
'Accept': '*/*',
'Referer': url,
'Authorization': auth_header,
'X-Amz-Date': datetime_now,
'X-Amz-Security-Token': session_token,
'X-Api-Key': self._AWS_API_KEY,
})['results'][0]['mcpId']
mcp_id = self._aws_execute_api({
'uri': '/1/web/brands/%s/episodes/scrid/%s' % (self._SNI_TABLE[site_id], video_id),
'access_key': get('AccessKeyId'),
'secret_key': get('SecretAccessKey'),
'session_token': get('SessionToken'),
}, video_id)['results'][0]['mcpId']
return self.url_result(
smuggle_url(

View File

@ -1,22 +1,53 @@
# coding: utf-8
from __future__ import unicode_literals
import re
import json
import math
import re
from .common import InfoExtractor
from .aws import AWSIE
from ..compat import compat_HTTPError
from ..utils import (
clean_html,
ExtractorError,
InAdvancePagedList,
int_or_none,
parse_iso8601,
str_or_none,
urlencode_postdata,
clean_html,
)
class ShahidIE(InfoExtractor):
class ShahidBaseIE(AWSIE):
_AWS_PROXY_HOST = 'api2.shahid.net'
_AWS_API_KEY = '2RRtuMHx95aNI1Kvtn2rChEuwsCogUd4samGPjLh'
def _handle_error(self, e):
fail_data = self._parse_json(
e.cause.read().decode('utf-8'), None, fatal=False)
if fail_data:
faults = fail_data.get('faults', [])
faults_message = ', '.join([clean_html(fault['userMessage']) for fault in faults if fault.get('userMessage')])
if faults_message:
raise ExtractorError(faults_message, expected=True)
def _call_api(self, path, video_id, request=None):
query = {}
if request:
query['request'] = json.dumps(request)
try:
return self._aws_execute_api({
'uri': '/proxy/v2/' + path,
'access_key': 'AKIAI6X4TYCIXM2B7MUQ',
'secret_key': '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',
}, video_id, query)
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError):
self._handle_error(e)
raise
class ShahidIE(ShahidBaseIE):
_NETRC_MACHINE = 'shahid'
_VALID_URL = r'https?://shahid\.mbc\.net/ar/(?:serie|show|movie)s/[^/]+/(?P<type>episode|clip|movie)-(?P<id>\d+)'
_TESTS = [{
@ -41,34 +72,25 @@ class ShahidIE(InfoExtractor):
'only_matching': True
}]
def _api2_request(self, *args, **kwargs):
try:
return self._download_json(*args, **kwargs)
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError):
fail_data = self._parse_json(
e.cause.read().decode('utf-8'), None, fatal=False)
if fail_data:
faults = fail_data.get('faults', [])
faults_message = ', '.join([clean_html(fault['userMessage']) for fault in faults if fault.get('userMessage')])
if faults_message:
raise ExtractorError(faults_message, expected=True)
raise
def _real_initialize(self):
email, password = self._get_login_info()
if email is None:
return
user_data = self._api2_request(
'https://shahid.mbc.net/wd/service/users/login',
None, 'Logging in', data=json.dumps({
'email': email,
'password': password,
'basic': 'false',
}).encode('utf-8'), headers={
'Content-Type': 'application/json; charset=UTF-8',
})['user']
try:
user_data = self._download_json(
'https://shahid.mbc.net/wd/service/users/login',
None, 'Logging in', data=json.dumps({
'email': email,
'password': password,
'basic': 'false',
}).encode('utf-8'), headers={
'Content-Type': 'application/json; charset=UTF-8',
})['user']
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError):
self._handle_error(e)
raise
self._download_webpage(
'https://shahid.mbc.net/populateContext',
@ -81,25 +103,13 @@ class ShahidIE(InfoExtractor):
'sessionId': user_data['sessionId'],
}))
def _get_api_data(self, response):
data = response.get('data', {})
error = data.get('error')
if error:
raise ExtractorError(
'%s returned error: %s' % (self.IE_NAME, '\n'.join(error.values())),
expected=True)
return data
def _real_extract(self, url):
page_type, video_id = re.match(self._VALID_URL, url).groups()
if page_type == 'clip':
page_type = 'episode'
playout = self._api2_request(
'https://api2.shahid.net/proxy/v2/playout/url/' + video_id,
video_id, 'Downloading player JSON')['playout']
playout = self._call_api(
'playout/url/' + video_id, video_id)['playout']
if playout.get('drm'):
raise ExtractorError('This video is DRM protected.', expected=True)
@ -107,13 +117,27 @@ class ShahidIE(InfoExtractor):
formats = self._extract_m3u8_formats(playout['url'], video_id, 'mp4')
self._sort_formats(formats)
video = self._get_api_data(self._download_json(
# video = self._call_api(
# 'product/id', video_id, {
# 'id': video_id,
# 'productType': 'ASSET',
# 'productSubType': page_type.upper()
# })['productModel']
response = self._download_json(
'http://api.shahid.net/api/v1_1/%s/%s' % (page_type, video_id),
video_id, 'Downloading video JSON', query={
'apiKey': 'sh@hid0nlin3',
'hash': 'b2wMCTHpSmyxGqQjJFOycRmLSex+BpTK/ooxy6vHaqs=',
}))[page_type]
})
data = response.get('data', {})
error = data.get('error')
if error:
raise ExtractorError(
'%s returned error: %s' % (self.IE_NAME, '\n'.join(error.values())),
expected=True)
video = data[page_type]
title = video['title']
categories = [
category['name']
@ -135,3 +159,57 @@ class ShahidIE(InfoExtractor):
'episode_id': video_id,
'formats': formats,
}
class ShahidShowIE(ShahidBaseIE):
_VALID_URL = r'https?://shahid\.mbc\.net/ar/(?:show|serie)s/[^/]+/(?:show|series)-(?P<id>\d+)'
_TESTS = [{
'url': 'https://shahid.mbc.net/ar/shows/%D8%B1%D8%A7%D9%85%D8%B2-%D9%82%D8%B1%D8%B4-%D8%A7%D9%84%D8%A8%D8%AD%D8%B1/show-79187',
'info_dict': {
'id': '79187',
'title': 'رامز قرش البحر',
'description': 'md5:c88fa7e0f02b0abd39d417aee0d046ff',
},
'playlist_mincount': 32,
}, {
'url': 'https://shahid.mbc.net/ar/series/How-to-live-Longer-(The-Big-Think)/series-291861',
'only_matching': True
}]
_PAGE_SIZE = 30
def _real_extract(self, url):
show_id = self._match_id(url)
product = self._call_api(
'playableAsset', show_id, {'showId': show_id})['productModel']
playlist = product['playlist']
playlist_id = playlist['id']
show = product.get('show', {})
def page_func(page_num):
playlist = self._call_api(
'product/playlist', show_id, {
'playListId': playlist_id,
'pageNumber': page_num,
'pageSize': 30,
'sorts': [{
'order': 'DESC',
'type': 'SORTDATE'
}],
})
for product in playlist.get('productList', {}).get('products', []):
product_url = product.get('productUrl', []).get('url')
if not product_url:
continue
yield self.url_result(
product_url, 'Shahid',
str_or_none(product.get('id')),
product.get('title'))
entries = InAdvancePagedList(
page_func,
math.ceil(playlist['count'] / self._PAGE_SIZE),
self._PAGE_SIZE)
return self.playlist_result(
entries, show_id, show.get('title'), show.get('description'))

View File

@ -414,7 +414,7 @@ class VKIE(VKBaseIE):
view_count = str_to_int(self._search_regex(
r'class=["\']mv_views_count[^>]+>\s*([\d,.]+)',
info_page, 'view count', fatal=False))
info_page, 'view count', default=None))
formats = []
for format_id, format_url in data.items():

View File

@ -2,7 +2,6 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from .kaltura import KalturaIE
from ..utils import (
ExtractorError,
int_or_none,
@ -17,11 +16,10 @@ class VootIE(InfoExtractor):
_TESTS = [{
'url': 'https://www.voot.com/shows/ishq-ka-rang-safed/1/360558/is-this-the-end-of-kamini-/441353',
'info_dict': {
'id': '0_8ledb18o',
'id': '441353',
'ext': 'mp4',
'title': 'Ishq Ka Rang Safed - Season 01 - Episode 340',
'description': 'md5:06291fbbbc4dcbe21235c40c262507c1',
'uploader_id': 'batchUser',
'timestamp': 1472162937,
'upload_date': '20160825',
'duration': 1146,
@ -61,8 +59,11 @@ class VootIE(InfoExtractor):
media = media_info['assets']
entry_id = media['EntryId']
title = media['MediaName']
formats = self._extract_m3u8_formats(
'https://cdnapisec.kaltura.com/p/1982551/playManifest/pt/https/f/applehttp/t/web/e/' + media['EntryId'],
video_id, 'mp4', m3u8_id='hls')
self._sort_formats(formats)
description, series, season_number, episode, episode_number = [None] * 5
@ -82,9 +83,7 @@ class VootIE(InfoExtractor):
episode_number = int_or_none(value)
return {
'_type': 'url_transparent',
'url': 'kaltura:1982551:%s' % entry_id,
'ie_key': KalturaIE.ie_key(),
'id': video_id,
'title': title,
'description': description,
'series': series,
@ -95,4 +94,5 @@ class VootIE(InfoExtractor):
'duration': int_or_none(media.get('Duration')),
'view_count': int_or_none(media.get('ViewCounter')),
'like_count': int_or_none(media.get('like_counter')),
'formats': formats,
}

View File

@ -2270,6 +2270,19 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
r'(?s)<h1 class="pl-header-title[^"]*"[^>]*>\s*(.*?)\s*</h1>',
page, 'title', default=None)
_UPLOADER_BASE = r'class=["\']pl-header-details[^>]+>\s*<li>\s*<a[^>]+\bhref='
uploader = self._search_regex(
r'%s["\']/(?:user|channel)/[^>]+>([^<]+)' % _UPLOADER_BASE,
page, 'uploader', default=None)
mobj = re.search(
r'%s(["\'])(?P<path>/(?:user|channel)/(?P<uploader_id>.+?))\1' % _UPLOADER_BASE,
page)
if mobj:
uploader_id = mobj.group('uploader_id')
uploader_url = compat_urlparse.urljoin(url, mobj.group('path'))
else:
uploader_id = uploader_url = None
has_videos = True
if not playlist_title:
@ -2280,8 +2293,15 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
except StopIteration:
has_videos = False
return has_videos, self.playlist_result(
playlist = self.playlist_result(
self._entries(page, playlist_id), playlist_id, playlist_title)
playlist.update({
'uploader': uploader,
'uploader_id': uploader_id,
'uploader_url': uploader_url,
})
return has_videos, playlist
def _check_download_just_video(self, url, playlist_id):
# Check if it's a video-specific URL

View File

@ -42,6 +42,7 @@ class XAttrMetadataPP(PostProcessor):
'user.dublincore.format': 'format',
}
num_written = 0
for xattrname, infoname in xattr_mapping.items():
value = info.get(infoname)
@ -52,6 +53,7 @@ class XAttrMetadataPP(PostProcessor):
byte_value = value.encode('utf-8')
write_xattr(filename, xattrname, byte_value)
num_written += 1
return [], info
@ -62,8 +64,8 @@ class XAttrMetadataPP(PostProcessor):
except XAttrMetadataError as e:
if e.reason == 'NO_SPACE':
self._downloader.report_warning(
'There\'s no disk space left or disk quota exceeded. ' +
'Extended attributes are not written.')
'There\'s no disk space left, disk quota exceeded or filesystem xattr limit exceeded. ' +
(('Some ' if num_written else '') + 'extended attributes are not written.').capitalize())
elif e.reason == 'VALUE_TOO_LONG':
self._downloader.report_warning(
'Unable to write extended attributes due to too long values.')

View File

@ -159,6 +159,8 @@ DATE_FORMATS = (
'%Y-%m-%dT%H:%M',
'%b %d %Y at %H:%M',
'%b %d %Y at %H:%M:%S',
'%B %d %Y at %H:%M',
'%B %d %Y at %H:%M:%S',
)
DATE_FORMATS_DAY_FIRST = list(DATE_FORMATS)

View File

@ -1,3 +1,3 @@
from __future__ import unicode_literals
__version__ = '2017.12.10'
__version__ = '2017.12.14'