Compare commits

..

10 Commits

13 changed files with 176 additions and 179 deletions

View File

@ -6,8 +6,8 @@
---
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.06.19.1*. 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 Issues with outdated version will be rejected.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 **2016.06.19.1**
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.06.20*. 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 Issues with outdated version will be rejected.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 **2016.06.20**
### 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 2016.06.19.1
[debug] youtube-dl version 2016.06.20
[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

@ -44,8 +44,8 @@
- **appletrailers:section**
- **archive.org**: archive.org videos
- **ARD**
- **ARD:mediathek**
- **ARD:mediathek**: Saarländischer Rundfunk
- **ARD:mediathek**
- **arte.tv**
- **arte.tv:+7**
- **arte.tv:cinema**

View File

@ -2,14 +2,24 @@ from __future__ import unicode_literals
import os.path
import re
import binascii
try:
from Crypto.Cipher import AES
can_decrypt_frag = True
except ImportError:
can_decrypt_frag = False
from .fragment import FragmentFD
from .external import FFmpegFD
from ..compat import compat_urlparse
from ..compat import (
compat_urlparse,
compat_struct_pack,
)
from ..utils import (
encodeFilename,
sanitize_open,
parse_m3u8_attributes,
)
@ -21,7 +31,7 @@ class HlsFD(FragmentFD):
@staticmethod
def can_download(manifest):
UNSUPPORTED_FEATURES = (
r'#EXT-X-KEY:METHOD=(?!NONE)', # encrypted streams [1]
r'#EXT-X-KEY:METHOD=(?!NONE|AES-128)', # encrypted streams [1]
r'#EXT-X-BYTERANGE', # playlists composed of byte ranges of media files [2]
# Live streams heuristic does not always work (e.g. geo restricted to Germany
@ -39,7 +49,9 @@ class HlsFD(FragmentFD):
# 3. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3.2
# 4. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3.5
)
return all(not re.search(feature, manifest) for feature in UNSUPPORTED_FEATURES)
check_results = [not re.search(feature, manifest) for feature in UNSUPPORTED_FEATURES]
check_results.append(can_decrypt_frag or '#EXT-X-KEY:METHOD=AES-128' not in manifest)
return all(check_results)
def real_download(self, filename, info_dict):
man_url = info_dict['url']
@ -57,36 +69,60 @@ class HlsFD(FragmentFD):
fd.add_progress_hook(ph)
return fd.real_download(filename, info_dict)
fragment_urls = []
total_frags = 0
for line in s.splitlines():
line = line.strip()
if line and not line.startswith('#'):
segment_url = (
line
if re.match(r'^https?://', line)
else compat_urlparse.urljoin(man_url, line))
fragment_urls.append(segment_url)
# We only download the first fragment during the test
if self.params.get('test', False):
break
total_frags += 1
ctx = {
'filename': filename,
'total_frags': len(fragment_urls),
'total_frags': total_frags,
}
self._prepare_and_start_frag_download(ctx)
i = 0
media_sequence = 0
decrypt_info = {'METHOD': 'NONE'}
frags_filenames = []
for i, frag_url in enumerate(fragment_urls):
frag_filename = '%s-Frag%d' % (ctx['tmpfilename'], i)
success = ctx['dl'].download(frag_filename, {'url': frag_url})
if not success:
return False
down, frag_sanitized = sanitize_open(frag_filename, 'rb')
ctx['dest_stream'].write(down.read())
down.close()
frags_filenames.append(frag_sanitized)
for line in s.splitlines():
line = line.strip()
if line:
if not line.startswith('#'):
frag_url = (
line
if re.match(r'^https?://', line)
else compat_urlparse.urljoin(man_url, line))
frag_filename = '%s-Frag%d' % (ctx['tmpfilename'], i)
success = ctx['dl'].download(frag_filename, {'url': frag_url})
if not success:
return False
down, frag_sanitized = sanitize_open(frag_filename, 'rb')
frag_content = down.read()
down.close()
if decrypt_info['METHOD'] == 'AES-128':
iv = decrypt_info.get('IV') or compat_struct_pack('>8xq', media_sequence)
frag_content = AES.new(
decrypt_info['KEY'], AES.MODE_CBC, iv).decrypt(frag_content)
ctx['dest_stream'].write(frag_content)
frags_filenames.append(frag_sanitized)
# We only download the first fragment during the test
if self.params.get('test', False):
break
i += 1
media_sequence += 1
elif line.startswith('#EXT-X-KEY'):
decrypt_info = parse_m3u8_attributes(line[11:])
if decrypt_info['METHOD'] == 'AES-128':
if 'IV' in decrypt_info:
decrypt_info['IV'] = binascii.unhexlify(decrypt_info['IV'][2:])
if not re.match(r'^https?://', decrypt_info['URI']):
decrypt_info['URI'] = compat_urlparse.urljoin(
man_url, decrypt_info['URI'])
decrypt_info['KEY'] = self.ydl.urlopen(decrypt_info['URI']).read()
elif line.startswith('#EXT-X-MEDIA-SEQUENCE'):
media_sequence = int(line[22:])
self._finish_frag_download(ctx)

View File

@ -2,16 +2,14 @@ from __future__ import unicode_literals
import re
from .theplatform import ThePlatformIE
from .theplatform import ThePlatformFeedIE
from ..utils import (
xpath_text,
xpath_element,
int_or_none,
find_xpath_attr,
)
class CBSBaseIE(ThePlatformIE):
class CBSBaseIE(ThePlatformFeedIE):
def _parse_smil_subtitles(self, smil, namespace=None, subtitles_lang='en'):
closed_caption_e = find_xpath_attr(smil, self._xpath_ns('.//param', namespace), 'name', 'ClosedCaptionURL')
return {
@ -21,9 +19,22 @@ class CBSBaseIE(ThePlatformIE):
}]
} if closed_caption_e is not None and closed_caption_e.attrib.get('value') else []
def _extract_video_info(self, filter_query, video_id):
return self._extract_feed_info(
'dJ5BDC', 'VxxJg8Ymh8sE', filter_query, video_id, lambda entry: {
'series': entry.get('cbs$SeriesTitle'),
'season_number': int_or_none(entry.get('cbs$SeasonNumber')),
'episode': entry.get('cbs$EpisodeTitle'),
'episode_number': int_or_none(entry.get('cbs$EpisodeNumber')),
}, {
'StreamPack': {
'manifest': 'm3u',
}
})
class CBSIE(CBSBaseIE):
_VALID_URL = r'(?:cbs:(?P<content_id>\w+)|https?://(?:www\.)?(?:cbs\.com/shows/[^/]+/(?:video|artist)|colbertlateshow\.com/(?:video|podcasts))/[^/]+/(?P<display_id>[^/]+))'
_VALID_URL = r'(?:cbs:|https?://(?:www\.)?(?:cbs\.com/shows/[^/]+/video|colbertlateshow\.com/(?:video|podcasts))/)(?P<id>[\w-]+)'
_TESTS = [{
'url': 'http://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/',
@ -38,25 +49,7 @@ class CBSIE(CBSBaseIE):
'upload_date': '20131127',
'uploader': 'CBSI-NEW',
},
'params': {
# rtmp download
'skip_download': True,
},
'_skip': 'Blocked outside the US',
}, {
'url': 'http://www.cbs.com/shows/liveonletterman/artist/221752/st-vincent/',
'info_dict': {
'id': 'WWF_5KqY3PK1',
'display_id': 'st-vincent',
'ext': 'flv',
'title': 'Live on Letterman - St. Vincent',
'description': 'Live On Letterman: St. Vincent in concert from New York\'s Ed Sullivan Theater on Tuesday, July 16, 2014.',
'duration': 3221,
},
'params': {
# rtmp download
'skip_download': True,
},
'expected_warnings': ['Failed to download m3u8 information'],
'_skip': 'Blocked outside the US',
}, {
'url': 'http://colbertlateshow.com/video/8GmB0oY0McANFvp2aEffk9jZZZ2YyXxy/the-colbeard/',
@ -68,44 +61,5 @@ class CBSIE(CBSBaseIE):
TP_RELEASE_URL_TEMPLATE = 'http://link.theplatform.com/s/dJ5BDC/%s?mbr=true'
def _real_extract(self, url):
content_id, display_id = re.match(self._VALID_URL, url).groups()
if not content_id:
webpage = self._download_webpage(url, display_id)
content_id = self._search_regex(
[r"video\.settings\.content_id\s*=\s*'([^']+)';", r"cbsplayer\.contentId\s*=\s*'([^']+)';"],
webpage, 'content id')
items_data = self._download_xml(
'http://can.cbs.com/thunder/player/videoPlayerService.php',
content_id, query={'partner': 'cbs', 'contentId': content_id})
video_data = xpath_element(items_data, './/item')
title = xpath_text(video_data, 'videoTitle', 'title', True)
subtitles = {}
formats = []
for item in items_data.findall('.//item'):
pid = xpath_text(item, 'pid')
if not pid:
continue
tp_release_url = self.TP_RELEASE_URL_TEMPLATE % pid
if '.m3u8' in xpath_text(item, 'contentUrl', default=''):
tp_release_url += '&manifest=m3u'
tp_formats, tp_subtitles = self._extract_theplatform_smil(
tp_release_url, content_id, 'Downloading %s SMIL data' % pid)
formats.extend(tp_formats)
subtitles = self._merge_subtitles(subtitles, tp_subtitles)
self._sort_formats(formats)
info = self.get_metadata('dJ5BDC/media/guid/2198311517/%s' % content_id, content_id)
info.update({
'id': content_id,
'display_id': display_id,
'title': title,
'series': xpath_text(video_data, 'seriesTitle'),
'season_number': int_or_none(xpath_text(video_data, 'seasonNumber')),
'episode_number': int_or_none(xpath_text(video_data, 'episodeNumber')),
'duration': int_or_none(xpath_text(video_data, 'videoLength'), 1000),
'thumbnail': xpath_text(video_data, 'previewImageURL'),
'formats': formats,
'subtitles': subtitles,
})
return info
content_id = self._match_id(url)
return self._extract_video_info('byGuid=%s' % content_id, content_id)

View File

@ -30,9 +30,12 @@ class CBSNewsIE(CBSBaseIE):
{
'url': 'http://www.cbsnews.com/videos/fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack/',
'info_dict': {
'id': 'fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack',
'id': 'SNJBOYzXiWBOvaLsdzwH8fmtP1SCd91Y',
'ext': 'mp4',
'title': 'Fort Hood shooting: Army downplays mental illness as cause of attack',
'description': 'md5:4a6983e480542d8b333a947bfc64ddc7',
'upload_date': '19700101',
'uploader': 'CBSI-NEW',
'thumbnail': 're:^https?://.*\.jpg$',
'duration': 205,
'subtitles': {
@ -58,30 +61,8 @@ class CBSNewsIE(CBSBaseIE):
webpage, 'video JSON info'), video_id)
item = video_info['item'] if 'item' in video_info else video_info
title = item.get('articleTitle') or item.get('hed')
duration = item.get('duration')
thumbnail = item.get('mediaImage') or item.get('thumbnail')
subtitles = {}
formats = []
for format_id in ['RtmpMobileLow', 'RtmpMobileHigh', 'Hls', 'RtmpDesktop']:
pid = item.get('media' + format_id)
if not pid:
continue
release_url = 'http://link.theplatform.com/s/dJ5BDC/%s?mbr=true' % pid
tp_formats, tp_subtitles = self._extract_theplatform_smil(release_url, video_id, 'Downloading %s SMIL data' % pid)
formats.extend(tp_formats)
subtitles = self._merge_subtitles(subtitles, tp_subtitles)
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'thumbnail': thumbnail,
'duration': duration,
'formats': formats,
'subtitles': subtitles,
}
guid = item['mpxRefId']
return self._extract_video_info('byGuid=%s' % guid, guid)
class CBSNewsLiveVideoIE(InfoExtractor):

View File

@ -1,30 +1,28 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from .cbs import CBSBaseIE
class CBSSportsIE(InfoExtractor):
_VALID_URL = r'https?://www\.cbssports\.com/video/player/(?P<section>[^/]+)/(?P<id>[^/]+)'
class CBSSportsIE(CBSBaseIE):
_VALID_URL = r'https?://www\.cbssports\.com/video/player/[^/]+/(?P<id>\d+)'
_TEST = {
'url': 'http://www.cbssports.com/video/player/tennis/318462531970/0/us-open-flashbacks-1990s',
_TESTS = [{
'url': 'http://www.cbssports.com/video/player/videos/708337219968/0/ben-simmons-the-next-lebron?-not-so-fast',
'info_dict': {
'id': '_d5_GbO8p1sT',
'ext': 'flv',
'title': 'US Open flashbacks: 1990s',
'description': 'Bill Macatee relives the best moments in US Open history from the 1990s.',
'id': '708337219968',
'ext': 'mp4',
'title': 'Ben Simmons the next LeBron? Not so fast',
'description': 'md5:854294f627921baba1f4b9a990d87197',
'timestamp': 1466293740,
'upload_date': '20160618',
'uploader': 'CBSI-NEW',
},
}
'params': {
# m3u8 download
'skip_download': True,
}
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
section = mobj.group('section')
video_id = mobj.group('id')
all_videos = self._download_json(
'http://www.cbssports.com/data/video/player/getVideos/%s?as=json' % section,
video_id)
# The json file contains the info of all the videos in the section
video_info = next(v for v in all_videos if v['pcid'] == video_id)
return self.url_result('theplatform:%s' % video_info['pid'], 'ThePlatform')
video_id = self._match_id(url)
return self._extract_video_info('byId=%s' % video_id, video_id)

View File

@ -53,6 +53,7 @@ from ..utils import (
mimetype2ext,
update_Request,
update_url_query,
parse_m3u8_attributes,
)
@ -1150,23 +1151,11 @@ class InfoExtractor(object):
}]
last_info = None
last_media = None
kv_rex = re.compile(
r'(?P<key>[a-zA-Z_-]+)=(?P<val>"[^"]+"|[^",]+)(?:,|$)')
for line in m3u8_doc.splitlines():
if line.startswith('#EXT-X-STREAM-INF:'):
last_info = {}
for m in kv_rex.finditer(line):
v = m.group('val')
if v.startswith('"'):
v = v[1:-1]
last_info[m.group('key')] = v
last_info = parse_m3u8_attributes(line)
elif line.startswith('#EXT-X-MEDIA:'):
last_media = {}
for m in kv_rex.finditer(line):
v = m.group('val')
if v.startswith('"'):
v = v[1:-1]
last_media[m.group('key')] = v
last_media = parse_m3u8_attributes(line)
elif line.startswith('#') or not line.strip():
continue
else:

View File

@ -1,7 +1,10 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import smuggle_url
from ..utils import (
smuggle_url,
update_url_query,
)
class FoxSportsIE(InfoExtractor):
@ -9,11 +12,15 @@ class FoxSportsIE(InfoExtractor):
_TEST = {
'url': 'http://www.foxsports.com/video?vid=432609859715',
'md5': 'b49050e955bebe32c301972e4012ac17',
'info_dict': {
'id': 'gA0bHB3Ladz3',
'ext': 'flv',
'id': 'i0qKWsk3qJaM',
'ext': 'mp4',
'title': 'Courtney Lee on going up 2-0 in series vs. Blazers',
'description': 'Courtney Lee talks about Memphis being focused.',
'upload_date': '20150423',
'timestamp': 1429761109,
'uploader': 'NEWA-FNG-FOXSPORTS',
},
'add_ie': ['ThePlatform'],
}
@ -28,5 +35,8 @@ class FoxSportsIE(InfoExtractor):
r"data-player-config='([^']+)'", webpage, 'data player config'),
video_id)
return self.url_result(smuggle_url(
config['releaseURL'] + '&manifest=f4m', {'force_smil_url': True}))
return self.url_result(smuggle_url(update_url_query(
config['releaseURL'], {
'mbr': 'true',
'switch': 'http',
}), {'force_smil_url': True}))

View File

@ -3,7 +3,7 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import(
from ..utils import (
unified_strdate,
str_to_int,
)

View File

@ -277,9 +277,9 @@ class ThePlatformIE(ThePlatformBaseIE):
class ThePlatformFeedIE(ThePlatformBaseIE):
_URL_TEMPLATE = '%s//feed.theplatform.com/f/%s/%s?form=json&byGuid=%s'
_VALID_URL = r'https?://feed\.theplatform\.com/f/(?P<provider_id>[^/]+)/(?P<feed_id>[^?/]+)\?(?:[^&]+&)*byGuid=(?P<id>[a-zA-Z0-9_]+)'
_TEST = {
_URL_TEMPLATE = '%s//feed.theplatform.com/f/%s/%s?form=json&%s'
_VALID_URL = r'https?://feed\.theplatform\.com/f/(?P<provider_id>[^/]+)/(?P<feed_id>[^?/]+)\?(?:[^&]+&)*(?P<filter>by(?:Gui|I)d=(?P<id>[\w-]+))'
_TESTS = [{
# From http://player.theplatform.com/p/7wvmTC/MSNBCEmbeddedOffSite?guid=n_hardball_5biden_140207
'url': 'http://feed.theplatform.com/f/7wvmTC/msnbc_video-p-test?form=json&pretty=true&range=-40&byGuid=n_hardball_5biden_140207',
'md5': '6e32495b5073ab414471b615c5ded394',
@ -295,32 +295,38 @@ class ThePlatformFeedIE(ThePlatformBaseIE):
'categories': ['MSNBC/Issues/Democrats', 'MSNBC/Issues/Elections/Election 2016'],
'uploader': 'NBCU-NEWS',
},
}
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
provider_id = mobj.group('provider_id')
feed_id = mobj.group('feed_id')
real_url = self._URL_TEMPLATE % (self.http_scheme(), provider_id, feed_id, video_id)
feed = self._download_json(real_url, video_id)
entry = feed['entries'][0]
def _extract_feed_info(self, provider_id, feed_id, filter_query, video_id, custom_fields=None, asset_types_query={}):
real_url = self._URL_TEMPLATE % (self.http_scheme(), provider_id, feed_id, filter_query)
entry = self._download_json(real_url, video_id)['entries'][0]
formats = []
subtitles = {}
first_video_id = None
duration = None
asset_types = []
for item in entry['media$content']:
smil_url = item['plfile$url'] + '&mbr=true'
smil_url = item['plfile$url']
cur_video_id = ThePlatformIE._match_id(smil_url)
if first_video_id is None:
first_video_id = cur_video_id
duration = float_or_none(item.get('plfile$duration'))
cur_formats, cur_subtitles = self._extract_theplatform_smil(smil_url, video_id, 'Downloading SMIL data for %s' % cur_video_id)
formats.extend(cur_formats)
subtitles = self._merge_subtitles(subtitles, cur_subtitles)
for asset_type in item['plfile$assetTypes']:
if asset_type in asset_types:
continue
asset_types.append(asset_type)
query = {
'mbr': 'true',
'formats': item['plfile$format'],
'assetTypes': asset_type,
}
if asset_type in asset_types_query:
query.update(asset_types_query[asset_type])
cur_formats, cur_subtitles = self._extract_theplatform_smil(update_url_query(
smil_url, query), video_id, 'Downloading SMIL data for %s' % asset_type)
formats.extend(cur_formats)
subtitles = self._merge_subtitles(subtitles, cur_subtitles)
self._sort_formats(formats)
@ -344,5 +350,17 @@ class ThePlatformFeedIE(ThePlatformBaseIE):
'timestamp': timestamp,
'categories': categories,
})
if custom_fields:
ret.update(custom_fields(entry))
return ret
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
provider_id = mobj.group('provider_id')
feed_id = mobj.group('feed_id')
filter_query = mobj.group('filter')
return self._extract_feed_info(provider_id, feed_id, filter_query, video_id)

View File

@ -131,8 +131,9 @@ class JSInterpreter(object):
if variable in local_vars:
obj = local_vars[variable]
else:
obj = self._objects.setdefault(
variable, self.extract_object(variable))
if variable not in self._objects:
self._objects[variable] = self.extract_object(variable)
obj = self._objects[variable]
if arg_str is None:
# Member access
@ -203,7 +204,8 @@ class JSInterpreter(object):
argvals = tuple([
int(v) if v.isdigit() else local_vars[v]
for v in m.group('args').split(',')])
self._functions.setdefault(fname, self.extract_function(fname))
if fname not in self._functions:
self._functions[fname] = self.extract_function(fname)
return self._functions[fname](argvals)
raise ExtractorError('Unsupported JS expression %r' % expr)

View File

@ -2852,3 +2852,12 @@ def decode_packed_codes(code):
return re.sub(
r'\b(\w+)\b', lambda mobj: symbol_table[mobj.group(0)],
obfucasted_code)
def parse_m3u8_attributes(attrib):
info = {}
for (key, val) in re.findall(r'(?P<key>[A-Z0-9-]+)=(?P<val>"[^"]+"|[^",]+)(?:,|$)', attrib):
if val.startswith('"'):
val = val[1:-1]
info[key] = val
return info

View File

@ -1,3 +1,3 @@
from __future__ import unicode_literals
__version__ = '2016.06.19.1'
__version__ = '2016.06.20'