Compare commits

...

10 Commits

Author SHA1 Message Date
Sergey M․
250eea6821 release 2017.03.02 2017-03-02 22:33:22 +07:00
Sergey M․
28d15b73f8 [ChangeLog] Actualize 2017-03-02 22:29:56 +07:00
Yen Chi Hsuan
11bb6ad1a5 [facebook] Fix extraction (closes #12323)
Almost all videos now use the pagelet type 'permalink_video_pagelet'
2017-03-02 20:51:24 +08:00
Yen Chi Hsuan
c9612c0487 [youtube] Mark errors about rental videos as expected
Closes #12324
2017-03-02 16:59:53 +08:00
Yen Chi Hsuan
af5049f128 [adobepass] Add Charter Spectrum (#11465)
Thanks @tv21 for the fix!
2017-03-02 02:15:51 +08:00
Sergey M․
158af5242e [utils] Carry long doc string 2017-03-01 23:04:02 +07:00
Sergey M․
40df485f55 [YoutubeDL] Don't sanitize identifiers (closes #12317) 2017-03-01 23:03:36 +07:00
Sergey M․
4b8a984c67 [npo] Add support for audio 2017-03-01 22:21:13 +07:00
Sergey M․
83e8fce628 [npo] Improve extraction and update tests 2017-03-01 22:14:46 +07:00
Sergey M․
aa9cc2ecbf [npo] Adapt to app.php API (closes #12311) 2017-03-01 05:03:35 +07:00
9 changed files with 245 additions and 231 deletions

View File

@@ -6,8 +6,8 @@
---
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.02.28*. 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 Issues with outdated version will be rejected.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 **2017.02.28**
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.03.02*. 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 Issues with outdated version will be rejected.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 **2017.03.02**
### Before submitting an *issue* make sure you have:
- [ ] At least skimmed through [README](https://github.com/rg3/youtube-dl/blob/master/README.md) and **most notably** [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
@@ -35,7 +35,7 @@ $ youtube-dl -v <your command line>
[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 2017.02.28
[debug] youtube-dl version 2017.03.02
[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 +1,16 @@
version 2017.03.02
Core
+ [adobepass] Add support for Charter Spectrum (#11465)
* [YoutubeDL] Don't sanitize identifiers in output template (#12317)
Extractors
* [facebook] Fix extraction (#12323, #12330)
* [youtube] Mark errors about rental videos as expected (#12324)
+ [npo] Add support for audio
* [npo] Adapt to app.php API (#12311, #12320)
version 2017.02.28
Core

View File

@@ -616,7 +616,7 @@ class YoutubeDL(object):
sanitize = lambda k, v: sanitize_filename(
compat_str(v),
restricted=self.params.get('restrictfilenames'),
is_id=(k == 'id'))
is_id=(k == 'id' or k.endswith('_id')))
template_dict = dict((k, v if isinstance(v, compat_numeric_types) else sanitize(k, v))
for k, v in template_dict.items()
if v is not None and not isinstance(v, (list, tuple, dict)))

View File

@@ -36,6 +36,11 @@ MSO_INFO = {
'username_field': 'Ecom_User_ID',
'password_field': 'Ecom_Password',
},
'Charter_Direct': {
'name': 'Charter Spectrum',
'username_field': 'IDToken1',
'password_field': 'IDToken2',
},
'thr030': {
'name': '3 Rivers Communications'
},

View File

@@ -303,7 +303,7 @@ class FacebookIE(InfoExtractor):
if not video_data:
server_js_data = self._parse_json(
self._search_regex(
r'bigPipe\.onPageletArrive\(({.+?})\)\s*;\s*}\s*\)\s*,\s*["\']onPageletArrive\s+(?:stream_pagelet|pagelet_group_mall)',
r'bigPipe\.onPageletArrive\(({.+?})\)\s*;\s*}\s*\)\s*,\s*["\']onPageletArrive\s+(?:stream_pagelet|pagelet_group_mall|permalink_video_pagelet)',
webpage, 'js data', default='{}'),
video_id, transform_source=js_to_json, fatal=False)
if server_js_data:

View File

@@ -3,41 +3,27 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_HTTPError
from ..compat import (
compat_HTTPError,
compat_str,
)
from ..utils import (
determine_ext,
ExtractorError,
fix_xml_ampersands,
orderedSet,
parse_duration,
qualities,
strip_jsonp,
unified_strdate,
ExtractorError,
)
class NPOBaseIE(InfoExtractor):
def _get_token(self, video_id):
token_page = self._download_webpage(
'http://ida.omroep.nl/npoplayer/i.js',
video_id, note='Downloading token')
token = self._search_regex(
r'npoplayer\.token = "(.+?)"', token_page, 'token')
# Decryption algorithm extracted from http://npoplayer.omroep.nl/csjs/npoplayer-min.js
token_l = list(token)
first = second = None
for i in range(5, len(token_l) - 4):
if token_l[i].isdigit():
if first is None:
first = i
elif second is None:
second = i
if first is None or second is None:
first = 12
second = 13
token_l[first], token_l[second] = token_l[second], token_l[first]
return ''.join(token_l)
return self._download_json(
'http://ida.omroep.nl/app.php/auth', video_id,
note='Downloading token')['token']
class NPOIE(NPOBaseIE):
@@ -58,103 +44,113 @@ class NPOIE(NPOBaseIE):
(?P<id>[^/?#]+)
'''
_TESTS = [
{
'url': 'http://www.npo.nl/nieuwsuur/22-06-2014/VPWON_1220719',
'md5': '4b3f9c429157ec4775f2c9cb7b911016',
'info_dict': {
'id': 'VPWON_1220719',
'ext': 'm4v',
'title': 'Nieuwsuur',
'description': 'Dagelijks tussen tien en elf: nieuws, sport en achtergronden.',
'upload_date': '20140622',
},
_TESTS = [{
'url': 'http://www.npo.nl/nieuwsuur/22-06-2014/VPWON_1220719',
'md5': '4b3f9c429157ec4775f2c9cb7b911016',
'info_dict': {
'id': 'VPWON_1220719',
'ext': 'm4v',
'title': 'Nieuwsuur',
'description': 'Dagelijks tussen tien en elf: nieuws, sport en achtergronden.',
'upload_date': '20140622',
},
{
'url': 'http://www.npo.nl/de-mega-mike-mega-thomas-show/27-02-2009/VARA_101191800',
'md5': 'da50a5787dbfc1603c4ad80f31c5120b',
'info_dict': {
'id': 'VARA_101191800',
'ext': 'm4v',
'title': 'De Mega Mike & Mega Thomas show: The best of.',
'description': 'md5:3b74c97fc9d6901d5a665aac0e5400f4',
'upload_date': '20090227',
'duration': 2400,
},
}, {
'url': 'http://www.npo.nl/de-mega-mike-mega-thomas-show/27-02-2009/VARA_101191800',
'md5': 'da50a5787dbfc1603c4ad80f31c5120b',
'info_dict': {
'id': 'VARA_101191800',
'ext': 'm4v',
'title': 'De Mega Mike & Mega Thomas show: The best of.',
'description': 'md5:3b74c97fc9d6901d5a665aac0e5400f4',
'upload_date': '20090227',
'duration': 2400,
},
{
'url': 'http://www.npo.nl/tegenlicht/25-02-2013/VPWON_1169289',
'md5': 'f8065e4e5a7824068ed3c7e783178f2c',
'info_dict': {
'id': 'VPWON_1169289',
'ext': 'm4v',
'title': 'Tegenlicht: De toekomst komt uit Afrika',
'description': 'md5:52cf4eefbc96fffcbdc06d024147abea',
'upload_date': '20130225',
'duration': 3000,
},
}, {
'url': 'http://www.npo.nl/tegenlicht/25-02-2013/VPWON_1169289',
'md5': 'f8065e4e5a7824068ed3c7e783178f2c',
'info_dict': {
'id': 'VPWON_1169289',
'ext': 'm4v',
'title': 'Tegenlicht: Zwart geld. De toekomst komt uit Afrika',
'description': 'md5:52cf4eefbc96fffcbdc06d024147abea',
'upload_date': '20130225',
'duration': 3000,
},
{
'url': 'http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706',
'info_dict': {
'id': 'WO_VPRO_043706',
'ext': 'wmv',
'title': 'De nieuwe mens - Deel 1',
'description': 'md5:518ae51ba1293ffb80d8d8ce90b74e4b',
'duration': 4680,
},
'params': {
# mplayer mms download
'skip_download': True,
}
}, {
'url': 'http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706',
'info_dict': {
'id': 'WO_VPRO_043706',
'ext': 'm4v',
'title': 'De nieuwe mens - Deel 1',
'description': 'md5:518ae51ba1293ffb80d8d8ce90b74e4b',
'duration': 4680,
},
# non asf in streams
{
'url': 'http://www.npo.nl/hoe-gaat-europa-verder-na-parijs/10-01-2015/WO_NOS_762771',
'md5': 'b3da13de374cbe2d5332a7e910bef97f',
'info_dict': {
'id': 'WO_NOS_762771',
'ext': 'mp4',
'title': 'Hoe gaat Europa verder na Parijs?',
},
},
{
'url': 'http://www.ntr.nl/Aap-Poot-Pies/27/detail/Aap-poot-pies/VPWON_1233944#content',
'md5': '01c6a2841675995da1f0cf776f03a9c3',
'info_dict': {
'id': 'VPWON_1233944',
'ext': 'm4v',
'title': 'Aap, poot, pies',
'description': 'md5:c9c8005d1869ae65b858e82c01a91fde',
'upload_date': '20150508',
'duration': 599,
},
},
{
'url': 'http://www.omroepwnl.nl/video/fragment/vandaag-de-dag-verkiezingen__POMS_WNL_853698',
'md5': 'd30cd8417b8b9bca1fdff27428860d08',
'info_dict': {
'id': 'POW_00996502',
'ext': 'm4v',
'title': '''"Dit is wel een 'landslide'..."''',
'description': 'md5:f8d66d537dfb641380226e31ca57b8e8',
'upload_date': '20150508',
'duration': 462,
},
},
{
'url': 'http://www.zapp.nl/de-bzt-show/gemist/KN_1687547',
'only_matching': True,
},
{
'url': 'http://www.zapp.nl/de-bzt-show/filmpjes/POMS_KN_7315118',
'only_matching': True,
},
{
'url': 'http://www.zapp.nl/beste-vrienden-quiz/extra-video-s/WO_NTR_1067990',
'only_matching': True,
'params': {
'skip_download': True,
}
]
}, {
# non asf in streams
'url': 'http://www.npo.nl/hoe-gaat-europa-verder-na-parijs/10-01-2015/WO_NOS_762771',
'info_dict': {
'id': 'WO_NOS_762771',
'ext': 'mp4',
'title': 'Hoe gaat Europa verder na Parijs?',
},
'params': {
'skip_download': True,
}
}, {
'url': 'http://www.ntr.nl/Aap-Poot-Pies/27/detail/Aap-poot-pies/VPWON_1233944#content',
'info_dict': {
'id': 'VPWON_1233944',
'ext': 'm4v',
'title': 'Aap, poot, pies',
'description': 'md5:c9c8005d1869ae65b858e82c01a91fde',
'upload_date': '20150508',
'duration': 599,
},
'params': {
'skip_download': True,
}
}, {
'url': 'http://www.omroepwnl.nl/video/fragment/vandaag-de-dag-verkiezingen__POMS_WNL_853698',
'info_dict': {
'id': 'POW_00996502',
'ext': 'm4v',
'title': '''"Dit is wel een 'landslide'..."''',
'description': 'md5:f8d66d537dfb641380226e31ca57b8e8',
'upload_date': '20150508',
'duration': 462,
},
'params': {
'skip_download': True,
}
}, {
# audio
'url': 'http://www.npo.nl/jouw-stad-rotterdam/29-01-2017/RBX_FUNX_6683215/RBX_FUNX_7601437',
'info_dict': {
'id': 'RBX_FUNX_6683215',
'ext': 'mp3',
'title': 'Jouw Stad Rotterdam',
'description': 'md5:db251505244f097717ec59fabc372d9f',
},
'params': {
'skip_download': True,
}
}, {
'url': 'http://www.zapp.nl/de-bzt-show/gemist/KN_1687547',
'only_matching': True,
}, {
'url': 'http://www.zapp.nl/de-bzt-show/filmpjes/POMS_KN_7315118',
'only_matching': True,
}, {
'url': 'http://www.zapp.nl/beste-vrienden-quiz/extra-video-s/WO_NTR_1067990',
'only_matching': True,
}, {
# live stream
'url': 'npo:LI_NL1_4188102',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
@@ -183,70 +179,115 @@ class NPOIE(NPOBaseIE):
token = self._get_token(video_id)
formats = []
urls = set()
pubopties = metadata.get('pubopties')
if pubopties:
quality = qualities(['adaptive', 'wmv_sb', 'h264_sb', 'wmv_bb', 'h264_bb', 'wvc1_std', 'h264_std'])
for format_id in pubopties:
format_info = self._download_json(
'http://ida.omroep.nl/odi/?prid=%s&puboptions=%s&adaptive=yes&token=%s'
% (video_id, format_id, token),
video_id, 'Downloading %s JSON' % format_id)
if format_info.get('error_code', 0) or format_info.get('errorcode', 0):
quality = qualities(['adaptive', 'wmv_sb', 'h264_sb', 'wmv_bb', 'h264_bb', 'wvc1_std', 'h264_std'])
items = self._download_json(
'http://ida.omroep.nl/app.php/%s' % video_id, video_id,
'Downloading formats JSON', query={
'adaptive': 'yes',
'token': token,
})['items'][0]
for num, item in enumerate(items):
item_url = item.get('url')
if not item_url or item_url in urls:
continue
urls.add(item_url)
format_id = self._search_regex(
r'video/ida/([^/]+)', item_url, 'format id',
default=None)
def add_format_url(format_url):
formats.append({
'url': format_url,
'format_id': format_id,
'quality': quality(format_id),
})
# Example: http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706
if item.get('contentType') in ('url', 'audio'):
add_format_url(item_url)
continue
try:
stream_info = self._download_json(
item_url + '&type=json', video_id,
'Downloading %s stream JSON'
% item.get('label') or item.get('format') or format_id or num)
except ExtractorError as ee:
if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404:
error = (self._parse_json(
ee.cause.read().decode(), video_id,
fatal=False) or {}).get('errorstring')
if error:
raise ExtractorError(error, expected=True)
raise
# Stream URL instead of JSON, example: npo:LI_NL1_4188102
if isinstance(stream_info, compat_str):
if not stream_info.startswith('http'):
continue
streams = format_info.get('streams')
if streams:
try:
video_info = self._download_json(
streams[0] + '&type=json',
video_id, 'Downloading %s stream JSON' % format_id)
except ExtractorError as ee:
if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404:
error = (self._parse_json(ee.cause.read().decode(), video_id, fatal=False) or {}).get('errorstring')
if error:
raise ExtractorError(error, expected=True)
raise
else:
video_info = format_info
video_url = video_info.get('url')
if not video_url:
video_url = stream_info
# JSON
else:
video_url = stream_info.get('url')
if not video_url or video_url in urls:
continue
urls.add(item_url)
if determine_ext(video_url) == 'm3u8':
formats.extend(self._extract_m3u8_formats(
video_url, video_id, ext='mp4',
entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
else:
add_format_url(video_url)
is_live = metadata.get('medium') == 'live'
if not is_live:
for num, stream in enumerate(metadata.get('streams', [])):
stream_url = stream.get('url')
if not stream_url or stream_url in urls:
continue
if format_id == 'adaptive':
formats.extend(self._extract_m3u8_formats(video_url, video_id, 'mp4'))
else:
urls.add(stream_url)
# smooth streaming is not supported
stream_type = stream.get('type', '').lower()
if stream_type in ['ss', 'ms']:
continue
if stream_type == 'hds':
f4m_formats = self._extract_f4m_formats(
stream_url, video_id, fatal=False)
# f4m downloader downloads only piece of live stream
for f4m_format in f4m_formats:
f4m_format['preference'] = -1
formats.extend(f4m_formats)
elif stream_type == 'hls':
formats.extend(self._extract_m3u8_formats(
stream_url, video_id, ext='mp4', fatal=False))
# Example: http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706
elif '.asf' in stream_url:
asx = self._download_xml(
stream_url, video_id,
'Downloading stream %d ASX playlist' % num,
transform_source=fix_xml_ampersands, fatal=False)
if not asx:
continue
ref = asx.find('./ENTRY/Ref')
if ref is None:
continue
video_url = ref.get('href')
if not video_url or video_url in urls:
continue
urls.add(video_url)
formats.append({
'url': video_url,
'format_id': format_id,
'quality': quality(format_id),
'ext': stream.get('formaat', 'asf'),
'quality': stream.get('kwaliteit'),
'preference': -10,
})
streams = metadata.get('streams')
if streams:
for i, stream in enumerate(streams):
stream_url = stream.get('url')
if not stream_url:
continue
if '.asf' not in stream_url:
else:
formats.append({
'url': stream_url,
'quality': stream.get('kwaliteit'),
})
continue
asx = self._download_xml(
stream_url, video_id,
'Downloading stream %d ASX playlist' % i,
transform_source=fix_xml_ampersands)
ref = asx.find('./ENTRY/Ref')
if ref is None:
continue
video_url = ref.get('href')
if not video_url:
continue
formats.append({
'url': video_url,
'ext': stream.get('formaat', 'asf'),
'quality': stream.get('kwaliteit'),
})
self._sort_formats(formats)
@@ -259,28 +300,28 @@ class NPOIE(NPOBaseIE):
return {
'id': video_id,
'title': title,
'title': self._live_title(title) if is_live else title,
'description': metadata.get('info'),
'thumbnail': metadata.get('images', [{'url': None}])[-1]['url'],
'upload_date': unified_strdate(metadata.get('gidsdatum')),
'duration': parse_duration(metadata.get('tijdsduur')),
'formats': formats,
'subtitles': subtitles,
'is_live': is_live,
}
class NPOLiveIE(NPOBaseIE):
IE_NAME = 'npo.nl:live'
_VALID_URL = r'https?://(?:www\.)?npo\.nl/live/(?P<id>.+)'
_VALID_URL = r'https?://(?:www\.)?npo\.nl/live/(?P<id>[^/?#&]+)'
_TEST = {
'url': 'http://www.npo.nl/live/npo-1',
'info_dict': {
'id': 'LI_NEDERLAND1_136692',
'id': 'LI_NL1_4188102',
'display_id': 'npo-1',
'ext': 'mp4',
'title': 're:^Nederland 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'description': 'Livestream',
'title': 're:^NPO 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'is_live': True,
},
'params': {
@@ -296,58 +337,12 @@ class NPOLiveIE(NPOBaseIE):
live_id = self._search_regex(
r'data-prid="([^"]+)"', webpage, 'live id')
metadata = self._download_json(
'http://e.omroep.nl/metadata/%s' % live_id,
display_id, transform_source=strip_jsonp)
token = self._get_token(display_id)
formats = []
streams = metadata.get('streams')
if streams:
for stream in streams:
stream_type = stream.get('type').lower()
# smooth streaming is not supported
if stream_type in ['ss', 'ms']:
continue
stream_info = self._download_json(
'http://ida.omroep.nl/aapi/?stream=%s&token=%s&type=jsonp'
% (stream.get('url'), token),
display_id, 'Downloading %s JSON' % stream_type)
if stream_info.get('error_code', 0) or stream_info.get('errorcode', 0):
continue
stream_url = self._download_json(
stream_info['stream'], display_id,
'Downloading %s URL' % stream_type,
'Unable to download %s URL' % stream_type,
transform_source=strip_jsonp, fatal=False)
if not stream_url:
continue
if stream_type == 'hds':
f4m_formats = self._extract_f4m_formats(stream_url, display_id)
# f4m downloader downloads only piece of live stream
for f4m_format in f4m_formats:
f4m_format['preference'] = -1
formats.extend(f4m_formats)
elif stream_type == 'hls':
formats.extend(self._extract_m3u8_formats(stream_url, display_id, 'mp4'))
else:
formats.append({
'url': stream_url,
'preference': -10,
})
self._sort_formats(formats)
return {
'_type': 'url_transparent',
'url': 'npo:%s' % live_id,
'ie_key': NPOIE.ie_key(),
'id': live_id,
'display_id': display_id,
'title': self._live_title(metadata['titel']),
'description': metadata['info'],
'thumbnail': metadata.get('images', [{'url': None}])[-1]['url'],
'formats': formats,
'is_live': True,
}

View File

@@ -1454,7 +1454,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
# Check for "rental" videos
if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
raise ExtractorError('"rental" videos not supported')
raise ExtractorError('"rental" videos not supported. See https://github.com/rg3/youtube-dl/issues/359 for more information.', expected=True)
# Start extracting information
self.report_information_extraction(video_id)

View File

@@ -473,7 +473,8 @@ def timeconvert(timestr):
def sanitize_filename(s, restricted=False, is_id=False):
"""Sanitizes a string so it could be used as part of a filename.
If restricted is set, use a stricter subset of allowed characters.
Set is_id if this is not an arbitrary string, but an ID that should be kept if possible
Set is_id if this is not an arbitrary string, but an ID that should be kept
if possible.
"""
def replace_insane(char):
if restricted and char in ACCENT_CHARS:

View File

@@ -1,3 +1,3 @@
from __future__ import unicode_literals
__version__ = '2017.02.28'
__version__ = '2017.03.02'