Merge branch 'master' of https://github.com/rg3/youtube-dl
This commit is contained in:
Gilles Habran
commit
91ba156b43
@ -319,7 +319,7 @@ class F4mFD(FragmentFD):
|
||||
doc = compat_etree_fromstring(manifest)
|
||||
formats = [(int(f.attrib.get('bitrate', -1)), f)
|
||||
for f in self._get_unencrypted_media(doc)]
|
||||
if requested_bitrate is None:
|
||||
if requested_bitrate is None or len(formats) == 1:
|
||||
# get the best format
|
||||
formats = sorted(formats, key=lambda f: f[0])
|
||||
rate, media = formats[-1]
|
||||
|
||||
@ -987,7 +987,7 @@ class InfoExtractor(object):
|
||||
|
||||
def _extract_f4m_formats(self, manifest_url, video_id, preference=None, f4m_id=None,
|
||||
transform_source=lambda s: fix_xml_ampersands(s).strip(),
|
||||
fatal=True):
|
||||
fatal=True, m3u8_id=None):
|
||||
manifest = self._download_xml(
|
||||
manifest_url, video_id, 'Downloading f4m manifest',
|
||||
'Unable to download f4m manifest',
|
||||
@ -1001,11 +1001,11 @@ class InfoExtractor(object):
|
||||
|
||||
return self._parse_f4m_formats(
|
||||
manifest, manifest_url, video_id, preference=preference, f4m_id=f4m_id,
|
||||
transform_source=transform_source, fatal=fatal)
|
||||
transform_source=transform_source, fatal=fatal, m3u8_id=m3u8_id)
|
||||
|
||||
def _parse_f4m_formats(self, manifest, manifest_url, video_id, preference=None, f4m_id=None,
|
||||
transform_source=lambda s: fix_xml_ampersands(s).strip(),
|
||||
fatal=True):
|
||||
fatal=True, m3u8_id=None):
|
||||
# currently youtube-dl cannot decode the playerVerificationChallenge as Akamai uses Adobe Alchemy
|
||||
akamai_pv = manifest.find('{http://ns.adobe.com/f4m/1.0}pv-2.0')
|
||||
if akamai_pv is not None and ';' in akamai_pv.text:
|
||||
@ -1029,9 +1029,26 @@ class InfoExtractor(object):
|
||||
'base URL', default=None)
|
||||
if base_url:
|
||||
base_url = base_url.strip()
|
||||
|
||||
bootstrap_info = xpath_text(
|
||||
manifest, ['{http://ns.adobe.com/f4m/1.0}bootstrapInfo', '{http://ns.adobe.com/f4m/2.0}bootstrapInfo'],
|
||||
'bootstrap info', default=None)
|
||||
|
||||
for i, media_el in enumerate(media_nodes):
|
||||
tbr = int_or_none(media_el.attrib.get('bitrate'))
|
||||
width = int_or_none(media_el.attrib.get('width'))
|
||||
height = int_or_none(media_el.attrib.get('height'))
|
||||
format_id = '-'.join(filter(None, [f4m_id, compat_str(i if tbr is None else tbr)]))
|
||||
# If <bootstrapInfo> is present, the specified f4m is a
|
||||
# stream-level manifest, and only set-level manifests may refer to
|
||||
# external resources. See section 11.4 and section 4 of F4M spec
|
||||
if bootstrap_info is None:
|
||||
media_url = None
|
||||
# @href is introduced in 2.0, see section 11.6 of F4M spec
|
||||
if manifest_version == '2.0':
|
||||
media_url = media_el.attrib.get('href') or media_el.attrib.get('url')
|
||||
media_url = media_el.attrib.get('href')
|
||||
if media_url is None:
|
||||
media_url = media_el.attrib.get('url')
|
||||
if not media_url:
|
||||
continue
|
||||
manifest_url = (
|
||||
@ -1041,19 +1058,37 @@ class InfoExtractor(object):
|
||||
# since bitrates in parent manifest (this one) and media_url manifest
|
||||
# may differ leading to inability to resolve the format by requested
|
||||
# bitrate in f4m downloader
|
||||
if determine_ext(manifest_url) == 'f4m':
|
||||
formats.extend(self._extract_f4m_formats(
|
||||
ext = determine_ext(manifest_url)
|
||||
if ext == 'f4m':
|
||||
f4m_formats = self._extract_f4m_formats(
|
||||
manifest_url, video_id, preference=preference, f4m_id=f4m_id,
|
||||
transform_source=transform_source, fatal=fatal))
|
||||
transform_source=transform_source, fatal=fatal)
|
||||
# Sometimes stream-level manifest contains single media entry that
|
||||
# does not contain any quality metadata (e.g. http://matchtv.ru/#live-player).
|
||||
# At the same time parent's media entry in set-level manifest may
|
||||
# contain it. We will copy it from parent in such cases.
|
||||
if len(f4m_formats) == 1:
|
||||
f = f4m_formats[0]
|
||||
f.update({
|
||||
'tbr': f.get('tbr') or tbr,
|
||||
'width': f.get('width') or width,
|
||||
'height': f.get('height') or height,
|
||||
'format_id': f.get('format_id') if not tbr else format_id,
|
||||
})
|
||||
formats.extend(f4m_formats)
|
||||
continue
|
||||
elif ext == 'm3u8':
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
manifest_url, video_id, 'mp4', preference=preference,
|
||||
m3u8_id=m3u8_id, fatal=fatal))
|
||||
continue
|
||||
tbr = int_or_none(media_el.attrib.get('bitrate'))
|
||||
formats.append({
|
||||
'format_id': '-'.join(filter(None, [f4m_id, compat_str(i if tbr is None else tbr)])),
|
||||
'format_id': format_id,
|
||||
'url': manifest_url,
|
||||
'ext': 'flv',
|
||||
'ext': 'flv' if bootstrap_info else None,
|
||||
'tbr': tbr,
|
||||
'width': int_or_none(media_el.attrib.get('width')),
|
||||
'height': int_or_none(media_el.attrib.get('height')),
|
||||
'width': width,
|
||||
'height': height,
|
||||
'preference': preference,
|
||||
})
|
||||
return formats
|
||||
|
||||
@ -2,13 +2,16 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import int_or_none
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
unified_strdate,
|
||||
)
|
||||
from ..compat import compat_urlparse
|
||||
|
||||
|
||||
class DWIE(InfoExtractor):
|
||||
IE_NAME = 'dw'
|
||||
_VALID_URL = r'https?://(?:www\.)?dw\.com/(?:[^/]+/)+av-(?P<id>\d+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?dw\.com/(?:[^/]+/)+(?:av|e)-(?P<id>\d+)'
|
||||
_TESTS = [{
|
||||
# video
|
||||
'url': 'http://www.dw.com/en/intelligent-light/av-19112290',
|
||||
@ -31,6 +34,16 @@ class DWIE(InfoExtractor):
|
||||
'description': 'md5:bc9ca6e4e063361e21c920c53af12405',
|
||||
'upload_date': '20160311',
|
||||
}
|
||||
}, {
|
||||
'url': 'http://www.dw.com/en/documentaries-welcome-to-the-90s-2016-05-21/e-19220158-9798',
|
||||
'md5': '56b6214ef463bfb9a3b71aeb886f3cf1',
|
||||
'info_dict': {
|
||||
'id': '19274438',
|
||||
'ext': 'mp4',
|
||||
'title': 'Welcome to the 90s – Hip Hop',
|
||||
'description': 'Welcome to the 90s - The Golden Decade of Hip Hop',
|
||||
'upload_date': '20160521',
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
@ -38,6 +51,7 @@ class DWIE(InfoExtractor):
|
||||
webpage = self._download_webpage(url, media_id)
|
||||
hidden_inputs = self._hidden_inputs(webpage)
|
||||
title = hidden_inputs['media_title']
|
||||
media_id = hidden_inputs.get('media_id') or media_id
|
||||
|
||||
if hidden_inputs.get('player_type') == 'video' and hidden_inputs.get('stream_file') == '1':
|
||||
formats = self._extract_smil_formats(
|
||||
@ -49,13 +63,20 @@ class DWIE(InfoExtractor):
|
||||
else:
|
||||
formats = [{'url': hidden_inputs['file_name']}]
|
||||
|
||||
upload_date = hidden_inputs.get('display_date')
|
||||
if not upload_date:
|
||||
upload_date = self._html_search_regex(
|
||||
r'<span[^>]+class="date">([0-9.]+)\s*\|', webpage,
|
||||
'upload date', default=None)
|
||||
upload_date = unified_strdate(upload_date)
|
||||
|
||||
return {
|
||||
'id': media_id,
|
||||
'title': title,
|
||||
'description': self._og_search_description(webpage),
|
||||
'thumbnail': hidden_inputs.get('preview_image'),
|
||||
'duration': int_or_none(hidden_inputs.get('file_duration')),
|
||||
'upload_date': hidden_inputs.get('display_date'),
|
||||
'upload_date': upload_date,
|
||||
'formats': formats,
|
||||
}
|
||||
|
||||
|
||||
@ -24,20 +24,10 @@ class EpornerIE(InfoExtractor):
|
||||
'view_count': int,
|
||||
'age_limit': 18,
|
||||
},
|
||||
},
|
||||
}, {
|
||||
# New (May 2016) URL layout
|
||||
{
|
||||
'url': 'http://www.eporner.com/hd-porn/3YRUtzMcWn0/Star-Wars-XXX-Parody/',
|
||||
'md5': '3469eeaa93b6967a34cdbdbb9d064b33',
|
||||
'info_dict': {
|
||||
'id': '3YRUtzMcWn0',
|
||||
'display_id': 'Star-Wars-XXX-Parody',
|
||||
'ext': 'mp4',
|
||||
'title': 'Star Wars XXX Parody',
|
||||
'duration': 361.0,
|
||||
'view_count': int,
|
||||
'age_limit': 18,
|
||||
},
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
||||
@ -833,7 +833,10 @@ from .tvc import (
|
||||
)
|
||||
from .tvigle import TvigleIE
|
||||
from .tvland import TVLandIE
|
||||
from .tvp import TvpIE, TvpSeriesIE
|
||||
from .tvp import (
|
||||
TVPIE,
|
||||
TVPSeriesIE,
|
||||
)
|
||||
from .tvplay import TVPlayIE
|
||||
from .tweakers import TweakersIE
|
||||
from .twentyfourvideo import TwentyFourVideoIE
|
||||
|
||||
@ -4,9 +4,8 @@ import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
xpath_text,
|
||||
dict_get,
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
)
|
||||
|
||||
|
||||
@ -23,6 +22,19 @@ class PlaywireIE(InfoExtractor):
|
||||
'duration': 145.94,
|
||||
},
|
||||
}, {
|
||||
# m3u8 in f4m
|
||||
'url': 'http://config.playwire.com/21772/videos/v2/4840492/zeus.json',
|
||||
'info_dict': {
|
||||
'id': '4840492',
|
||||
'ext': 'mp4',
|
||||
'title': 'ITV EL SHOW FULL',
|
||||
},
|
||||
'params': {
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
# Multiple resolutions while bitrates missing
|
||||
'url': 'http://cdn.playwire.com/11625/embed/85228.html',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
@ -48,25 +60,10 @@ class PlaywireIE(InfoExtractor):
|
||||
thumbnail = content.get('poster')
|
||||
src = content['media']['f4m']
|
||||
|
||||
f4m = self._download_xml(src, video_id)
|
||||
base_url = xpath_text(f4m, './{http://ns.adobe.com/f4m/1.0}baseURL', 'base url', fatal=True)
|
||||
formats = []
|
||||
for media in f4m.findall('./{http://ns.adobe.com/f4m/1.0}media'):
|
||||
media_url = media.get('url')
|
||||
if not media_url:
|
||||
continue
|
||||
tbr = int_or_none(media.get('bitrate'))
|
||||
width = int_or_none(media.get('width'))
|
||||
height = int_or_none(media.get('height'))
|
||||
f = {
|
||||
'url': '%s/%s' % (base_url, media.attrib['url']),
|
||||
'tbr': tbr,
|
||||
'width': width,
|
||||
'height': height,
|
||||
}
|
||||
if not (tbr or width or height):
|
||||
f['quality'] = 1 if '-hd.' in media_url else 0
|
||||
formats.append(f)
|
||||
formats = self._extract_f4m_formats(src, video_id, m3u8_id='hls')
|
||||
for a_format in formats:
|
||||
if not dict_get(a_format, ['tbr', 'width', 'height']):
|
||||
a_format['quality'] = 1 if '-hd.' in a_format['url'] else 0
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
|
||||
@ -1,4 +1,4 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
@ -6,20 +6,13 @@ import re
|
||||
from .common import InfoExtractor
|
||||
|
||||
|
||||
class TvpIE(InfoExtractor):
|
||||
IE_NAME = 'tvp.pl'
|
||||
_VALID_URL = r'https?://(?:vod|www)\.tvp\.pl/.*/(?P<id>\d+)$'
|
||||
class TVPIE(InfoExtractor):
|
||||
IE_NAME = 'tvp'
|
||||
IE_DESC = 'Telewizja Polska'
|
||||
_VALID_URL = r'https?://[^/]+\.tvp\.(?:pl|info)/(?:(?!\d+/)[^/]+/)*(?P<id>\d+)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://vod.tvp.pl/filmy-fabularne/filmy-za-darmo/ogniem-i-mieczem/wideo/odc-2/4278035',
|
||||
'md5': 'cdd98303338b8a7f7abab5cd14092bf2',
|
||||
'info_dict': {
|
||||
'id': '4278035',
|
||||
'ext': 'wmv',
|
||||
'title': 'Ogniem i mieczem, odc. 2',
|
||||
},
|
||||
}, {
|
||||
'url': 'http://vod.tvp.pl/seriale/obyczajowe/czas-honoru/sezon-1-1-13/i-seria-odc-13/194536',
|
||||
'url': 'http://vod.tvp.pl/194536/i-seria-odc-13',
|
||||
'md5': '8aa518c15e5cc32dfe8db400dc921fbb',
|
||||
'info_dict': {
|
||||
'id': '194536',
|
||||
@ -36,12 +29,22 @@ class TvpIE(InfoExtractor):
|
||||
},
|
||||
}, {
|
||||
'url': 'http://vod.tvp.pl/seriale/obyczajowe/na-sygnale/sezon-2-27-/odc-39/17834272',
|
||||
'md5': 'c3b15ed1af288131115ff17a17c19dda',
|
||||
'info_dict': {
|
||||
'id': '17834272',
|
||||
'ext': 'mp4',
|
||||
'title': 'Na sygnale, odc. 39',
|
||||
},
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://wiadomosci.tvp.pl/25169746/24052016-1200',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://krakow.tvp.pl/25511623/25lecie-mck-wyjatkowe-miejsce-na-mapie-krakowa',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://teleexpress.tvp.pl/25522307/wierni-wzieli-udzial-w-procesjach',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://sport.tvp.pl/25522165/krychowiak-uspokaja-w-sprawie-kontuzji-dwa-tygodnie-to-maksimum',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.tvp.info/25511919/trwa-rewolucja-wladza-zdecydowala-sie-na-pogwalcenie-konstytucji',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
@ -92,8 +95,8 @@ class TvpIE(InfoExtractor):
|
||||
}
|
||||
|
||||
|
||||
class TvpSeriesIE(InfoExtractor):
|
||||
IE_NAME = 'tvp.pl:Series'
|
||||
class TVPSeriesIE(InfoExtractor):
|
||||
IE_NAME = 'tvp:series'
|
||||
_VALID_URL = r'https?://vod\.tvp\.pl/(?:[^/]+/){2}(?P<id>[^/]+)/?$'
|
||||
|
||||
_TESTS = [{
|
||||
@ -127,7 +130,7 @@ class TvpSeriesIE(InfoExtractor):
|
||||
videos_paths = re.findall(
|
||||
'(?s)class="shortTitle">.*?href="(/[^"]+)', playlist)
|
||||
entries = [
|
||||
self.url_result('http://vod.tvp.pl%s' % v_path, ie=TvpIE.ie_key())
|
||||
self.url_result('http://vod.tvp.pl%s' % v_path, ie=TVPIE.ie_key())
|
||||
for v_path in videos_paths]
|
||||
|
||||
return {
|
||||
|
||||
@ -1,8 +1,7 @@
|
||||
# coding: utf-8
|
||||
from __future__ import division, unicode_literals
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
import time
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
@ -23,7 +22,7 @@ class VLiveIE(InfoExtractor):
|
||||
'info_dict': {
|
||||
'id': '1326',
|
||||
'ext': 'mp4',
|
||||
'title': "[V] Girl's Day's Broadcast",
|
||||
'title': "[V LIVE] Girl's Day's Broadcast",
|
||||
'creator': "Girl's Day",
|
||||
'view_count': int,
|
||||
},
|
||||
@ -35,24 +34,11 @@ class VLiveIE(InfoExtractor):
|
||||
webpage = self._download_webpage(
|
||||
'http://www.vlive.tv/video/%s' % video_id, video_id)
|
||||
|
||||
# UTC+x - UTC+9 (KST)
|
||||
tz = time.altzone if time.localtime().tm_isdst == 1 else time.timezone
|
||||
tz_offset = -tz // 60 - 9 * 60
|
||||
self._set_cookie('vlive.tv', 'timezoneOffset', '%d' % tz_offset)
|
||||
|
||||
status_params = self._download_json(
|
||||
'http://www.vlive.tv/video/status?videoSeq=%s' % video_id,
|
||||
video_id, 'Downloading JSON status',
|
||||
headers={'Referer': url.encode('utf-8')})
|
||||
status = status_params.get('status')
|
||||
air_start = status_params.get('onAirStartAt', '')
|
||||
is_live = status_params.get('isLive')
|
||||
|
||||
video_params = self._search_regex(
|
||||
r'vlive\.tv\.video\.ajax\.request\.handler\.init\((.+)\)',
|
||||
r'\bvlive\.video\.init\(([^)]+)\)',
|
||||
webpage, 'video params')
|
||||
live_params, long_video_id, key = re.split(
|
||||
r'"\s*,\s*"', video_params)[1:4]
|
||||
status, _, _, live_params, long_video_id, key = re.split(
|
||||
r'"\s*,\s*"', video_params)[2:8]
|
||||
|
||||
if status == 'LIVE_ON_AIR' or status == 'BIG_EVENT_ON_AIR':
|
||||
live_params = self._parse_json('"%s"' % live_params, video_id)
|
||||
@ -61,8 +47,6 @@ class VLiveIE(InfoExtractor):
|
||||
elif status == 'VOD_ON_AIR' or status == 'BIG_EVENT_INTRO':
|
||||
if long_video_id and key:
|
||||
return self._replay(video_id, webpage, long_video_id, key)
|
||||
elif is_live:
|
||||
status = 'LIVE_END'
|
||||
else:
|
||||
status = 'COMING_SOON'
|
||||
|
||||
@ -70,7 +54,7 @@ class VLiveIE(InfoExtractor):
|
||||
raise ExtractorError('Uploading for replay. Please wait...',
|
||||
expected=True)
|
||||
elif status == 'COMING_SOON':
|
||||
raise ExtractorError('Coming soon! %s' % air_start, expected=True)
|
||||
raise ExtractorError('Coming soon!', expected=True)
|
||||
elif status == 'CANCELED':
|
||||
raise ExtractorError('We are sorry, '
|
||||
'but the live broadcast has been canceled.',
|
||||
|
||||
@ -1035,6 +1035,7 @@ def unified_strdate(date_str, day_first=True):
|
||||
format_expressions.extend([
|
||||
'%d-%m-%Y',
|
||||
'%d.%m.%Y',
|
||||
'%d.%m.%y',
|
||||
'%d/%m/%Y',
|
||||
'%d/%m/%y',
|
||||
'%d/%m/%Y %H:%M:%S',
|
||||
@ -1910,7 +1911,7 @@ def parse_age_limit(s):
|
||||
|
||||
def strip_jsonp(code):
|
||||
return re.sub(
|
||||
r'(?s)^[a-zA-Z0-9_.]+\s*\(\s*(.*)\);?\s*?(?://[^\n]*)*$', r'\1', code)
|
||||
r'(?s)^[a-zA-Z0-9_.$]+\s*\(\s*(.*)\);?\s*?(?://[^\n]*)*$', r'\1', code)
|
||||
|
||||
|
||||
def js_to_json(code):
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user