R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Merge branch 'master' into KeezMovies-issue-16134

Browse Source
This commit is contained in:
Parmjit Virk 2018-04-17 12:54:15 -05:00
commit 9e61f0e191
15 changed files with 264 additions and 51 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
.github/ISSUE_TEMPLATE.md vendored
View File

@ -6,8 +6,8 @@
---
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.04.09*. 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 Issues with outdated version will be rejected.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 **2018.04.09**
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.04.16*. 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 Issues with outdated version will be rejected.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 **2018.04.16**
### 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
@ -36,7 +36,7 @@ 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 2018.04.09
[debug] youtube-dl version 2018.04.16
[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: {}

13
ChangeLog
View File

@ -1,3 +1,16 @@
version 2018.04.16
Extractors
* [smotri:broadcast] Fix extraction (#16180)
+ [picarto] Add support for picarto.tv (#6205, #12514, #15276, #15551)
* [vine:user] Fix extraction (#15514, #16190)
* [pornhub] Relax URL regular expression (#16165)
* [cbc:watch] Re-acquire device token when expired (#16160)
+ [fxnetworks] Add support for https theplatform URLs (#16125, #16157)
+ [instagram:user] Add request signing (#16119)
+ [twitch] Add support for mobile URLs (#16146)
version 2018.04.09
Core

2
docs/supportedsites.md
View File

@ -628,6 +628,8 @@
- **PhilharmonieDeParis**: Philharmonie de Paris
- **phoenix.de**
- **Photobucket**
- **Picarto**
- **PicartoVod**
- **Piksel**
- **Pinkbike**
- **Pladform**

4
test/test_subtitles.py
View File

@ -232,7 +232,7 @@ class TestNPOSubtitles(BaseTestSubtitles):
class TestMTVSubtitles(BaseTestSubtitles):
url = 'http://www.cc.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother'
url = 'http://www.cc.com/video-clips/p63lk0/adam-devine-s-house-party-chasing-white-swans'
IE = ComedyCentralIE
def getInfoDict(self):
@ -243,7 +243,7 @@ class TestMTVSubtitles(BaseTestSubtitles):
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['en']))
self.assertEqual(md5(subtitles['en']), 'b9f6ca22a6acf597ec76f61749765e65')
self.assertEqual(md5(subtitles['en']), '78206b8d8a0cfa9da64dc026eea48961')
class TestNRKSubtitles(BaseTestSubtitles):

2
test/test_youtube_lists.py
View File

@ -61,7 +61,7 @@ class TestYoutubeLists(unittest.TestCase):
dl = FakeYDL()
dl.params['extract_flat'] = True
ie = YoutubePlaylistIE(dl)
result = ie.extract('https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re')
result = ie.extract('https://www.youtube.com/playlist?list=PL-KKIb8rvtMSrAO9YFbeM6UQrAqoFTUWv')
self.assertIsPlaylist(result)
for entry in result['entries']:
self.assertTrue(entry.get('title'))

0
youtube_dl/extractor/americastestkitchen.py Executable file → Normal file
View File

2
youtube_dl/extractor/cbs.py
View File

@ -65,7 +65,7 @@ class CBSIE(CBSBaseIE):
last_e = None
for item in items_data.findall('.//item'):
asset_type = xpath_text(item, 'assetType')
if not asset_type or asset_type in asset_types:
if not asset_type or asset_type in asset_types or asset_type in ('HLS_FPS', 'DASH_CENC'):
continue
asset_types.append(asset_type)
query = {

0
youtube_dl/extractor/cda.py Executable file → Normal file
View File

4
youtube_dl/extractor/extractors.py
View File

@ -815,6 +815,10 @@ from .periscope import (
from .philharmoniedeparis import PhilharmonieDeParisIE
from .phoenix import PhoenixIE
from .photobucket import PhotobucketIE
from .picarto import (
PicartoIE,
PicartoVodIE,
)
from .piksel import PikselIE
from .pinkbike import PinkbikeIE
from .pladform import PladformIE

49
youtube_dl/extractor/instagram.py
View File

@ -6,11 +6,16 @@ import json
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..compat import (
compat_str,
compat_HTTPError,
)
from ..utils import (
ExtractorError,
get_element_by_attribute,
int_or_none,
lowercase_escape,
std_headers,
try_get,
)
@ -239,6 +244,8 @@ class InstagramUserIE(InfoExtractor):
}
}
_gis_tmpl = None
def _entries(self, data):
def get_count(suffix):
return int_or_none(try_get(
@ -257,16 +264,36 @@ class InstagramUserIE(InfoExtractor):
'first': 100,
'after': cursor,
})
s = '%s:%s:%s' % (rhx_gis, csrf_token, variables)
media = self._download_json(
'https://www.instagram.com/graphql/query/', uploader_id,
'Downloading JSON page %d' % page_num, headers={
'X-Requested-With': 'XMLHttpRequest',
'X-Instagram-GIS': hashlib.md5(s.encode('utf-8')).hexdigest(),
}, query={
'query_hash': '472f257a40c653c64c666ce877d59d2b',
'variables': variables,
})['data']['user']['edge_owner_to_timeline_media']
if self._gis_tmpl:
gis_tmpls = [self._gis_tmpl]
else:
gis_tmpls = [
'%s' % rhx_gis,
'',
'%s:%s' % (rhx_gis, csrf_token),
'%s:%s:%s' % (rhx_gis, csrf_token, std_headers['User-Agent']),
]
for gis_tmpl in gis_tmpls:
try:
media = self._download_json(
'https://www.instagram.com/graphql/query/', uploader_id,
'Downloading JSON page %d' % page_num, headers={
'X-Requested-With': 'XMLHttpRequest',
'X-Instagram-GIS': hashlib.md5(
('%s:%s' % (gis_tmpl, variables)).encode('utf-8')).hexdigest(),
}, query={
'query_hash': '42323d64886122307be10013ad2dcc44',
'variables': variables,
})['data']['user']['edge_owner_to_timeline_media']
self._gis_tmpl = gis_tmpl
break
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
if gis_tmpl != gis_tmpls[-1]:
continue
raise
edges = media.get('edges')
if not edges or not isinstance(edges, list):

0
youtube_dl/extractor/joj.py Executable file → Normal file
View File

165
youtube_dl/extractor/picarto.py Normal file
View File

@ -0,0 +1,165 @@
# coding: utf-8
from __future__ import unicode_literals
import time
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
ExtractorError,
js_to_json,
try_get,
update_url_query,
urlencode_postdata,
)
class PicartoIE(InfoExtractor):
_VALID_URL = r'https?://(?:www.)?picarto\.tv/(?P<id>[a-zA-Z0-9]+)'
_TEST = {
'url': 'https://picarto.tv/Setz',
'info_dict': {
'id': 'Setz',
'ext': 'mp4',
'title': 're:^Setz [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'timestamp': int,
'is_live': True
},
'skip': 'Stream is offline',
}
@classmethod
def suitable(cls, url):
return False if PicartoVodIE.suitable(url) else super(PicartoIE, cls).suitable(url)
def _real_extract(self, url):
channel_id = self._match_id(url)
stream_page = self._download_webpage(url, channel_id)
if '>This channel does not exist' in stream_page:
raise ExtractorError(
'Channel %s does not exist' % channel_id, expected=True)
player = self._parse_json(
self._search_regex(
r'(?s)playerSettings\[\d+\]\s*=\s*(\{.+?\}\s*\n)', stream_page,
'player settings'),
channel_id, transform_source=js_to_json)
if player.get('online') is False:
raise ExtractorError('Stream is offline', expected=True)
cdn_data = self._download_json(
'https://picarto.tv/process/channel', channel_id,
data=urlencode_postdata({'loadbalancinginfo': channel_id}),
note='Downloading load balancing info')
def get_event(key):
return try_get(player, lambda x: x['event'][key], compat_str) or ''
params = {
'token': player.get('token') or '',
'ticket': get_event('ticket'),
'con': int(time.time() * 1000),
'type': get_event('ticket'),
'scope': get_event('scope'),
}
prefered_edge = cdn_data.get('preferedEdge')
default_tech = player.get('defaultTech')
formats = []
for edge in cdn_data['edges']:
edge_ep = edge.get('ep')
if not edge_ep or not isinstance(edge_ep, compat_str):
continue
edge_id = edge.get('id')
for tech in cdn_data['techs']:
tech_label = tech.get('label')
tech_type = tech.get('type')
preference = 0
if edge_id == prefered_edge:
preference += 1
if tech_type == default_tech:
preference += 1
format_id = []
if edge_id:
format_id.append(edge_id)
if tech_type == 'application/x-mpegurl' or tech_label == 'HLS':
format_id.append('hls')
formats.extend(self._extract_m3u8_formats(
update_url_query(
'https://%s/hls/%s/index.m3u8'
% (edge_ep, channel_id), params),
channel_id, 'mp4', preference=preference,
m3u8_id='-'.join(format_id), fatal=False))
continue
elif tech_type == 'video/mp4' or tech_label == 'MP4':
format_id.append('mp4')
formats.append({
'url': update_url_query(
'https://%s/mp4/%s.mp4' % (edge_ep, channel_id),
params),
'format_id': '-'.join(format_id),
'preference': preference,
})
else:
# rtmp format does not seem to work
continue
self._sort_formats(formats)
mature = player.get('mature')
if mature is None:
age_limit = None
else:
age_limit = 18 if mature is True else 0
return {
'id': channel_id,
'title': self._live_title(channel_id),
'is_live': True,
'thumbnail': player.get('vodThumb'),
'age_limit': age_limit,
'formats': formats,
}
class PicartoVodIE(InfoExtractor):
_VALID_URL = r'https?://(?:www.)?picarto\.tv/videopopout/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://picarto.tv/videopopout/ArtofZod_2017.12.12.00.13.23.flv',
'md5': '3ab45ba4352c52ee841a28fb73f2d9ca',
'info_dict': {
'id': 'ArtofZod_2017.12.12.00.13.23.flv',
'ext': 'mp4',
'title': 'ArtofZod_2017.12.12.00.13.23.flv',
'thumbnail': r're:^https?://.*\.jpg'
},
}, {
'url': 'https://picarto.tv/videopopout/Plague',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
vod_info = self._parse_json(
self._search_regex(
r'(?s)#vod-player["\']\s*,\s*(\{.+?\})\s*\)', webpage,
video_id),
video_id, transform_source=js_to_json)
formats = self._extract_m3u8_formats(
vod_info['vod'], video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls')
self._sort_formats(formats)
return {
'id': video_id,
'title': video_id,
'thumbnail': vod_info.get('vodThumb'),
'formats': formats,
}

12
youtube_dl/extractor/smotri.py
View File

@ -310,6 +310,7 @@ class SmotriBroadcastIE(InfoExtractor):
IE_DESC = 'Smotri.com broadcasts'
IE_NAME = 'smotri:broadcast'
_VALID_URL = r'https?://(?:www\.)?(?P<url>smotri\.com/live/(?P<id>[^/]+))/?.*'
_NETRC_MACHINE = 'smotri'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
@ -352,17 +353,18 @@ class SmotriBroadcastIE(InfoExtractor):
adult_content = False
ticket = self._html_search_regex(
r"window\.broadcast_control\.addFlashVar\('file'\s*,\s*'([^']+)'\)",
broadcast_page, 'broadcast ticket')
(r'data-user-file=(["\'])(?P<ticket>(?!\1).+)\1',
r"window\.broadcast_control\.addFlashVar\('file'\s*,\s*'(?P<ticket>[^']+)'\)"),
broadcast_page, 'broadcast ticket', group='ticket')
url = 'http://smotri.com/broadcast/view/url/?ticket=%s' % ticket
broadcast_url = 'http://smotri.com/broadcast/view/url/?ticket=%s' % ticket
broadcast_password = self._downloader.params.get('videopassword')
if broadcast_password:
url += '&pass=%s' % hashlib.md5(broadcast_password.encode('utf-8')).hexdigest()
broadcast_url += '&pass=%s' % hashlib.md5(broadcast_password.encode('utf-8')).hexdigest()
broadcast_json_page = self._download_webpage(
url, broadcast_id, 'Downloading broadcast JSON')
broadcast_url, broadcast_id, 'Downloading broadcast JSON')
try:
broadcast_json = json.loads(broadcast_json_page)

54
youtube_dl/extractor/vine.py
View File

@ -2,9 +2,9 @@
from __future__ import unicode_literals
import re
import itertools
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
determine_ext,
int_or_none,
@ -112,21 +112,24 @@ class VineIE(InfoExtractor):
class VineUserIE(InfoExtractor):
IE_NAME = 'vine:user'
_VALID_URL = r'(?:https?://)?vine\.co/(?P<u>u/)?(?P<user>[^/]+)/?(\?.*)?$'
_VALID_URL = r'https?://vine\.co/(?P<u>u/)?(?P<user>[^/]+)'
_VINE_BASE_URL = 'https://vine.co/'
_TESTS = [
{
'url': 'https://vine.co/Visa',
'info_dict': {
'id': 'Visa',
},
'playlist_mincount': 46,
_TESTS = [{
'url': 'https://vine.co/itsruthb',
'info_dict': {
'id': 'itsruthb',
'title': 'Ruth B',
'description': '| Instagram/Twitter: itsruthb | still a lost boy from neverland',
},
{
'url': 'https://vine.co/u/941705360593584128',
'only_matching': True,
},
]
'playlist_mincount': 611,
}, {
'url': 'https://vine.co/u/942914934646415360',
'only_matching': True,
}]
@classmethod
def suitable(cls, url):
return False if VineIE.suitable(url) else super(VineUserIE, cls).suitable(url)
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
@ -138,17 +141,14 @@ class VineUserIE(InfoExtractor):
profile_data = self._download_json(
profile_url, user, note='Downloading user profile data')
user_id = profile_data['data']['userId']
timeline_data = []
for pagenum in itertools.count(1):
timeline_url = '%sapi/timelines/users/%s?page=%s&size=100' % (
self._VINE_BASE_URL, user_id, pagenum)
timeline_page = self._download_json(
timeline_url, user, note='Downloading page %d' % pagenum)
timeline_data.extend(timeline_page['data']['records'])
if timeline_page['data']['nextPage'] is None:
break
data = profile_data['data']
user_id = data.get('userId') or data['userIdStr']
profile = self._download_json(
'https://archive.vine.co/profiles/%s.json' % user_id, user_id)
entries = [
self.url_result(e['permalinkUrl'], 'Vine') for e in timeline_data]
return self.playlist_result(entries, user)
self.url_result(
'https://vine.co/v/%s' % post_id, ie='Vine', video_id=post_id)
for post_id in profile['posts']
if post_id and isinstance(post_id, compat_str)]
return self.playlist_result(
entries, user, profile.get('username'), profile.get('description'))

2
youtube_dl/version.py
View File

@ -1,3 +1,3 @@
from __future__ import unicode_literals
__version__ = '2018.04.09'
__version__ = '2018.04.16'