Merge pull request #2 from rg3/master

t
This commit is contained in:
世外桃源 2016-11-12 14:12:22 +08:00 committed by GitHub
commit d59467d33b
60 changed files with 1660 additions and 401 deletions

View File

@ -6,8 +6,8 @@
---
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.10.21.1*. 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 Issues with outdated version will be rejected.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 **2016.10.21.1**
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.11.08.1*. 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 Issues with outdated version will be rejected.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 **2016.11.08.1**
### 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 2016.10.21.1
[debug] youtube-dl version 2016.11.08.1
[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: {}

1
.gitignore vendored
View File

@ -30,6 +30,7 @@ updates_key.pem
*.m4v
*.mp3
*.3gp
*.wav
*.part
*.swp
test/testdata

View File

@ -188,3 +188,5 @@ Xie Yanbo
Philip Xu
John Hawkinson
Rich Leeper
Zhong Jianxin
Thor77

View File

@ -245,7 +245,7 @@ Say `meta` from the previous example has a `title` and you are about to extract
title = meta['title']
```
If `title` disappeares from `meta` in future due to some changes on the hoster's side the extraction would fail since `title` is mandatory. That's expected.
If `title` disappears from `meta` in future due to some changes on the hoster's side the extraction would fail since `title` is mandatory. That's expected.
Assume that you have some another source you can extract `title` from, for example `og:title` HTML meta of a `webpage`. In this case you can provide a fallback scenario:

View File

@ -1,11 +1,102 @@
version <unreleased>
Extractors
+ [audioboom] Recognize /posts/ URLs (#11149)
version 2016.11.08.1
Extractors
* [espn:article] Fix support for espn.com articles
* [franceculture] Fix extraction (#11140)
version 2016.11.08
Extractors
* [tmz:article] Fix extraction (#11052)
* [espn] Fix extraction (#11041)
* [mitele] Fix extraction after website redesign (#10824)
- [ard] Remove age restriction check (#11129)
* [generic] Improve support for pornhub.com embeds (#11100)
+ [generic] Add support for redtube.com embeds (#11099)
+ [generic] Add support for drtuber.com embeds (#11098)
+ [redtube] Add support for embed URLs
+ [drtuber] Add support for embed URLs
+ [yahoo] Improve content id extraction (#11088)
* [toutv] Relax URL regular expression (#11121)
version 2016.11.04
Core
* [extractor/common] Tolerate malformed RESOLUTION attribute in m3u8
manifests (#11113)
* [downloader/ism] Fix AVC Decoder Configuration Record
Extractors
+ [fox9] Add support for fox9.com (#11110)
+ [anvato] Extract more metadata and improve formats extraction
* [vodlocker] Improve removed videos detection (#11106)
+ [vzaar] Add support for vzaar.com (#11093)
+ [vice] Add support for uplynk preplay videos (#11101)
* [tubitv] Fix extraction (#11061)
+ [shahid] Add support for authentication (#11091)
+ [radiocanada] Add subtitles support (#11096)
+ [generic] Add support for ISM manifests
version 2016.11.02
Core
+ Add basic support for Smooth Streaming protocol (#8118, #10969)
* Improve MPD manifest base URL extraction (#10909, #11079)
* Fix --match-filter for int-like strings (#11082)
Extractors
+ [mva] Add support for ISM formats
+ [msn] Add support for ISM formats
+ [onet] Add support for ISM formats
+ [tvp] Add support for ISM formats
+ [nicknight] Add support for nicknight sites (#10769)
version 2016.10.30
Extractors
* [facebook] Improve 1080P video detection (#11073)
* [imgur] Recognize /r/ URLs (#11071)
* [beeg] Fix extraction (#11069)
* [openload] Fix extraction (#10408)
* [gvsearch] Modernize and fix search request (#11051)
* [adultswim] Fix extraction (#10979)
+ [nobelprize] Add support for nobelprize.org (#9999)
* [hornbunny] Fix extraction (#10981)
* [tvp] Improve video id extraction (#10585)
version 2016.10.26
Extractors
+ [rentv] Add support for ren.tv (#10620)
+ [ard] Detect unavailable videos (#11018)
* [vk] Fix extraction (#11022)
version 2016.10.25
Core
* Running youtube-dl in the background is fixed (#10996, #10706, #955)
Extractors
+ [jamendo] Add support for jamendo.com (#10132, #10736)
+ [pandatv] Add support for panda.tv (#10736)
+ [dotsub] Support Vimeo embed (#10964)
* [litv] Fix extraction
+ [vimeo] Delegate ondemand redirects to ondemand extractor (#10994)
* [vivo] Fix extraction (#11003)
+ [twitch:stream] Add support for rebroadcasts (#10995)
* [pluralsight] Fix subtitles conversion (#10990)
version 2016.10.21.1

View File

@ -1,7 +1,7 @@
all: youtube-dl README.md CONTRIBUTING.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish supportedsites
clean:
rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish youtube_dl/extractor/lazy_extractors.py *.dump *.part* *.info.json *.mp4 *.m4a *.flv *.mp3 *.avi *.mkv *.webm *.3gp *.jpg *.png CONTRIBUTING.md.tmp ISSUE_TEMPLATE.md.tmp youtube-dl youtube-dl.exe
rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish youtube_dl/extractor/lazy_extractors.py *.dump *.part* *.info.json *.mp4 *.m4a *.flv *.mp3 *.avi *.mkv *.webm *.3gp *.wav *.jpg *.png CONTRIBUTING.md.tmp ISSUE_TEMPLATE.md.tmp youtube-dl youtube-dl.exe
find . -name "*.pyc" -delete
find . -name "*.class" -delete

View File

@ -758,7 +758,7 @@ Once the video is fully downloaded, use any video player, such as [mpv](https://
### I extracted a video URL with `-g`, but it does not play on another machine / in my webbrowser.
It depends a lot on the service. In many cases, requests for the video (to download/play it) must come from the same IP address and with the same cookies. Use the `--cookies` option to write the required cookies into a file, and advise your downloader to read cookies from that file. Some sites also require a common user agent to be used, use `--dump-user-agent` to see the one in use by youtube-dl.
It depends a lot on the service. In many cases, requests for the video (to download/play it) must come from the same IP address and with the same cookies and/or HTTP headers. Use the `--cookies` option to write the required cookies into a file, and advise your downloader to read cookies from that file. Some sites also require a common user agent to be used, use `--dump-user-agent` to see the one in use by youtube-dl. You can also get necessary cookies and HTTP headers from JSON output obtained with `--dump-json`.
It may be beneficial to use IPv6; in some cases, the restrictions are only applied to IPv4. Some services (sometimes only for a subset of videos) do not restrict the video URL by IP address, cookie, or user-agent, but these are the exception rather than the rule.
@ -1083,7 +1083,7 @@ Say `meta` from the previous example has a `title` and you are about to extract
title = meta['title']
```
If `title` disappeares from `meta` in future due to some changes on the hoster's side the extraction would fail since `title` is mandatory. That's expected.
If `title` disappears from `meta` in future due to some changes on the hoster's side the extraction would fail since `title` is mandatory. That's expected.
Assume that you have some another source you can extract `title` from, for example `og:title` HTML meta of a `webpage`. In this case you can provide a fallback scenario:

View File

@ -225,6 +225,7 @@
- **EroProfile**
- **Escapist**
- **ESPN**
- **ESPNArticle**
- **EsriVideo**
- **Europa**
- **EveryonesMixtape**
@ -247,6 +248,7 @@
- **FootyRoom**
- **Formula1**
- **FOX**
- **FOX9**
- **Foxgay**
- **foxnews**: Fox News and Fox Business Video
- **foxnews:article**
@ -332,6 +334,8 @@
- **ivideon**: Ivideon TV
- **Iwara**
- **Izlesene**
- **Jamendo**
- **JamendoAlbum**
- **JeuxVideo**
- **Jove**
- **jpopsuki.tv**
@ -481,11 +485,13 @@
- **nhl.com:videocenter:category**: NHL videocenter category
- **nick.com**
- **nick.de**
- **nicknight**
- **niconico**: ニコニコ動画
- **NiconicoPlaylist**
- **Nintendo**
- **njoy**: N-JOY
- **njoy:embed**
- **NobelPrize**
- **Noco**
- **Normalboots**
- **NosVideo**
@ -527,6 +533,7 @@
- **orf:iptv**: iptv.ORF.at
- **orf:oe1**: Radio Österreich 1
- **orf:tvthek**: ORF TVthek
- **PandaTV**: 熊猫TV
- **pandora.tv**: 판도라TV
- **parliamentlive.tv**: UK parliament videos
- **Patreon**
@ -586,6 +593,8 @@
- **RDS**: RDS.ca
- **RedTube**
- **RegioTV**
- **RENTV**
- **RENTVArticle**
- **Restudy**
- **Reuters**
- **ReverbNation**
@ -641,7 +650,7 @@
- **ServingSys**
- **Sexu**
- **Shahid**
- **Shared**: shared.sx and vivo.sx
- **Shared**: shared.sx
- **ShareSix**
- **Sina**
- **SixPlay**
@ -848,6 +857,7 @@
- **Vimple**: Vimple - one-click video hosting
- **Vine**
- **vine:user**
- **Vivo**: vivo.sx
- **vk**: VK
- **vk:uservideos**: VK - User's Videos
- **vk:wallpost**
@ -862,6 +872,7 @@
- **vube**: Vube.com
- **VuClip**
- **VyboryMos**
- **Vzaar**
- **Walla**
- **washingtonpost**
- **washingtonpost:article**

View File

@ -605,6 +605,7 @@ class TestYoutubeDL(unittest.TestCase):
'extractor': 'TEST',
'duration': 30,
'filesize': 10 * 1024,
'playlist_id': '42',
}
second = {
'id': '2',
@ -614,6 +615,7 @@ class TestYoutubeDL(unittest.TestCase):
'duration': 10,
'description': 'foo',
'filesize': 5 * 1024,
'playlist_id': '43',
}
videos = [first, second]
@ -650,6 +652,10 @@ class TestYoutubeDL(unittest.TestCase):
res = get_videos(f)
self.assertEqual(res, ['1'])
f = match_filter_func('playlist_id = 42')
res = get_videos(f)
self.assertEqual(res, ['1'])
def test_playlist_items_selection(self):
entries = [{
'id': compat_str(i),

View File

@ -69,6 +69,7 @@ from youtube_dl.utils import (
uppercase_escape,
lowercase_escape,
url_basename,
base_url,
urlencode_postdata,
urshift,
update_url_query,
@ -437,6 +438,13 @@ class TestUtil(unittest.TestCase):
url_basename('http://media.w3.org/2010/05/sintel/trailer.mp4'),
'trailer.mp4')
def test_base_url(self):
self.assertEqual(base_url('http://foo.de/'), 'http://foo.de/')
self.assertEqual(base_url('http://foo.de/bar'), 'http://foo.de/')
self.assertEqual(base_url('http://foo.de/bar/'), 'http://foo.de/bar/')
self.assertEqual(base_url('http://foo.de/bar/baz'), 'http://foo.de/bar/')
self.assertEqual(base_url('http://foo.de/bar/baz?x=z/x/c'), 'http://foo.de/bar/')
def test_parse_age_limit(self):
self.assertEqual(parse_age_limit(None), None)
self.assertEqual(parse_age_limit(False), None)

View File

@ -1658,7 +1658,7 @@ class YoutubeDL(object):
video_ext, audio_ext = audio.get('ext'), video.get('ext')
if video_ext and audio_ext:
COMPATIBLE_EXTS = (
('mp3', 'mp4', 'm4a', 'm4p', 'm4b', 'm4r', 'm4v'),
('mp3', 'mp4', 'm4a', 'm4p', 'm4b', 'm4r', 'm4v', 'ismv', 'isma'),
('webm')
)
for exts in COMPATIBLE_EXTS:

View File

@ -7,6 +7,7 @@ from .http import HttpFD
from .rtmp import RtmpFD
from .dash import DashSegmentsFD
from .rtsp import RtspFD
from .ism import IsmFD
from .external import (
get_external_downloader,
FFmpegFD,
@ -24,6 +25,7 @@ PROTOCOL_MAP = {
'rtsp': RtspFD,
'f4m': F4mFD,
'http_dash_segments': DashSegmentsFD,
'ism': IsmFD,
}

View File

@ -0,0 +1,271 @@
from __future__ import unicode_literals
import os
import time
import struct
import binascii
import io
from .fragment import FragmentFD
from ..compat import compat_urllib_error
from ..utils import (
sanitize_open,
encodeFilename,
)
u8 = struct.Struct(b'>B')
u88 = struct.Struct(b'>Bx')
u16 = struct.Struct(b'>H')
u1616 = struct.Struct(b'>Hxx')
u32 = struct.Struct(b'>I')
u64 = struct.Struct(b'>Q')
s88 = struct.Struct(b'>bx')
s16 = struct.Struct(b'>h')
s1616 = struct.Struct(b'>hxx')
s32 = struct.Struct(b'>i')
unity_matrix = (s32.pack(0x10000) + s32.pack(0) * 3) * 2 + s32.pack(0x40000000)
TRACK_ENABLED = 0x1
TRACK_IN_MOVIE = 0x2
TRACK_IN_PREVIEW = 0x4
SELF_CONTAINED = 0x1
def box(box_type, payload):
return u32.pack(8 + len(payload)) + box_type + payload
def full_box(box_type, version, flags, payload):
return box(box_type, u8.pack(version) + u32.pack(flags)[1:] + payload)
def write_piff_header(stream, params):
track_id = params['track_id']
fourcc = params['fourcc']
duration = params['duration']
timescale = params.get('timescale', 10000000)
language = params.get('language', 'und')
height = params.get('height', 0)
width = params.get('width', 0)
is_audio = width == 0 and height == 0
creation_time = modification_time = int(time.time())
ftyp_payload = b'isml' # major brand
ftyp_payload += u32.pack(1) # minor version
ftyp_payload += b'piff' + b'iso2' # compatible brands
stream.write(box(b'ftyp', ftyp_payload)) # File Type Box
mvhd_payload = u64.pack(creation_time)
mvhd_payload += u64.pack(modification_time)
mvhd_payload += u32.pack(timescale)
mvhd_payload += u64.pack(duration)
mvhd_payload += s1616.pack(1) # rate
mvhd_payload += s88.pack(1) # volume
mvhd_payload += u16.pack(0) # reserved
mvhd_payload += u32.pack(0) * 2 # reserved
mvhd_payload += unity_matrix
mvhd_payload += u32.pack(0) * 6 # pre defined
mvhd_payload += u32.pack(0xffffffff) # next track id
moov_payload = full_box(b'mvhd', 1, 0, mvhd_payload) # Movie Header Box
tkhd_payload = u64.pack(creation_time)
tkhd_payload += u64.pack(modification_time)
tkhd_payload += u32.pack(track_id) # track id
tkhd_payload += u32.pack(0) # reserved
tkhd_payload += u64.pack(duration)
tkhd_payload += u32.pack(0) * 2 # reserved
tkhd_payload += s16.pack(0) # layer
tkhd_payload += s16.pack(0) # alternate group
tkhd_payload += s88.pack(1 if is_audio else 0) # volume
tkhd_payload += u16.pack(0) # reserved
tkhd_payload += unity_matrix
tkhd_payload += u1616.pack(width)
tkhd_payload += u1616.pack(height)
trak_payload = full_box(b'tkhd', 1, TRACK_ENABLED | TRACK_IN_MOVIE | TRACK_IN_PREVIEW, tkhd_payload) # Track Header Box
mdhd_payload = u64.pack(creation_time)
mdhd_payload += u64.pack(modification_time)
mdhd_payload += u32.pack(timescale)
mdhd_payload += u64.pack(duration)
mdhd_payload += u16.pack(((ord(language[0]) - 0x60) << 10) | ((ord(language[1]) - 0x60) << 5) | (ord(language[2]) - 0x60))
mdhd_payload += u16.pack(0) # pre defined
mdia_payload = full_box(b'mdhd', 1, 0, mdhd_payload) # Media Header Box
hdlr_payload = u32.pack(0) # pre defined
hdlr_payload += b'soun' if is_audio else b'vide' # handler type
hdlr_payload += u32.pack(0) * 3 # reserved
hdlr_payload += (b'Sound' if is_audio else b'Video') + b'Handler\0' # name
mdia_payload += full_box(b'hdlr', 0, 0, hdlr_payload) # Handler Reference Box
if is_audio:
smhd_payload = s88.pack(0) # balance
smhd_payload = u16.pack(0) # reserved
media_header_box = full_box(b'smhd', 0, 0, smhd_payload) # Sound Media Header
else:
vmhd_payload = u16.pack(0) # graphics mode
vmhd_payload += u16.pack(0) * 3 # opcolor
media_header_box = full_box(b'vmhd', 0, 1, vmhd_payload) # Video Media Header
minf_payload = media_header_box
dref_payload = u32.pack(1) # entry count
dref_payload += full_box(b'url ', 0, SELF_CONTAINED, b'') # Data Entry URL Box
dinf_payload = full_box(b'dref', 0, 0, dref_payload) # Data Reference Box
minf_payload += box(b'dinf', dinf_payload) # Data Information Box
stsd_payload = u32.pack(1) # entry count
sample_entry_payload = u8.pack(0) * 6 # reserved
sample_entry_payload += u16.pack(1) # data reference index
if is_audio:
sample_entry_payload += u32.pack(0) * 2 # reserved
sample_entry_payload += u16.pack(params.get('channels', 2))
sample_entry_payload += u16.pack(params.get('bits_per_sample', 16))
sample_entry_payload += u16.pack(0) # pre defined
sample_entry_payload += u16.pack(0) # reserved
sample_entry_payload += u1616.pack(params['sampling_rate'])
if fourcc == 'AACL':
sample_entry_box = box(b'mp4a', sample_entry_payload)
else:
sample_entry_payload = sample_entry_payload
sample_entry_payload += u16.pack(0) # pre defined
sample_entry_payload += u16.pack(0) # reserved
sample_entry_payload += u32.pack(0) * 3 # pre defined
sample_entry_payload += u16.pack(width)
sample_entry_payload += u16.pack(height)
sample_entry_payload += u1616.pack(0x48) # horiz resolution 72 dpi
sample_entry_payload += u1616.pack(0x48) # vert resolution 72 dpi
sample_entry_payload += u32.pack(0) # reserved
sample_entry_payload += u16.pack(1) # frame count
sample_entry_payload += u8.pack(0) * 32 # compressor name
sample_entry_payload += u16.pack(0x18) # depth
sample_entry_payload += s16.pack(-1) # pre defined
codec_private_data = binascii.unhexlify(params['codec_private_data'])
if fourcc in ('H264', 'AVC1'):
sps, pps = codec_private_data.split(u32.pack(1))[1:]
avcc_payload = u8.pack(1) # configuration version
avcc_payload += sps[1:4] # avc profile indication + profile compatibility + avc level indication
avcc_payload += u8.pack(0xfc | (params.get('nal_unit_length_field', 4) - 1)) # complete represenation (1) + reserved (11111) + length size minus one
avcc_payload += u8.pack(1) # reserved (0) + number of sps (0000001)
avcc_payload += u16.pack(len(sps))
avcc_payload += sps
avcc_payload += u8.pack(1) # number of pps
avcc_payload += u16.pack(len(pps))
avcc_payload += pps
sample_entry_payload += box(b'avcC', avcc_payload) # AVC Decoder Configuration Record
sample_entry_box = box(b'avc1', sample_entry_payload) # AVC Simple Entry
stsd_payload += sample_entry_box
stbl_payload = full_box(b'stsd', 0, 0, stsd_payload) # Sample Description Box
stts_payload = u32.pack(0) # entry count
stbl_payload += full_box(b'stts', 0, 0, stts_payload) # Decoding Time to Sample Box
stsc_payload = u32.pack(0) # entry count
stbl_payload += full_box(b'stsc', 0, 0, stsc_payload) # Sample To Chunk Box
stco_payload = u32.pack(0) # entry count
stbl_payload += full_box(b'stco', 0, 0, stco_payload) # Chunk Offset Box
minf_payload += box(b'stbl', stbl_payload) # Sample Table Box
mdia_payload += box(b'minf', minf_payload) # Media Information Box
trak_payload += box(b'mdia', mdia_payload) # Media Box
moov_payload += box(b'trak', trak_payload) # Track Box
mehd_payload = u64.pack(duration)
mvex_payload = full_box(b'mehd', 1, 0, mehd_payload) # Movie Extends Header Box
trex_payload = u32.pack(track_id) # track id
trex_payload += u32.pack(1) # default sample description index
trex_payload += u32.pack(0) # default sample duration
trex_payload += u32.pack(0) # default sample size
trex_payload += u32.pack(0) # default sample flags
mvex_payload += full_box(b'trex', 0, 0, trex_payload) # Track Extends Box
moov_payload += box(b'mvex', mvex_payload) # Movie Extends Box
stream.write(box(b'moov', moov_payload)) # Movie Box
def extract_box_data(data, box_sequence):
data_reader = io.BytesIO(data)
while True:
box_size = u32.unpack(data_reader.read(4))[0]
box_type = data_reader.read(4)
if box_type == box_sequence[0]:
box_data = data_reader.read(box_size - 8)
if len(box_sequence) == 1:
return box_data
return extract_box_data(box_data, box_sequence[1:])
data_reader.seek(box_size - 8, 1)
class IsmFD(FragmentFD):
"""
Download segments in a ISM manifest
"""
FD_NAME = 'ism'
def real_download(self, filename, info_dict):
segments = info_dict['fragments'][:1] if self.params.get(
'test', False) else info_dict['fragments']
ctx = {
'filename': filename,
'total_frags': len(segments),
}
self._prepare_and_start_frag_download(ctx)
segments_filenames = []
fragment_retries = self.params.get('fragment_retries', 0)
skip_unavailable_fragments = self.params.get('skip_unavailable_fragments', True)
track_written = False
for i, segment in enumerate(segments):
segment_url = segment['url']
segment_name = 'Frag%d' % i
target_filename = '%s-%s' % (ctx['tmpfilename'], segment_name)
count = 0
while count <= fragment_retries:
try:
success = ctx['dl'].download(target_filename, {'url': segment_url})
if not success:
return False
down, target_sanitized = sanitize_open(target_filename, 'rb')
down_data = down.read()
if not track_written:
tfhd_data = extract_box_data(down_data, [b'moof', b'traf', b'tfhd'])
info_dict['_download_params']['track_id'] = u32.unpack(tfhd_data[4:8])[0]
write_piff_header(ctx['dest_stream'], info_dict['_download_params'])
track_written = True
ctx['dest_stream'].write(down_data)
down.close()
segments_filenames.append(target_sanitized)
break
except compat_urllib_error.HTTPError as err:
count += 1
if count <= fragment_retries:
self.report_retry_fragment(err, segment_name, count, fragment_retries)
if count > fragment_retries:
if skip_unavailable_fragments:
self.report_skip_fragment(segment_name)
continue
self.report_error('giving up after %s fragment retries' % fragment_retries)
return False
self._finish_frag_download(ctx)
for segment_file in segments_filenames:
os.remove(encodeFilename(segment_file))
return True

View File

@ -96,6 +96,27 @@ class AdultSwimIE(TurnerBaseIE):
'skip_download': True,
},
'expected_warnings': ['Unable to download f4m manifest'],
}, {
'url': 'http://www.adultswim.com/videos/toonami/friday-october-14th-2016/',
'info_dict': {
'id': 'eYiLsKVgQ6qTC6agD67Sig',
'title': 'Toonami - Friday, October 14th, 2016',
'description': 'md5:99892c96ffc85e159a428de85c30acde',
},
'playlist': [{
'md5': '',
'info_dict': {
'id': 'eYiLsKVgQ6qTC6agD67Sig',
'ext': 'mp4',
'title': 'Toonami - Friday, October 14th, 2016',
'description': 'md5:99892c96ffc85e159a428de85c30acde',
},
}],
'params': {
# m3u8 download
'skip_download': True,
},
'expected_warnings': ['Unable to download f4m manifest'],
}]
@staticmethod
@ -163,6 +184,8 @@ class AdultSwimIE(TurnerBaseIE):
segment_ids = [clip['videoPlaybackID'] for clip in video_info['clips']]
elif video_info.get('videoPlaybackID'):
segment_ids = [video_info['videoPlaybackID']]
elif video_info.get('id'):
segment_ids = [video_info['id']]
else:
if video_info.get('auth') is True:
raise ExtractorError(

View File

@ -157,22 +157,16 @@ class AnvatoIE(InfoExtractor):
video_data_url, video_id, transform_source=strip_jsonp,
data=json.dumps(payload).encode('utf-8'))
def _extract_anvato_videos(self, webpage, video_id):
anvplayer_data = self._parse_json(self._html_search_regex(
r'<script[^>]+data-anvp=\'([^\']+)\'', webpage,
'Anvato player data'), video_id)
video_id = anvplayer_data['video']
access_key = anvplayer_data['accessKey']
def _get_anvato_videos(self, access_key, video_id):
video_data = self._get_video_json(access_key, video_id)
formats = []
for published_url in video_data['published_urls']:
video_url = published_url['embed_url']
media_format = published_url.get('format')
ext = determine_ext(video_url)
if ext == 'smil':
if ext == 'smil' or media_format == 'smil':
formats.extend(self._extract_smil_formats(video_url, video_id))
continue
@ -183,7 +177,7 @@ class AnvatoIE(InfoExtractor):
'tbr': tbr if tbr != 0 else None,
}
if ext == 'm3u8':
if ext == 'm3u8' or media_format in ('m3u8', 'm3u8-variant'):
# Not using _extract_m3u8_formats here as individual media
# playlists are also included in published_urls.
if tbr is None:
@ -194,7 +188,7 @@ class AnvatoIE(InfoExtractor):
'format_id': '-'.join(filter(None, ['hls', compat_str(tbr)])),
'ext': 'mp4',
})
elif ext == 'mp3':
elif ext == 'mp3' or media_format == 'mp3':
a_format['vcodec'] = 'none'
else:
a_format.update({
@ -218,7 +212,19 @@ class AnvatoIE(InfoExtractor):
'formats': formats,
'title': video_data.get('def_title'),
'description': video_data.get('def_description'),
'tags': video_data.get('def_tags', '').split(','),
'categories': video_data.get('categories'),
'thumbnail': video_data.get('thumbnail'),
'timestamp': int_or_none(video_data.get(
'ts_published') or video_data.get('ts_added')),
'uploader': video_data.get('mcp_id'),
'duration': int_or_none(video_data.get('duration')),
'subtitles': subtitles,
}
def _extract_anvato_videos(self, webpage, video_id):
anvplayer_data = self._parse_json(self._html_search_regex(
r'<script[^>]+data-anvp=\'([^\']+)\'', webpage,
'Anvato player data'), video_id)
return self._get_anvato_videos(
anvplayer_data['accessKey'], anvplayer_data['video'])

View File

@ -174,11 +174,15 @@ class ARDMediathekIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
if '>Der gewünschte Beitrag ist nicht mehr verfügbar.<' in webpage:
raise ExtractorError('Video %s is no longer available' % video_id, expected=True)
ERRORS = (
('>Leider liegt eine Störung vor.', 'Video %s is unavailable'),
('>Der gewünschte Beitrag ist nicht mehr verfügbar.<',
'Video %s is no longer available'),
)
if 'Diese Sendung ist für Jugendliche unter 12 Jahren nicht geeignet. Der Clip ist deshalb nur von 20 bis 6 Uhr verfügbar.' in webpage:
raise ExtractorError('This program is only suitable for those aged 12 and older. Video %s is therefore only available between 20 pm and 6 am.' % video_id, expected=True)
for pattern, message in ERRORS:
if pattern in webpage:
raise ExtractorError(message % video_id, expected=True)
if re.search(r'[\?&]rss($|[=&])', url):
doc = compat_etree_fromstring(webpage.encode('utf-8'))

View File

@ -6,8 +6,8 @@ from ..utils import float_or_none
class AudioBoomIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?audioboom\.com/boos/(?P<id>[0-9]+)'
_TEST = {
_VALID_URL = r'https?://(?:www\.)?audioboom\.com/(?:boos|posts)/(?P<id>[0-9]+)'
_TESTS = [{
'url': 'https://audioboom.com/boos/4279833-3-09-2016-czaban-hour-3?t=0',
'md5': '63a8d73a055c6ed0f1e51921a10a5a76',
'info_dict': {
@ -19,7 +19,10 @@ class AudioBoomIE(InfoExtractor):
'uploader': 'Steve Czaban',
'uploader_url': 're:https?://(?:www\.)?audioboom\.com/channel/steveczabanyahoosportsradio',
}
}
}, {
'url': 'https://audioboom.com/posts/4279833-3-09-2016-czaban-hour-3?t=0',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)

View File

@ -46,19 +46,19 @@ class BeegIE(InfoExtractor):
self._proto_relative_url(cpl_url), video_id,
'Downloading cpl JS', fatal=False)
if cpl:
beeg_version = self._search_regex(
r'beeg_version\s*=\s*(\d+)', cpl,
'beeg version', default=None) or self._search_regex(
beeg_version = int_or_none(self._search_regex(
r'beeg_version\s*=\s*([^\b]+)', cpl,
'beeg version', default=None)) or self._search_regex(
r'/(\d+)\.js', cpl_url, 'beeg version', default=None)
beeg_salt = self._search_regex(
r'beeg_salt\s*=\s*(["\'])(?P<beeg_salt>.+?)\1', cpl, 'beeg beeg_salt',
r'beeg_salt\s*=\s*(["\'])(?P<beeg_salt>.+?)\1', cpl, 'beeg salt',
default=None, group='beeg_salt')
beeg_version = beeg_version or '1750'
beeg_salt = beeg_salt or 'MIDtGaw96f0N1kMMAM1DE46EC9pmFr'
beeg_version = beeg_version or '2000'
beeg_salt = beeg_salt or 'pmweAkq8lAYKdfWcFCUj0yoVgoPlinamH5UE1CB3H'
video = self._download_json(
'http://api.beeg.com/api/v6/%s/video/%s' % (beeg_version, video_id),
'https://api.beeg.com/api/v6/%s/video/%s' % (beeg_version, video_id),
video_id)
def split(o, e):

View File

@ -22,6 +22,7 @@ class CBSLocalIE(AnvatoIE):
'thumbnail': 're:^https?://.*',
'timestamp': 1463440500,
'upload_date': '20160516',
'uploader': 'CBS',
'subtitles': {
'en': 'mincount:5',
},
@ -35,6 +36,7 @@ class CBSLocalIE(AnvatoIE):
'Syndication\\Curb.tv',
'Content\\News'
],
'tags': ['CBS 2 News Evening'],
},
}, {
# SendtoNews embed

View File

@ -30,6 +30,7 @@ from ..downloader.f4m import remove_encrypted_media
from ..utils import (
NO_DEFAULT,
age_restricted,
base_url,
bug_reports_message,
clean_html,
compiled_regex_type,
@ -1279,9 +1280,10 @@ class InfoExtractor(object):
}
resolution = last_info.get('RESOLUTION')
if resolution:
width_str, height_str = resolution.split('x')
f['width'] = int(width_str)
f['height'] = int(height_str)
mobj = re.search(r'(?P<width>\d+)[xX](?P<height>\d+)', resolution)
if mobj:
f['width'] = int(mobj.group('width'))
f['height'] = int(mobj.group('height'))
# Unified Streaming Platform
mobj = re.search(
r'audio.*?(?:%3D|=)(\d+)(?:-video.*?(?:%3D|=)(\d+))?', f['url'])
@ -1539,7 +1541,7 @@ class InfoExtractor(object):
if res is False:
return []
mpd, urlh = res
mpd_base_url = re.match(r'https?://.+/', urlh.geturl()).group()
mpd_base_url = base_url(urlh.geturl())
return self._parse_mpd_formats(
compat_etree_fromstring(mpd.encode('utf-8')), mpd_id, mpd_base_url,
@ -1780,6 +1782,105 @@ class InfoExtractor(object):
self.report_warning('Unknown MIME type %s in DASH manifest' % mime_type)
return formats
def _extract_ism_formats(self, ism_url, video_id, ism_id=None, note=None, errnote=None, fatal=True):
res = self._download_webpage_handle(
ism_url, video_id,
note=note or 'Downloading ISM manifest',
errnote=errnote or 'Failed to download ISM manifest',
fatal=fatal)
if res is False:
return []
ism, urlh = res
return self._parse_ism_formats(
compat_etree_fromstring(ism.encode('utf-8')), urlh.geturl(), ism_id)
def _parse_ism_formats(self, ism_doc, ism_url, ism_id=None):
if ism_doc.get('IsLive') == 'TRUE' or ism_doc.find('Protection') is not None:
return []
duration = int(ism_doc.attrib['Duration'])
timescale = int_or_none(ism_doc.get('TimeScale')) or 10000000
formats = []
for stream in ism_doc.findall('StreamIndex'):
stream_type = stream.get('Type')
if stream_type not in ('video', 'audio'):
continue
url_pattern = stream.attrib['Url']
stream_timescale = int_or_none(stream.get('TimeScale')) or timescale
stream_name = stream.get('Name')
for track in stream.findall('QualityLevel'):
fourcc = track.get('FourCC')
# TODO: add support for WVC1 and WMAP
if fourcc not in ('H264', 'AVC1', 'AACL'):
self.report_warning('%s is not a supported codec' % fourcc)
continue
tbr = int(track.attrib['Bitrate']) // 1000
width = int_or_none(track.get('MaxWidth'))
height = int_or_none(track.get('MaxHeight'))
sampling_rate = int_or_none(track.get('SamplingRate'))
track_url_pattern = re.sub(r'{[Bb]itrate}', track.attrib['Bitrate'], url_pattern)
track_url_pattern = compat_urlparse.urljoin(ism_url, track_url_pattern)
fragments = []
fragment_ctx = {
'time': 0,
}
stream_fragments = stream.findall('c')
for stream_fragment_index, stream_fragment in enumerate(stream_fragments):
fragment_ctx['time'] = int_or_none(stream_fragment.get('t')) or fragment_ctx['time']
fragment_repeat = int_or_none(stream_fragment.get('r')) or 1
fragment_ctx['duration'] = int_or_none(stream_fragment.get('d'))
if not fragment_ctx['duration']:
try:
next_fragment_time = int(stream_fragment[stream_fragment_index + 1].attrib['t'])
except IndexError:
next_fragment_time = duration
fragment_ctx['duration'] = (next_fragment_time - fragment_ctx['time']) / fragment_repeat
for _ in range(fragment_repeat):
fragments.append({
'url': re.sub(r'{start[ _]time}', compat_str(fragment_ctx['time']), track_url_pattern),
'duration': fragment_ctx['duration'] / stream_timescale,
})
fragment_ctx['time'] += fragment_ctx['duration']
format_id = []
if ism_id:
format_id.append(ism_id)
if stream_name:
format_id.append(stream_name)
format_id.append(compat_str(tbr))
formats.append({
'format_id': '-'.join(format_id),
'url': ism_url,
'manifest_url': ism_url,
'ext': 'ismv' if stream_type == 'video' else 'isma',
'width': width,
'height': height,
'tbr': tbr,
'asr': sampling_rate,
'vcodec': 'none' if stream_type == 'audio' else fourcc,
'acodec': 'none' if stream_type == 'video' else fourcc,
'protocol': 'ism',
'fragments': fragments,
'_download_params': {
'duration': duration,
'timescale': stream_timescale,
'width': width or 0,
'height': height or 0,
'fourcc': fourcc,
'codec_private_data': track.get('CodecPrivateData'),
'sampling_rate': sampling_rate,
'channels': int_or_none(track.get('Channels', 2)),
'bits_per_sample': int_or_none(track.get('BitsPerSample', 16)),
'nal_unit_length_field': int_or_none(track.get('NALUnitLengthField', 4)),
},
})
return formats
def _parse_html5_media_entries(self, base_url, webpage, video_id, m3u8_id=None, m3u8_entry_protocol='m3u8'):
def absolute_url(video_url):
return compat_urlparse.urljoin(base_url, video_url)

View File

@ -10,8 +10,8 @@ from ..utils import (
class DrTuberIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?drtuber\.com/video/(?P<id>\d+)/(?P<display_id>[\w-]+)'
_TEST = {
_VALID_URL = r'https?://(?:www\.)?drtuber\.com/(?:video|embed)/(?P<id>\d+)(?:/(?P<display_id>[\w-]+))?'
_TESTS = [{
'url': 'http://www.drtuber.com/video/1740434/hot-perky-blonde-naked-golf',
'md5': '93e680cf2536ad0dfb7e74d94a89facd',
'info_dict': {
@ -25,20 +25,30 @@ class DrTuberIE(InfoExtractor):
'thumbnail': 're:https?://.*\.jpg$',
'age_limit': 18,
}
}
}, {
'url': 'http://www.drtuber.com/embed/489939',
'only_matching': True,
}]
@staticmethod
def _extract_urls(webpage):
return re.findall(
r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?drtuber\.com/embed/\d+)',
webpage)
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
display_id = mobj.group('display_id')
display_id = mobj.group('display_id') or video_id
webpage = self._download_webpage(url, display_id)
webpage = self._download_webpage(
'http://www.drtuber.com/video/%s' % video_id, display_id)
video_url = self._html_search_regex(
r'<source src="([^"]+)"', webpage, 'video URL')
title = self._html_search_regex(
(r'class="title_watch"[^>]*><p>([^<]+)<',
(r'class="title_watch"[^>]*><(?:p|h\d+)[^>]*>([^<]+)<',
r'<p[^>]+class="title_substrate">([^<]+)</p>',
r'<title>([^<]+) - \d+'),
webpage, 'title')

View File

@ -4,11 +4,13 @@ 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 (
ExtractorError,
int_or_none,
url_basename,
)
@ -77,7 +79,7 @@ class EaglePlatformIE(InfoExtractor):
if status != 200:
raise ExtractorError(' '.join(response['errors']), expected=True)
def _download_json(self, url_or_request, video_id, note='Downloading JSON metadata'):
def _download_json(self, url_or_request, video_id, note='Downloading JSON metadata', *args, **kwargs):
try:
response = super(EaglePlatformIE, self)._download_json(url_or_request, video_id, note)
except ExtractorError as ee:
@ -116,29 +118,38 @@ class EaglePlatformIE(InfoExtractor):
m3u8_url = self._get_video_url(secure_m3u8, video_id, 'Downloading m3u8 JSON')
m3u8_formats = self._extract_m3u8_formats(
m3u8_url, video_id,
'mp4', entry_protocol='m3u8_native', m3u8_id='hls')
m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False)
formats.extend(m3u8_formats)
mp4_url = self._get_video_url(
m3u8_formats_dict = {}
for f in m3u8_formats:
if f.get('height') is not None:
m3u8_formats_dict[f['height']] = f
mp4_data = self._download_json(
# Secure mp4 URL is constructed according to Player.prototype.mp4 from
# http://lentaru.media.eagleplatform.com/player/player.js
re.sub(r'm3u8|hlsvod|hls|f4m', 'mp4', secure_m3u8),
video_id, 'Downloading mp4 JSON')
mp4_url_basename = url_basename(mp4_url)
for m3u8_format in m3u8_formats:
mobj = re.search('/([^/]+)/index\.m3u8', m3u8_format['url'])
if mobj:
http_format = m3u8_format.copy()
video_url = mp4_url.replace(mp4_url_basename, mobj.group(1))
if not self._is_valid_url(video_url, video_id):
re.sub(r'm3u8|hlsvod|hls|f4m', 'mp4s', secure_m3u8),
video_id, 'Downloading mp4 JSON', fatal=False)
if mp4_data:
for format_id, format_url in mp4_data.get('data', {}).items():
if not isinstance(format_url, compat_str):
continue
http_format.update({
'url': video_url,
'format_id': m3u8_format['format_id'].replace('hls', 'http'),
'protocol': 'http',
})
formats.append(http_format)
height = int_or_none(format_id)
if height is not None and m3u8_formats_dict.get(height):
f = m3u8_formats_dict[height].copy()
f.update({
'format_id': f['format_id'].replace('hls', 'http'),
'protocol': 'http',
})
else:
f = {
'format_id': 'http-%s' % format_id,
'height': int_or_none(format_id),
}
f['url'] = format_url
formats.append(f)
self._sort_formats(formats)

View File

@ -1,38 +1,117 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import remove_end
from ..compat import compat_str
from ..utils import (
determine_ext,
int_or_none,
unified_timestamp,
)
class ESPNIE(InfoExtractor):
_VALID_URL = r'https?://(?:espn\.go|(?:www\.)?espn)\.com/(?:[^/]+/)*(?P<id>[^/]+)'
_VALID_URL = r'https?://(?:espn\.go|(?:www\.)?espn)\.com/video/clip(?:\?.*?\bid=|/_/id/)(?P<id>\d+)'
_TESTS = [{
'url': 'http://espn.go.com/video/clip?id=10365079',
'md5': '60e5d097a523e767d06479335d1bdc58',
'info_dict': {
'id': 'FkYWtmazr6Ed8xmvILvKLWjd4QvYZpzG',
'id': '10365079',
'ext': 'mp4',
'title': '30 for 30 Shorts: Judging Jewell',
'description': None,
'description': 'md5:39370c2e016cb4ecf498ffe75bef7f0f',
'timestamp': 1390936111,
'upload_date': '20140128',
},
'params': {
'skip_download': True,
},
'add_ie': ['OoyalaExternal'],
}, {
# intl video, from http://www.espnfc.us/video/mls-highlights/150/video/2743663/must-see-moments-best-of-the-mls-season
'url': 'http://espn.go.com/video/clip?id=2743663',
'md5': 'f4ac89b59afc7e2d7dbb049523df6768',
'info_dict': {
'id': '50NDFkeTqRHB0nXBOK-RGdSG5YQPuxHg',
'id': '2743663',
'ext': 'mp4',
'title': 'Must-See Moments: Best of the MLS season',
'description': 'md5:4c2d7232beaea572632bec41004f0aeb',
'timestamp': 1449446454,
'upload_date': '20151207',
},
'params': {
'skip_download': True,
},
'add_ie': ['OoyalaExternal'],
'expected_warnings': ['Unable to download f4m manifest'],
}, {
'url': 'http://www.espn.com/video/clip?id=10365079',
'only_matching': True,
}, {
'url': 'http://www.espn.com/video/clip/_/id/17989860',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
clip = self._download_json(
'http://api-app.espn.com/v1/video/clips/%s' % video_id,
video_id)['videos'][0]
title = clip['headline']
format_urls = set()
formats = []
def traverse_source(source, base_source_id=None):
for source_id, source in source.items():
if isinstance(source, compat_str):
extract_source(source, base_source_id)
elif isinstance(source, dict):
traverse_source(
source,
'%s-%s' % (base_source_id, source_id)
if base_source_id else source_id)
def extract_source(source_url, source_id=None):
if source_url in format_urls:
return
format_urls.add(source_url)
ext = determine_ext(source_url)
if ext == 'smil':
formats.extend(self._extract_smil_formats(
source_url, video_id, fatal=False))
elif ext == 'f4m':
formats.extend(self._extract_f4m_formats(
source_url, video_id, f4m_id=source_id, fatal=False))
elif ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
source_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id=source_id, fatal=False))
else:
formats.append({
'url': source_url,
'format_id': source_id,
})
traverse_source(clip['links']['source'])
self._sort_formats(formats)
description = clip.get('caption') or clip.get('description')
thumbnail = clip.get('thumbnail')
duration = int_or_none(clip.get('duration'))
timestamp = unified_timestamp(clip.get('originalPublishDate'))
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'timestamp': timestamp,
'duration': duration,
'formats': formats,
}
class ESPNArticleIE(InfoExtractor):
_VALID_URL = r'https?://(?:espn\.go|(?:www\.)?espn)\.com/(?:[^/]+/)*(?P<id>[^/]+)'
_TESTS = [{
'url': 'https://espn.go.com/video/iframe/twitter/?cms=espn&id=10365079',
'only_matching': True,
}, {
@ -47,11 +126,12 @@ class ESPNIE(InfoExtractor):
}, {
'url': 'http://espn.go.com/nba/playoffs/2015/story/_/id/12887571/john-wall-washington-wizards-no-swelling-left-hand-wrist-game-5-return',
'only_matching': True,
}, {
'url': 'http://www.espn.com/video/clip?id=10365079',
'only_matching': True,
}]
@classmethod
def suitable(cls, url):
return False if ESPNIE.suitable(url) else super(ESPNArticleIE, cls).suitable(url)
def _real_extract(self, url):
video_id = self._match_id(url)
@ -61,23 +141,5 @@ class ESPNIE(InfoExtractor):
r'class=(["\']).*?video-play-button.*?\1[^>]+data-id=["\'](?P<id>\d+)',
webpage, 'video id', group='id')
cms = 'espn'
if 'data-source="intl"' in webpage:
cms = 'intl'
player_url = 'https://espn.go.com/video/iframe/twitter/?id=%s&cms=%s' % (video_id, cms)
player = self._download_webpage(
player_url, video_id)
pcode = self._search_regex(
r'["\']pcode=([^"\']+)["\']', player, 'pcode')
title = remove_end(
self._og_search_title(webpage),
'- ESPN Video').strip()
return {
'_type': 'url_transparent',
'url': 'ooyalaexternal:%s:%s:%s' % (cms, video_id, pcode),
'ie_key': 'OoyalaExternal',
'title': title,
}
return self.url_result(
'http://espn.go.com/video/clip?id=%s' % video_id, ESPNIE.ie_key())

View File

@ -267,7 +267,10 @@ from .engadget import EngadgetIE
from .eporner import EpornerIE
from .eroprofile import EroProfileIE
from .escapist import EscapistIE
from .espn import ESPNIE
from .espn import (
ESPNIE,
ESPNArticleIE,
)
from .esri import EsriVideoIE
from .europa import EuropaIE
from .everyonesmixtape import EveryonesMixtapeIE
@ -296,6 +299,7 @@ from .footyroom import FootyRoomIE
from .formula1 import Formula1IE
from .fourtube import FourTubeIE
from .fox import FOXIE
from .fox9 import FOX9IE
from .foxgay import FoxgayIE
from .foxnews import (
FoxNewsIE,
@ -408,6 +412,10 @@ from .ivi import (
from .ivideon import IvideonIE
from .iwara import IwaraIE
from .izlesene import IzleseneIE
from .jamendo import (
JamendoIE,
JamendoAlbumIE,
)
from .jeuxvideo import JeuxVideoIE
from .jove import JoveIE
from .jwplatform import JWPlatformIE
@ -592,6 +600,7 @@ from .nhl import (
from .nick import (
NickIE,
NickDeIE,
NickNightIE,
)
from .niconico import NiconicoIE, NiconicoPlaylistIE
from .ninecninemedia import (
@ -601,6 +610,7 @@ from .ninecninemedia import (
from .ninegag import NineGagIE
from .ninenow import NineNowIE
from .nintendo import NintendoIE
from .nobelprize import NobelPrizeIE
from .noco import NocoIE
from .normalboots import NormalbootsIE
from .nosvideo import NosVideoIE
@ -667,6 +677,7 @@ from .orf import (
ORFFM4IE,
ORFIPTVIE,
)
from .pandatv import PandaTVIE
from .pandoratv import PandoraTVIE
from .parliamentliveuk import ParliamentLiveUKIE
from .patreon import PatreonIE
@ -740,6 +751,10 @@ from .rbmaradio import RBMARadioIE
from .rds import RDSIE
from .redtube import RedTubeIE
from .regiotv import RegioTVIE
from .rentv import (
RENTVIE,
RENTVArticleIE,
)
from .restudy import RestudyIE
from .reuters import ReutersIE
from .reverbnation import ReverbNationIE
@ -1090,6 +1105,7 @@ from .vrt import VRTIE
from .vube import VubeIE
from .vuclip import VuClipIE
from .vyborymos import VyboryMosIE
from .vzaar import VzaarIE
from .walla import WallaIE
from .washingtonpost import (
WashingtonPostIE,

View File

@ -1,6 +1,5 @@
from __future__ import unicode_literals
import json
import re
import socket
@ -100,7 +99,8 @@ class FacebookIE(InfoExtractor):
'ext': 'mp4',
'title': '"What are you doing running in the snow?"',
'uploader': 'FailArmy',
}
},
'skip': 'Video gone',
}, {
'url': 'https://m.facebook.com/story.php?story_fbid=1035862816472149&id=116132035111903',
'md5': '1deb90b6ac27f7efcf6d747c8a27f5e3',
@ -110,6 +110,7 @@ class FacebookIE(InfoExtractor):
'title': 'What the Flock Is Going On In New Zealand Credit: ViralHog',
'uploader': 'S. Saint',
},
'skip': 'Video gone',
}, {
'note': 'swf params escaped',
'url': 'https://www.facebook.com/barackobama/posts/10153664894881749',
@ -119,6 +120,18 @@ class FacebookIE(InfoExtractor):
'ext': 'mp4',
'title': 'Facebook video #10153664894881749',
},
}, {
# have 1080P, but only up to 720p in swf params
'url': 'https://www.facebook.com/cnn/videos/10155529876156509/',
'md5': '0d9813160b146b3bc8744e006027fcc6',
'info_dict': {
'id': '10155529876156509',
'ext': 'mp4',
'title': 'Holocaust survivor becomes US citizen',
'timestamp': 1477818095,
'upload_date': '20161030',
'uploader': 'CNN',
},
}, {
'url': 'https://www.facebook.com/video.php?v=10204634152394104',
'only_matching': True,
@ -227,43 +240,13 @@ class FacebookIE(InfoExtractor):
video_data = None
BEFORE = '{swf.addParam(param[0], param[1]);});'
AFTER = '.forEach(function(variable) {swf.addVariable(variable[0], variable[1]);});'
PATTERN = re.escape(BEFORE) + '(?:\n|\\\\n)(.*?)' + re.escape(AFTER)
for m in re.findall(PATTERN, webpage):
swf_params = m.replace('\\\\', '\\').replace('\\"', '"')
data = dict(json.loads(swf_params))
params_raw = compat_urllib_parse_unquote(data['params'])
video_data_candidate = json.loads(params_raw)['video_data']
for _, f in video_data_candidate.items():
if not f:
continue
if isinstance(f, dict):
f = [f]
if not isinstance(f, list):
continue
if f[0].get('video_id') == video_id:
video_data = video_data_candidate
break
if video_data:
server_js_data = self._parse_json(self._search_regex(
r'handleServerJS\(({.+})(?:\);|,")', webpage, 'server js data', default='{}'), video_id)
for item in server_js_data.get('instances', []):
if item[1][0] == 'VideoConfig':
video_data = item[2][0]['videoData']
break
def video_data_list2dict(video_data):
ret = {}
for item in video_data:
format_id = item['stream_type']
ret.setdefault(format_id, []).append(item)
return ret
if not video_data:
server_js_data = self._parse_json(self._search_regex(
r'handleServerJS\(({.+})(?:\);|,")', webpage, 'server js data', default='{}'), video_id)
for item in server_js_data.get('instances', []):
if item[1][0] == 'VideoConfig':
video_data = video_data_list2dict(item[2][0]['videoData'])
break
if not video_data:
if not fatal_if_no_video:
return webpage, False
@ -276,7 +259,8 @@ class FacebookIE(InfoExtractor):
raise ExtractorError('Cannot parse data')
formats = []
for format_id, f in video_data.items():
for f in video_data:
format_id = f['stream_type']
if f and isinstance(f, dict):
f = [f]
if not f or not isinstance(f, list):

View File

@ -0,0 +1,43 @@
# coding: utf-8
from __future__ import unicode_literals
from .anvato import AnvatoIE
from ..utils import js_to_json
class FOX9IE(AnvatoIE):
_VALID_URL = r'https?://(?:www\.)?fox9\.com/(?:[^/]+/)+(?P<id>\d+)-story'
_TESTS = [{
'url': 'http://www.fox9.com/news/215123287-story',
'md5': 'd6e1b2572c3bab8a849c9103615dd243',
'info_dict': {
'id': '314473',
'ext': 'mp4',
'title': 'Bear climbs tree in downtown Duluth',
'description': 'md5:6a36bfb5073a411758a752455408ac90',
'duration': 51,
'timestamp': 1478123580,
'upload_date': '20161102',
'uploader': 'EPFOX',
'categories': ['News', 'Sports'],
'tags': ['news', 'video'],
},
}, {
'url': 'http://www.fox9.com/news/investigators/214070684-story',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_id = self._parse_json(
self._search_regex(
r'AnvatoPlaylist\s*\(\s*(\[.+?\])\s*\)\s*;',
webpage, 'anvato playlist'),
video_id, transform_source=js_to_json)[0]['video']
return self._get_anvato_videos(
'anvato_epfox_app_web_prod_b3373168e12f423f41504f207000188daf88251b',
video_id)

View File

@ -29,7 +29,7 @@ class FranceCultureIE(InfoExtractor):
webpage = self._download_webpage(url, display_id)
video_url = self._search_regex(
r'(?s)<div[^>]+class="[^"]*?title-zone-diffusion[^"]*?"[^>]*>.*?<a[^>]+href="([^"]+)"',
r'(?s)<div[^>]+class="[^"]*?title-zone-diffusion[^"]*?"[^>]*>.*?<button[^>]+data-asset-source="([^"]+)"',
webpage, 'video path')
title = self._og_search_title(webpage)
@ -38,7 +38,7 @@ class FranceCultureIE(InfoExtractor):
'(?s)<div[^>]+class="date"[^>]*>.*?<span[^>]+class="inner"[^>]*>([^<]+)<',
webpage, 'upload date', fatal=False))
thumbnail = self._search_regex(
r'(?s)<figure[^>]+itemtype="https://schema.org/ImageObject"[^>]*>.*?<img[^>]+data-pagespeed-(?:lazy|high-res)-src="([^"]+)"',
r'(?s)<figure[^>]+itemtype="https://schema.org/ImageObject"[^>]*>.*?<img[^>]+data-dejavu-src="([^"]+)"',
webpage, 'thumbnail', fatal=False)
uploader = self._html_search_regex(
r'(?s)<div id="emission".*?<span class="author">(.*?)</span>',

View File

@ -47,6 +47,8 @@ from .svt import SVTIE
from .pornhub import PornHubIE
from .xhamster import XHamsterEmbedIE
from .tnaflix import TNAFlixNetworkEmbedIE
from .drtuber import DrTuberIE
from .redtube import RedTubeIE
from .vimeo import VimeoIE
from .dailymotion import (
DailymotionIE,
@ -1208,20 +1210,6 @@ class GenericIE(InfoExtractor):
'duration': 51690,
},
},
# JWPlayer with M3U8
{
'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
'info_dict': {
'id': 'playlist',
'ext': 'mp4',
'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
'uploader': 'ren.tv',
},
'params': {
# m3u8 downloads
'skip_download': True,
}
},
# Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
# This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
{
@ -1648,6 +1636,10 @@ class GenericIE(InfoExtractor):
doc = compat_etree_fromstring(webpage.encode('utf-8'))
if doc.tag == 'rss':
return self._extract_rss(url, video_id, doc)
elif doc.tag == 'SmoothStreamingMedia':
info_dict['formats'] = self._parse_ism_formats(doc, url)
self._sort_formats(info_dict['formats'])
return info_dict
elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
smil = self._parse_smil(doc, url, video_id)
self._sort_formats(smil['formats'])
@ -1991,11 +1983,6 @@ class GenericIE(InfoExtractor):
if sportbox_urls:
return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
# Look for embedded PornHub player
pornhub_url = PornHubIE._extract_url(webpage)
if pornhub_url:
return self.url_result(pornhub_url, 'PornHub')
# Look for embedded XHamster player
xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
if xhamster_urls:
@ -2006,6 +1993,21 @@ class GenericIE(InfoExtractor):
if tnaflix_urls:
return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
# Look for embedded PornHub player
pornhub_urls = PornHubIE._extract_urls(webpage)
if pornhub_urls:
return _playlist_from_matches(pornhub_urls, ie=PornHubIE.ie_key())
# Look for embedded DrTuber player
drtuber_urls = DrTuberIE._extract_urls(webpage)
if drtuber_urls:
return _playlist_from_matches(drtuber_urls, ie=DrTuberIE.ie_key())
# Look for embedded RedTube player
redtube_urls = RedTubeIE._extract_urls(webpage)
if redtube_urls:
return _playlist_from_matches(redtube_urls, ie=RedTubeIE.ie_key())
# Look for embedded Tvigle player
mobj = re.search(
r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
@ -2463,6 +2465,21 @@ class GenericIE(InfoExtractor):
entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
elif ext == 'f4m':
entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
# Just matching .ism/manifest is not enough to be reliably sure
# whether it's actually an ISM manifest or some other streaming
# manifest since there are various streaming URL formats
# possible (see [1]) as well as some other shenanigans like
# .smil/manifest URLs that actually serve an ISM (see [2]) and
# so on.
# Thus the most reasonable way to solve this is to delegate
# to generic extractor in order to look into the contents of
# the manifest itself.
# 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
# 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
entry_info_dict = self.url_result(
smuggle_url(video_url, {'to_generic': True}),
GenericIE.ie_key())
else:
entry_info_dict['url'] = video_url

View File

@ -4,9 +4,6 @@ import itertools
import re
from .common import SearchInfoExtractor
from ..compat import (
compat_urllib_parse,
)
class GoogleSearchIE(SearchInfoExtractor):
@ -34,13 +31,16 @@ class GoogleSearchIE(SearchInfoExtractor):
}
for pagenum in itertools.count():
result_url = (
'http://www.google.com/search?tbm=vid&q=%s&start=%s&hl=en'
% (compat_urllib_parse.quote_plus(query), pagenum * 10))
webpage = self._download_webpage(
result_url, 'gvsearch:' + query,
note='Downloading result page ' + str(pagenum + 1))
'http://www.google.com/search',
'gvsearch:' + query,
note='Downloading result page %s' % (pagenum + 1),
query={
'tbm': 'vid',
'q': query,
'start': pagenum * 10,
'hl': 'en',
})
for hit_idx, mobj in enumerate(re.finditer(
r'<h3 class="r"><a href="([^"]+)"', webpage)):

View File

@ -1,8 +1,6 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
int_or_none,
@ -14,29 +12,24 @@ class HornBunnyIE(InfoExtractor):
_VALID_URL = r'http?://(?:www\.)?hornbunny\.com/videos/(?P<title_dash>[a-z-]+)-(?P<id>\d+)\.html'
_TEST = {
'url': 'http://hornbunny.com/videos/panty-slut-jerk-off-instruction-5227.html',
'md5': '95e40865aedd08eff60272b704852ad7',
'md5': 'e20fd862d1894b67564c96f180f43924',
'info_dict': {
'id': '5227',
'ext': 'flv',
'ext': 'mp4',
'title': 'panty slut jerk off instruction',
'duration': 550,
'age_limit': 18,
'view_count': int,
'thumbnail': 're:^https?://.*\.jpg$',
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
video_id = self._match_id(url)
webpage = self._download_webpage(
url, video_id, note='Downloading initial webpage')
title = self._html_search_regex(
r'class="title">(.*?)</h2>', webpage, 'title')
redirect_url = self._html_search_regex(
r'pg&settings=(.*?)\|0"\);', webpage, 'title')
webpage2 = self._download_webpage(redirect_url, video_id)
video_url = self._html_search_regex(
r'flvMask:(.*?);', webpage2, 'video_url')
webpage = self._download_webpage(url, video_id)
title = self._og_search_title(webpage)
info_dict = self._parse_html5_media_entries(url, webpage, video_id)[0]
duration = parse_duration(self._search_regex(
r'<strong>Runtime:</strong>\s*([0-9:]+)</div>',
@ -45,12 +38,12 @@ class HornBunnyIE(InfoExtractor):
r'<strong>Views:</strong>\s*(\d+)</div>',
webpage, 'view count', fatal=False))
return {
info_dict.update({
'id': video_id,
'url': video_url,
'title': title,
'ext': 'flv',
'duration': duration,
'view_count': view_count,
'age_limit': 18,
}
})
return info_dict

View File

@ -13,7 +13,7 @@ from ..utils import (
class ImgurIE(InfoExtractor):
_VALID_URL = r'https?://(?:i\.)?imgur\.com/(?:(?:gallery|topic/[^/]+)/)?(?P<id>[a-zA-Z0-9]{6,})(?:[/?#&]+|\.[a-z]+)?$'
_VALID_URL = r'https?://(?:i\.)?imgur\.com/(?:(?:gallery|(?:topic|r)/[^/]+)/)?(?P<id>[a-zA-Z0-9]{6,})(?:[/?#&]+|\.[a-z]+)?$'
_TESTS = [{
'url': 'https://i.imgur.com/A61SaA1.gifv',
@ -43,6 +43,9 @@ class ImgurIE(InfoExtractor):
}, {
'url': 'http://imgur.com/topic/Funny/N8rOudd',
'only_matching': True,
}, {
'url': 'http://imgur.com/r/aww/VQcQPhM',
'only_matching': True,
}]
def _real_extract(self, url):

View File

@ -0,0 +1,107 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from ..compat import compat_urlparse
from .common import InfoExtractor
class JamendoIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?jamendo\.com/track/(?P<id>[0-9]+)/(?P<display_id>[^/?#&]+)'
_TEST = {
'url': 'https://www.jamendo.com/track/196219/stories-from-emona-i',
'md5': '6e9e82ed6db98678f171c25a8ed09ffd',
'info_dict': {
'id': '196219',
'display_id': 'stories-from-emona-i',
'ext': 'flac',
'title': 'Stories from Emona I',
'thumbnail': 're:^https?://.*\.jpg'
}
}
def _real_extract(self, url):
mobj = self._VALID_URL_RE.match(url)
track_id = mobj.group('id')
display_id = mobj.group('display_id')
webpage = self._download_webpage(url, display_id)
title = self._html_search_meta('name', webpage, 'title')
formats = [{
'url': 'https://%s.jamendo.com/?trackid=%s&format=%s&from=app-97dab294'
% (sub_domain, track_id, format_id),
'format_id': format_id,
'ext': ext,
'quality': quality,
} for quality, (format_id, sub_domain, ext) in enumerate((
('mp31', 'mp3l', 'mp3'),
('mp32', 'mp3d', 'mp3'),
('ogg1', 'ogg', 'ogg'),
('flac', 'flac', 'flac'),
))]
self._sort_formats(formats)
thumbnail = self._html_search_meta(
'image', webpage, 'thumbnail', fatal=False)
return {
'id': track_id,
'display_id': display_id,
'thumbnail': thumbnail,
'title': title,
'formats': formats
}
class JamendoAlbumIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?jamendo\.com/album/(?P<id>[0-9]+)/(?P<display_id>[\w-]+)'
_TEST = {
'url': 'https://www.jamendo.com/album/121486/duck-on-cover',
'info_dict': {
'id': '121486',
'title': 'Duck On Cover'
},
'playlist': [{
'md5': 'e1a2fcb42bda30dfac990212924149a8',
'info_dict': {
'id': '1032333',
'ext': 'flac',
'title': 'Warmachine'
}
}, {
'md5': '1f358d7b2f98edfe90fd55dac0799d50',
'info_dict': {
'id': '1032330',
'ext': 'flac',
'title': 'Without Your Ghost'
}
}],
'params': {
'playlistend': 2
}
}
def _real_extract(self, url):
mobj = self._VALID_URL_RE.match(url)
album_id = mobj.group('id')
webpage = self._download_webpage(url, mobj.group('display_id'))
title = self._html_search_meta('name', webpage, 'title')
entries = [
self.url_result(
compat_urlparse.urljoin(url, m.group('path')),
ie=JamendoIE.ie_key(),
video_id=self._search_regex(
r'/track/(\d+)', m.group('path'),
'track id', default=None))
for m in re.finditer(
r'<a[^>]+href=(["\'])(?P<path>(?:(?!\1).)+)\1[^>]+class=["\'][^>]*js-trackrow-albumpage-link',
webpage)
]
return self.playlist_result(entries, album_id, title)

View File

@ -71,12 +71,15 @@ class MicrosoftVirtualAcademyIE(MicrosoftVirtualAcademyBaseIE):
formats = []
for sources in settings.findall(compat_xpath('.//MediaSources')):
if sources.get('videoType') == 'smoothstreaming':
continue
sources_type = sources.get('videoType')
for source in sources.findall(compat_xpath('./MediaSource')):
video_url = source.text
if not video_url or not video_url.startswith('http'):
continue
if sources_type == 'smoothstreaming':
formats.extend(self._extract_ism_formats(
video_url, video_id, 'mss', fatal=False))
continue
video_mode = source.get('videoMode')
height = int_or_none(self._search_regex(
r'^(\d+)[pP]$', video_mode or '', 'height', default=None))

View File

@ -1,19 +1,20 @@
# coding: utf-8
from __future__ import unicode_literals
import re
import uuid
from .common import InfoExtractor
from ..compat import (
compat_str,
compat_urllib_parse_urlencode,
compat_urlparse,
)
from ..utils import (
get_element_by_attribute,
int_or_none,
remove_start,
extract_attributes,
determine_ext,
smuggle_url,
parse_duration,
)
@ -72,16 +73,14 @@ class MiTeleBaseIE(InfoExtractor):
}
class MiTeleIE(MiTeleBaseIE):
class MiTeleIE(InfoExtractor):
IE_DESC = 'mitele.es'
_VALID_URL = r'https?://(?:www\.)?mitele\.es/(?:[^/]+/){3}(?P<id>[^/]+)/'
_VALID_URL = r'https?://(?:www\.)?mitele\.es/programas-tv/(?:[^/]+/)(?P<id>[^/]+)/player'
_TESTS = [{
'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/',
# MD5 is unstable
'url': 'http://www.mitele.es/programas-tv/diario-de/57b0dfb9c715da65618b4afa/player',
'info_dict': {
'id': '0NF1jJnxS1Wu3pHrmvFyw2',
'display_id': 'programa-144',
'id': '57b0dfb9c715da65618b4afa',
'ext': 'mp4',
'title': 'Tor, la web invisible',
'description': 'md5:3b6fce7eaa41b2d97358726378d9369f',
@ -91,57 +90,71 @@ class MiTeleIE(MiTeleBaseIE):
'thumbnail': 're:(?i)^https?://.*\.jpg$',
'duration': 2913,
},
'add_ie': ['Ooyala'],
}, {
# no explicit title
'url': 'http://www.mitele.es/programas-tv/cuarto-milenio/temporada-6/programa-226/',
'url': 'http://www.mitele.es/programas-tv/cuarto-milenio/57b0de3dc915da14058b4876/player',
'info_dict': {
'id': 'eLZSwoEd1S3pVyUm8lc6F',
'display_id': 'programa-226',
'id': '57b0de3dc915da14058b4876',
'ext': 'mp4',
'title': 'Cuarto Milenio - Temporada 6 - Programa 226',
'description': 'md5:50daf9fadefa4e62d9fc866d0c015701',
'title': 'Cuarto Milenio Temporada 6 Programa 226',
'description': 'md5:5ff132013f0cd968ffbf1f5f3538a65f',
'series': 'Cuarto Milenio',
'season': 'Temporada 6',
'episode': 'Programa 226',
'thumbnail': 're:(?i)^https?://.*\.jpg$',
'duration': 7312,
'duration': 7313,
},
'params': {
'skip_download': True,
},
'add_ie': ['Ooyala'],
}]
def _real_extract(self, url):
display_id = self._match_id(url)
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
webpage = self._download_webpage(url, display_id)
gigya_url = self._search_regex(r'<gigya-api>[^>]*</gigya-api>[^>]*<script\s*src="([^"]*)">[^>]*</script>', webpage, 'gigya', default=None)
gigya_sc = self._download_webpage(compat_urlparse.urljoin(r'http://www.mitele.es/', gigya_url), video_id, 'Downloading gigya script')
# Get a appKey/uuid for getting the session key
appKey_var = self._search_regex(r'value\("appGridApplicationKey",([0-9a-f]+)\)', gigya_sc, 'appKey variable')
appKey = self._search_regex(r'var %s="([0-9a-f]+)"' % appKey_var, gigya_sc, 'appKey')
uid = compat_str(uuid.uuid4())
session_url = 'https://appgrid-api.cloud.accedo.tv/session?appKey=%s&uuid=%s' % (appKey, uid)
session_json = self._download_json(session_url, video_id, 'Downloading session keys')
sessionKey = compat_str(session_json['sessionKey'])
info = self._get_player_info(url, webpage)
paths_url = 'https://appgrid-api.cloud.accedo.tv/metadata/general_configuration,%20web_configuration?sessionKey=' + sessionKey
paths = self._download_json(paths_url, video_id, 'Downloading paths JSON')
ooyala_s = paths['general_configuration']['api_configuration']['ooyala_search']
data_p = (
'http://' + ooyala_s['base_url'] + ooyala_s['full_path'] + ooyala_s['provider_id'] +
'/docs/' + video_id + '?include_titles=Series,Season&product_name=test&format=full')
data = self._download_json(data_p, video_id, 'Downloading data JSON')
source = data['hits']['hits'][0]['_source']
embedCode = source['offers'][0]['embed_codes'][0]
title = self._search_regex(
r'class="Destacado-text"[^>]*>\s*<strong>([^<]+)</strong>',
webpage, 'title', default=None)
titles = source['localizable_titles'][0]
title = titles.get('title_medium') or titles['title_long']
episode = titles['title_sort_name']
description = titles['summary_long']
titles_series = source['localizable_titles_series'][0]
series = titles_series['title_long']
titles_season = source['localizable_titles_season'][0]
season = titles_season['title_medium']
duration = parse_duration(source['videos'][0]['duration'])
mobj = re.search(r'''(?sx)
class="Destacado-text"[^>]*>.*?<h1>\s*
<span>(?P<series>[^<]+)</span>\s*
<span>(?P<season>[^<]+)</span>\s*
<span>(?P<episode>[^<]+)</span>''', webpage)
series, season, episode = mobj.groups() if mobj else [None] * 3
if not title:
if mobj:
title = '%s - %s - %s' % (series, season, episode)
else:
title = remove_start(self._search_regex(
r'<title>([^<]+)</title>', webpage, 'title'), 'Ver online ')
info.update({
'display_id': display_id,
return {
'_type': 'url_transparent',
# for some reason only HLS is supported
'url': smuggle_url('ooyala:' + embedCode, {'supportedformats': 'm3u8'}),
'id': video_id,
'title': title,
'description': get_element_by_attribute('class', 'text', webpage),
'description': description,
'series': series,
'season': season,
'episode': episode,
})
return info
'duration': duration,
'thumbnail': source['images'][0]['url'],
}

View File

@ -11,7 +11,7 @@ from ..utils import (
class MovieClipsIE(InfoExtractor):
_VALID_URL = r'https?://(?:www.)?movieclips\.com/videos/.+-(?P<id>\d+)(?:\?|$)'
_VALID_URL = r'https?://(?:www\.)?movieclips\.com/videos/.+-(?P<id>\d+)(?:\?|$)'
_TEST = {
'url': 'http://www.movieclips.com/videos/warcraft-trailer-1-561180739597',
'md5': '42b5a0352d4933a7bd54f2104f481244',

View File

@ -69,10 +69,9 @@ class MSNIE(InfoExtractor):
if not format_url:
continue
ext = determine_ext(format_url)
# .ism is not yet supported (see
# https://github.com/rg3/youtube-dl/issues/8118)
if ext == 'ism':
continue
formats.extend(self._extract_ism_formats(
format_url + '/Manifest', display_id, 'mss', fatal=False))
if 'm3u8' in format_url:
# m3u8_native should not be used here until
# https://github.com/rg3/youtube-dl/issues/9913 is fixed

View File

@ -1,6 +1,8 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .mtv import MTVServicesInfoExtractor
from ..utils import update_url_query
@ -69,7 +71,7 @@ class NickIE(MTVServicesInfoExtractor):
class NickDeIE(MTVServicesInfoExtractor):
IE_NAME = 'nick.de'
_VALID_URL = r'https?://(?:www\.)?(?:nick\.de|nickelodeon\.nl)/(?:playlist|shows)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_VALID_URL = r'https?://(?:www\.)?(?P<host>nick\.de|nickelodeon\.(?:nl|at))/(?:playlist|shows)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://www.nick.de/playlist/3773-top-videos/videos/episode/17306-zu-wasser-und-zu-land-rauchende-erdnusse',
'only_matching': True,
@ -79,15 +81,43 @@ class NickDeIE(MTVServicesInfoExtractor):
}, {
'url': 'http://www.nickelodeon.nl/shows/474-spongebob/videos/17403-een-kijkje-in-de-keuken-met-sandy-van-binnenuit',
'only_matching': True,
}, {
'url': 'http://www.nickelodeon.at/playlist/3773-top-videos/videos/episode/77993-das-letzte-gefecht',
'only_matching': True,
}]
def _extract_mrss_url(self, webpage, host):
return update_url_query(self._search_regex(
r'data-mrss=(["\'])(?P<url>http.+?)\1', webpage, 'mrss url', group='url'),
{'siteKey': host})
def _real_extract(self, url):
video_id = self._match_id(url)
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
host = mobj.group('host')
webpage = self._download_webpage(url, video_id)
mrss_url = update_url_query(self._search_regex(
r'data-mrss=(["\'])(?P<url>http.+?)\1', webpage, 'mrss url', group='url'),
{'siteKey': 'nick.de'})
mrss_url = self._extract_mrss_url(webpage, host)
return self._get_videos_info_from_url(mrss_url, video_id)
class NickNightIE(NickDeIE):
IE_NAME = 'nicknight'
_VALID_URL = r'https?://(?:www\.)(?P<host>nicknight\.(?:de|at|tv))/(?:playlist|shows)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://www.nicknight.at/shows/977-awkward/videos/85987-nimmer-beste-freunde',
'only_matching': True,
}, {
'url': 'http://www.nicknight.at/shows/977-awkward',
'only_matching': True,
}, {
'url': 'http://www.nicknight.at/shows/1900-faking-it',
'only_matching': True,
}]
def _extract_mrss_url(self, webpage, *args):
return self._search_regex(
r'mrss\s*:\s*(["\'])(?P<url>http.+?)\1', webpage,
'mrss url', group='url')

View File

@ -0,0 +1,62 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
js_to_json,
mimetype2ext,
determine_ext,
update_url_query,
get_element_by_attribute,
int_or_none,
)
class NobelPrizeIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?nobelprize\.org/mediaplayer.*?\bid=(?P<id>\d+)'
_TEST = {
'url': 'http://www.nobelprize.org/mediaplayer/?id=2636',
'md5': '04c81e5714bb36cc4e2232fee1d8157f',
'info_dict': {
'id': '2636',
'ext': 'mp4',
'title': 'Announcement of the 2016 Nobel Prize in Physics',
'description': 'md5:05beba57f4f5a4bbd4cf2ef28fcff739',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
media = self._parse_json(self._search_regex(
r'(?s)var\s*config\s*=\s*({.+?});', webpage,
'config'), video_id, js_to_json)['media']
title = media['title']
formats = []
for source in media.get('source', []):
source_src = source.get('src')
if not source_src:
continue
ext = mimetype2ext(source.get('type')) or determine_ext(source_src)
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
source_src, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
elif ext == 'f4m':
formats.extend(self._extract_f4m_formats(
update_url_query(source_src, {'hdcore': '3.7.0'}),
video_id, f4m_id='hds', fatal=False))
else:
formats.append({
'url': source_src,
})
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'description': get_element_by_attribute('itemprop', 'description', webpage),
'duration': int_or_none(media.get('duration')),
'formats': formats,
}

View File

@ -56,8 +56,8 @@ class OnetBaseIE(InfoExtractor):
continue
ext = determine_ext(video_url)
if format_id == 'ism':
# TODO: Support Microsoft Smooth Streaming
continue
formats.extend(self._extract_ism_formats(
video_url, video_id, 'mss', fatal=False))
elif ext == 'mpd':
formats.extend(self._extract_mpd_formats(
video_url, video_id, mpd_id='dash', fatal=False))

View File

@ -18,7 +18,7 @@ class OoyalaBaseIE(InfoExtractor):
_CONTENT_TREE_BASE = _PLAYER_BASE + 'player_api/v1/content_tree/'
_AUTHORIZATION_URL_TEMPLATE = _PLAYER_BASE + 'sas/player_api/v2/authorization/embed_code/%s/%s?'
def _extract(self, content_tree_url, video_id, domain='example.org'):
def _extract(self, content_tree_url, video_id, domain='example.org', supportedformats=None):
content_tree = self._download_json(content_tree_url, video_id)['content_tree']
metadata = content_tree[list(content_tree)[0]]
embed_code = metadata['embed_code']
@ -29,7 +29,7 @@ class OoyalaBaseIE(InfoExtractor):
self._AUTHORIZATION_URL_TEMPLATE % (pcode, embed_code) +
compat_urllib_parse_urlencode({
'domain': domain,
'supportedFormats': 'mp4,rtmp,m3u8,hds',
'supportedFormats': supportedformats or 'mp4,rtmp,m3u8,hds',
}), video_id)
cur_auth_data = auth_data['authorization_data'][embed_code]
@ -145,8 +145,9 @@ class OoyalaIE(OoyalaBaseIE):
url, smuggled_data = unsmuggle_url(url, {})
embed_code = self._match_id(url)
domain = smuggled_data.get('domain')
supportedformats = smuggled_data.get('supportedformats')
content_tree_url = self._CONTENT_TREE_BASE + 'embed_code/%s/%s' % (embed_code, embed_code)
return self._extract(content_tree_url, embed_code, domain)
return self._extract(content_tree_url, embed_code, domain, supportedformats)
class OoyalaExternalIE(OoyalaBaseIE):

View File

@ -82,7 +82,7 @@ class OpenloadIE(InfoExtractor):
if j >= 33 and j <= 126:
j = ((j + 14) % 94) + 33
if idx == len(enc_data) - 1:
j += 2
j += 3
video_url_chars += compat_chr(j)
video_url = 'https://openload.co/stream/%s?mime=true' % ''.join(video_url_chars)

View File

@ -0,0 +1,91 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
ExtractorError,
qualities,
)
class PandaTVIE(InfoExtractor):
IE_DESC = '熊猫TV'
_VALID_URL = r'http://(?:www\.)?panda\.tv/(?P<id>[0-9]+)'
_TEST = {
'url': 'http://www.panda.tv/10091',
'info_dict': {
'id': '10091',
'title': 're:.+',
'uploader': '囚徒',
'ext': 'flv',
'is_live': True,
},
'params': {
'skip_download': True,
},
'skip': 'Live stream is offline',
}
def _real_extract(self, url):
video_id = self._match_id(url)
config = self._download_json(
'http://www.panda.tv/api_room?roomid=%s' % video_id, video_id)
error_code = config.get('errno', 0)
if error_code is not 0:
raise ExtractorError(
'%s returned error %s: %s'
% (self.IE_NAME, error_code, config['errmsg']),
expected=True)
data = config['data']
video_info = data['videoinfo']
# 2 = live, 3 = offline
if video_info.get('status') != '2':
raise ExtractorError(
'Live stream is offline', expected=True)
title = data['roominfo']['name']
uploader = data.get('hostinfo', {}).get('name')
room_key = video_info['room_key']
stream_addr = video_info.get(
'stream_addr', {'OD': '1', 'HD': '1', 'SD': '1'})
# Reverse engineered from web player swf
# (http://s6.pdim.gs/static/07153e425f581151.swf at the moment of
# writing).
plflag0, plflag1 = video_info['plflag'].split('_')
plflag0 = int(plflag0) - 1
if plflag1 == '21':
plflag0 = 10
plflag1 = '4'
live_panda = 'live_panda' if plflag0 < 1 else ''
quality_key = qualities(['OD', 'HD', 'SD'])
suffix = ['_small', '_mid', '']
formats = []
for k, v in stream_addr.items():
if v != '1':
continue
quality = quality_key(k)
if quality <= 0:
continue
for pref, (ext, pl) in enumerate((('m3u8', '-hls'), ('flv', ''))):
formats.append({
'url': 'http://pl%s%s.live.panda.tv/live_panda/%s%s%s.%s'
% (pl, plflag1, room_key, live_panda, suffix[quality], ext),
'format_id': '%s-%s' % (k, ext),
'quality': quality,
'source_preference': pref,
})
self._sort_formats(formats)
return {
'id': video_id,
'title': self._live_title(title),
'uploader': uploader,
'formats': formats,
'is_live': True,
}

View File

@ -33,7 +33,7 @@ class PornHubIE(InfoExtractor):
(?:[a-z]+\.)?pornhub\.com/(?:view_video\.php\?viewkey=|embed/)|
(?:www\.)?thumbzilla\.com/video/
)
(?P<id>[0-9a-z]+)
(?P<id>[\da-z]+)
'''
_TESTS = [{
'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
@ -96,12 +96,11 @@ class PornHubIE(InfoExtractor):
'only_matching': True,
}]
@classmethod
def _extract_url(cls, webpage):
mobj = re.search(
r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?pornhub\.com/embed/\d+)\1', webpage)
if mobj:
return mobj.group('url')
@staticmethod
def _extract_urls(webpage):
return re.findall(
r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub\.com/embed/[\da-z]+)',
webpage)
def _extract_count(self, pattern, webpage, name):
return str_to_int(self._search_regex(

View File

@ -125,6 +125,14 @@ class RadioCanadaIE(InfoExtractor):
f4m_id='hds', fatal=False))
self._sort_formats(formats)
subtitles = {}
closed_caption_url = get_meta('closedCaption') or get_meta('closedCaptionHTML5')
if closed_caption_url:
subtitles['fr'] = [{
'url': closed_caption_url,
'ext': determine_ext(closed_caption_url, 'vtt'),
}]
return {
'id': video_id,
'title': get_meta('Title'),
@ -135,6 +143,7 @@ class RadioCanadaIE(InfoExtractor):
'season_number': int_or_none('SrcSaison'),
'episode_number': int_or_none('SrcEpisode'),
'upload_date': unified_strdate(get_meta('Date')),
'subtitles': subtitles,
'formats': formats,
}

View File

@ -1,5 +1,7 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
@ -10,8 +12,8 @@ from ..utils import (
class RedTubeIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?redtube\.com/(?P<id>[0-9]+)'
_TEST = {
_VALID_URL = r'https?://(?:(?:www\.)?redtube\.com/|embed\.redtube\.com/\?.*?\bid=)(?P<id>[0-9]+)'
_TESTS = [{
'url': 'http://www.redtube.com/66418',
'md5': '7b8c22b5e7098a3e1c09709df1126d2d',
'info_dict': {
@ -23,11 +25,21 @@ class RedTubeIE(InfoExtractor):
'view_count': int,
'age_limit': 18,
}
}
}, {
'url': 'http://embed.redtube.com/?bgcolor=000000&id=1443286',
'only_matching': True,
}]
@staticmethod
def _extract_urls(webpage):
return re.findall(
r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//embed\.redtube\.com/\?.*?\bid=\d+)',
webpage)
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
webpage = self._download_webpage(
'http://www.redtube.com/%s' % video_id, video_id)
if any(s in webpage for s in ['video-deleted-info', '>This video has been removed']):
raise ExtractorError('Video %s has been removed' % video_id, expected=True)

View File

@ -0,0 +1,76 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from .jwplatform import JWPlatformBaseIE
from ..compat import compat_str
class RENTVIE(JWPlatformBaseIE):
_VALID_URL = r'(?:rentv:|https?://(?:www\.)?ren\.tv/(?:player|video/epizod)/)(?P<id>\d+)'
_TESTS = [{
'url': 'http://ren.tv/video/epizod/118577',
'md5': 'd91851bf9af73c0ad9b2cdf76c127fbb',
'info_dict': {
'id': '118577',
'ext': 'mp4',
'title': 'Документальный спецпроект: "Промывка мозгов. Технологии XXI века"'
}
}, {
'url': 'http://ren.tv/player/118577',
'only_matching': True,
}, {
'url': 'rentv:118577',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage('http://ren.tv/player/' + video_id, video_id)
jw_config = self._parse_json(self._search_regex(
r'config\s*=\s*({.+});', webpage, 'jw config'), video_id)
return self._parse_jwplayer_data(jw_config, video_id, m3u8_id='hls')
class RENTVArticleIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?ren\.tv/novosti/\d{4}-\d{2}-\d{2}/(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'http://ren.tv/novosti/2016-10-26/video-mikroavtobus-popavshiy-v-dtp-s-gruzovikami-v-podmoskove-prevratilsya-v',
'md5': 'ebd63c4680b167693745ab91343df1d6',
'info_dict': {
'id': '136472',
'ext': 'mp4',
'title': 'Видео: микроавтобус, попавший в ДТП с грузовиками в Подмосковье, превратился в груду металла',
'description': 'Жертвами столкновения двух фур и микроавтобуса, по последним данным, стали семь человек.',
}
}, {
# TODO: invalid m3u8
'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
'info_dict': {
'id': 'playlist',
'ext': 'mp4',
'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
'uploader': 'ren.tv',
},
'params': {
# m3u8 downloads
'skip_download': True,
},
'skip': True,
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
drupal_settings = self._parse_json(self._search_regex(
r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);',
webpage, 'drupal settings'), display_id)
entries = []
for config_profile in drupal_settings.get('ren_jwplayer', {}).values():
media_id = config_profile.get('mediaid')
if not media_id:
continue
media_id = compat_str(media_id)
entries.append(self.url_result('rentv:' + media_id, 'RENTV', media_id))
return self.playlist_result(entries, display_id)

View File

@ -1,17 +1,24 @@
# coding: utf-8
from __future__ import unicode_literals
import re
import json
from .common import InfoExtractor
from ..compat import compat_HTTPError
from ..utils import (
ExtractorError,
int_or_none,
parse_iso8601,
str_or_none,
urlencode_postdata,
clean_html,
)
class ShahidIE(InfoExtractor):
_VALID_URL = r'https?://shahid\.mbc\.net/ar/episode/(?P<id>\d+)/?'
_NETRC_MACHINE = 'shahid'
_VALID_URL = r'https?://shahid\.mbc\.net/ar/(?P<type>episode|movie)/(?P<id>\d+)'
_TESTS = [{
'url': 'https://shahid.mbc.net/ar/episode/90574/%D8%A7%D9%84%D9%85%D9%84%D9%83-%D8%B9%D8%A8%D8%AF%D8%A7%D9%84%D9%84%D9%87-%D8%A7%D9%84%D8%A5%D9%86%D8%B3%D8%A7%D9%86-%D8%A7%D9%84%D9%85%D9%88%D8%B3%D9%85-1-%D9%83%D9%84%D9%8A%D8%A8-3.html',
'info_dict': {
@ -27,18 +34,54 @@ class ShahidIE(InfoExtractor):
# m3u8 download
'skip_download': True,
}
}, {
'url': 'https://shahid.mbc.net/ar/movie/151746/%D8%A7%D9%84%D9%82%D9%86%D8%A7%D8%B5%D8%A9.html',
'only_matching': True
}, {
# shahid plus subscriber only
'url': 'https://shahid.mbc.net/ar/episode/90511/%D9%85%D8%B1%D8%A7%D9%8A%D8%A7-2011-%D8%A7%D9%84%D9%85%D9%88%D8%B3%D9%85-1-%D8%A7%D9%84%D8%AD%D9%84%D9%82%D8%A9-1.html',
'only_matching': True
}]
def _call_api(self, path, video_id, note):
data = self._download_json(
'http://api.shahid.net/api/v1_1/' + path, video_id, note, query={
'apiKey': 'sh@hid0nlin3',
'hash': 'b2wMCTHpSmyxGqQjJFOycRmLSex+BpTK/ooxy6vHaqs=',
}).get('data', {})
def _real_initialize(self):
email, password = self._get_login_info()
if email is None:
return
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):
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
self._download_webpage(
'https://shahid.mbc.net/populateContext',
None, 'Populate Context', data=urlencode_postdata({
'firstName': user_data['firstName'],
'lastName': user_data['lastName'],
'userName': user_data['email'],
'csg_user_name': user_data['email'],
'subscriberId': user_data['id'],
'sessionId': user_data['sessionId'],
}))
def _get_api_data(self, response):
data = response.get('data', {})
error = data.get('error')
if error:
@ -49,11 +92,11 @@ class ShahidIE(InfoExtractor):
return data
def _real_extract(self, url):
video_id = self._match_id(url)
page_type, video_id = re.match(self._VALID_URL, url).groups()
player = self._call_api(
'Content/Episode/%s' % video_id,
video_id, 'Downloading player JSON')
player = self._get_api_data(self._download_json(
'https://shahid.mbc.net/arContent/getPlayerContent-param-.id-%s.type-player.html' % video_id,
video_id, 'Downloading player JSON'))
if player.get('drm'):
raise ExtractorError('This video is DRM protected.', expected=True)
@ -61,9 +104,12 @@ class ShahidIE(InfoExtractor):
formats = self._extract_m3u8_formats(player['url'], video_id, 'mp4')
self._sort_formats(formats)
video = self._call_api(
'episode/%s' % video_id, video_id,
'Downloading video JSON')['episode']
video = self._get_api_data(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]
title = video['title']
categories = [

View File

@ -32,12 +32,15 @@ class TMZArticleIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?tmz\.com/\d{4}/\d{2}/\d{2}/(?P<id>[^/]+)/?'
_TEST = {
'url': 'http://www.tmz.com/2015/04/19/bobby-brown-bobbi-kristina-awake-video-concert',
'md5': 'e482a414a38db73087450e3a6ce69d00',
'md5': '3316ff838ae5bb7f642537825e1e90d2',
'info_dict': {
'id': '0_6snoelag',
'ext': 'mp4',
'ext': 'mov',
'title': 'Bobby Brown Tells Crowd ... Bobbi Kristina is Awake',
'description': 'Bobby Brown stunned his audience during a concert Saturday night, when he told the crowd, "Bobbi is awake. She\'s watching me."',
'timestamp': 1429467813,
'upload_date': '20150419',
'uploader_id': 'batchUser',
}
}
@ -45,12 +48,9 @@ class TMZArticleIE(InfoExtractor):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
embedded_video_info_str = self._html_search_regex(
r'tmzVideoEmbedV2\("([^)]+)"\);', webpage, 'embedded video info')
embedded_video_info = self._parse_json(
embedded_video_info_str, video_id,
transform_source=lambda s: s.replace('\\', ''))
embedded_video_info = self._parse_json(self._html_search_regex(
r'tmzVideoEmbed\(({.+?})\);', webpage, 'embedded video info'),
video_id)
return self.url_result(
'http://www.tmz.com/videos/%s/' % embedded_video_info['id'])

View File

@ -15,11 +15,11 @@ from ..utils import (
class TouTvIE(InfoExtractor):
_NETRC_MACHINE = 'toutv'
IE_NAME = 'tou.tv'
_VALID_URL = r'https?://ici\.tou\.tv/(?P<id>[a-zA-Z0-9_-]+/S[0-9]+E[0-9]+)'
_VALID_URL = r'https?://ici\.tou\.tv/(?P<id>[a-zA-Z0-9_-]+(?:/S[0-9]+E[0-9]+)?)'
_access_token = None
_claims = None
_TEST = {
_TESTS = [{
'url': 'http://ici.tou.tv/garfield-tout-court/S2015E17',
'info_dict': {
'id': '122017',
@ -33,7 +33,10 @@ class TouTvIE(InfoExtractor):
'skip_download': True,
},
'skip': '404 Not Found',
}
}, {
'url': 'http://ici.tou.tv/hackers',
'only_matching': True,
}]
def _real_initialize(self):
email, password = self._get_login_info()

View File

@ -9,7 +9,6 @@ from ..utils import (
int_or_none,
sanitized_Request,
urlencode_postdata,
parse_iso8601,
)
@ -19,17 +18,13 @@ class TubiTvIE(InfoExtractor):
_NETRC_MACHINE = 'tubitv'
_TEST = {
'url': 'http://tubitv.com/video/283829/the_comedian_at_the_friday',
'md5': '43ac06be9326f41912dc64ccf7a80320',
'info_dict': {
'id': '283829',
'ext': 'mp4',
'title': 'The Comedian at The Friday',
'description': 'A stand up comedian is forced to look at the decisions in his life while on a one week trip to the west coast.',
'uploader': 'Indie Rights Films',
'upload_date': '20160111',
'timestamp': 1452555979,
},
'params': {
'skip_download': 'HLS download',
'uploader_id': 'bc168bee0d18dd1cb3b86c68706ab434',
},
}
@ -58,19 +53,28 @@ class TubiTvIE(InfoExtractor):
video_id = self._match_id(url)
video_data = self._download_json(
'http://tubitv.com/oz/videos/%s/content' % video_id, video_id)
title = video_data['n']
title = video_data['title']
formats = self._extract_m3u8_formats(
video_data['mh'], video_id, 'mp4', 'm3u8_native')
self._proto_relative_url(video_data['url']),
video_id, 'mp4', 'm3u8_native')
self._sort_formats(formats)
thumbnails = []
for thumbnail_url in video_data.get('thumbnails', []):
if not thumbnail_url:
continue
thumbnails.append({
'url': self._proto_relative_url(thumbnail_url),
})
subtitles = {}
for sub in video_data.get('sb', []):
sub_url = sub.get('u')
for sub in video_data.get('subtitles', []):
sub_url = sub.get('url')
if not sub_url:
continue
subtitles.setdefault(sub.get('l', 'en'), []).append({
'url': sub_url,
subtitles.setdefault(sub.get('lang', 'English'), []).append({
'url': self._proto_relative_url(sub_url),
})
return {
@ -78,9 +82,8 @@ class TubiTvIE(InfoExtractor):
'title': title,
'formats': formats,
'subtitles': subtitles,
'thumbnail': video_data.get('ph'),
'description': video_data.get('d'),
'duration': int_or_none(video_data.get('s')),
'timestamp': parse_iso8601(video_data.get('u')),
'uploader': video_data.get('on'),
'thumbnails': thumbnails,
'description': video_data.get('description'),
'duration': int_or_none(video_data.get('duration')),
'uploader_id': video_data.get('publisher_id'),
}

View File

@ -69,7 +69,8 @@ class TVPIE(InfoExtractor):
webpage = self._download_webpage(url, page_id)
video_id = self._search_regex([
r'<iframe[^>]+src="[^"]*?object_id=(\d+)',
"object_id\s*:\s*'(\d+)'"], webpage, 'video id')
r"object_id\s*:\s*'(\d+)'",
r'data-video-id="(\d+)"'], webpage, 'video id', default=page_id)
return {
'_type': 'url_transparent',
'url': 'tvp:' + video_id,
@ -138,6 +139,9 @@ class TVPEmbedIE(InfoExtractor):
# formats.extend(self._extract_mpd_formats(
# video_url_base + '.ism/video.mpd',
# video_id, mpd_id='dash', fatal=False))
formats.extend(self._extract_ism_formats(
video_url_base + '.ism/Manifest',
video_id, 'mss', fatal=False))
formats.extend(self._extract_f4m_formats(
video_url_base + '.ism/video.f4m',
video_id, f4m_id='hds', fatal=False))

View File

@ -13,7 +13,7 @@ from ..utils import (
class VesselIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?vessel\.com/(?:videos|embed)/(?P<id>[0-9a-zA-Z]+)'
_VALID_URL = r'https?://(?:www\.)?vessel\.com/(?:videos|embed)/(?P<id>[0-9a-zA-Z-_]+)'
_API_URL_TEMPLATE = 'https://www.vessel.com/api/view/items/%s'
_LOGIN_URL = 'https://www.vessel.com/api/account/login'
_NETRC_MACHINE = 'vessel'
@ -32,12 +32,18 @@ class VesselIE(InfoExtractor):
}, {
'url': 'https://www.vessel.com/embed/G4U7gUJ6a?w=615&h=346',
'only_matching': True,
}, {
'url': 'https://www.vessel.com/videos/F01_dsLj1',
'only_matching': True,
}, {
'url': 'https://www.vessel.com/videos/RRX-sir-J',
'only_matching': True,
}]
@staticmethod
def _extract_urls(webpage):
return [url for _, url in re.findall(
r'<iframe[^>]+src=(["\'])((?:https?:)?//(?:www\.)?vessel\.com/embed/[0-9a-zA-Z]+.*?)\1',
r'<iframe[^>]+src=(["\'])((?:https?:)?//(?:www\.)?vessel\.com/embed/[0-9a-zA-Z-_]+.*?)\1',
webpage)]
@staticmethod

View File

@ -1,12 +1,93 @@
# coding: utf-8
from __future__ import unicode_literals
import re
import time
import hashlib
import json
from .adobepass import AdobePassIE
from .common import InfoExtractor
from ..utils import ExtractorError
from ..compat import compat_HTTPError
from ..utils import (
int_or_none,
parse_age_limit,
str_or_none,
parse_duration,
ExtractorError,
extract_attributes,
)
class ViceIE(InfoExtractor):
class ViceBaseIE(AdobePassIE):
def _extract_preplay_video(self, url, webpage):
watch_hub_data = extract_attributes(self._search_regex(
r'(?s)(<watch-hub\s*.+?</watch-hub>)', webpage, 'watch hub'))
video_id = watch_hub_data['vms-id']
title = watch_hub_data['video-title']
query = {}
is_locked = watch_hub_data.get('video-locked') == '1'
if is_locked:
resource = self._get_mvpd_resource(
'VICELAND', title, video_id,
watch_hub_data.get('video-rating'))
query['tvetoken'] = self._extract_mvpd_auth(url, video_id, 'VICELAND', resource)
# signature generation algorithm is reverse engineered from signatureGenerator in
# webpack:///../shared/~/vice-player/dist/js/vice-player.js in
# https://www.viceland.com/assets/common/js/web.vendor.bundle.js
exp = int(time.time()) + 14400
query.update({
'exp': exp,
'sign': hashlib.sha512(('%s:GET:%d' % (video_id, exp)).encode()).hexdigest(),
})
try:
host = 'www.viceland' if is_locked else self._PREPLAY_HOST
preplay = self._download_json('https://%s.com/en_us/preplay/%s' % (host, video_id), video_id, query=query)
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400:
error = json.loads(e.cause.read().decode())
raise ExtractorError('%s said: %s' % (self.IE_NAME, error['details']), expected=True)
raise
video_data = preplay['video']
base = video_data['base']
uplynk_preplay_url = preplay['preplayURL']
episode = video_data.get('episode', {})
channel = video_data.get('channel', {})
subtitles = {}
cc_url = preplay.get('ccURL')
if cc_url:
subtitles['en'] = [{
'url': cc_url,
}]
return {
'_type': 'url_transparent',
'url': uplynk_preplay_url,
'id': video_id,
'title': title,
'description': base.get('body'),
'thumbnail': watch_hub_data.get('cover-image') or watch_hub_data.get('thumbnail'),
'duration': parse_duration(video_data.get('video_duration') or watch_hub_data.get('video-duration')),
'timestamp': int_or_none(video_data.get('created_at')),
'age_limit': parse_age_limit(video_data.get('video_rating')),
'series': video_data.get('show_title') or watch_hub_data.get('show-title'),
'episode_number': int_or_none(episode.get('episode_number') or watch_hub_data.get('episode')),
'episode_id': str_or_none(episode.get('id') or video_data.get('episode_id')),
'season_number': int_or_none(watch_hub_data.get('season')),
'season_id': str_or_none(episode.get('season_id')),
'uploader': channel.get('base', {}).get('title') or watch_hub_data.get('channel-title'),
'uploader_id': str_or_none(channel.get('id')),
'subtitles': subtitles,
'ie_key': 'UplynkPreplay',
}
class ViceIE(ViceBaseIE):
_VALID_URL = r'https?://(?:.+?\.)?vice\.com/(?:[^/]+/)?videos?/(?P<id>[^/?#&]+)'
_TESTS = [{
@ -21,7 +102,7 @@ class ViceIE(InfoExtractor):
'add_ie': ['Ooyala'],
}, {
'url': 'http://www.vice.com/video/how-to-hack-a-car',
'md5': '6fb2989a3fed069fb8eab3401fc2d3c9',
'md5': 'a7ecf64ee4fa19b916c16f4b56184ae2',
'info_dict': {
'id': '3jstaBeXgAs',
'ext': 'mp4',
@ -32,6 +113,22 @@ class ViceIE(InfoExtractor):
'upload_date': '20140529',
},
'add_ie': ['Youtube'],
}, {
'url': 'https://video.vice.com/en_us/video/the-signal-from-tolva/5816510690b70e6c5fd39a56',
'md5': '',
'info_dict': {
'id': '5816510690b70e6c5fd39a56',
'ext': 'mp4',
'uploader': 'Waypoint',
'title': 'The Signal From Tölva',
'uploader_id': '57f7d621e05ca860fa9ccaf9',
'timestamp': 1477941983938,
},
'params': {
# m3u8 download
'skip_download': True,
},
'add_ie': ['UplynkPreplay'],
}, {
'url': 'https://news.vice.com/video/experimenting-on-animals-inside-the-monkey-lab',
'only_matching': True,
@ -42,21 +139,21 @@ class ViceIE(InfoExtractor):
'url': 'https://munchies.vice.com/en/videos/watch-the-trailer-for-our-new-series-the-pizza-show',
'only_matching': True,
}]
_PREPLAY_HOST = 'video.vice'
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
try:
embed_code = self._search_regex(
r'embedCode=([^&\'"]+)', webpage,
'ooyala embed code', default=None)
if embed_code:
return self.url_result('ooyala:%s' % embed_code, 'Ooyala')
youtube_id = self._search_regex(
r'data-youtube-id="([^"]+)"', webpage, 'youtube id')
webpage, urlh = self._download_webpage_handle(url, video_id)
embed_code = self._search_regex(
r'embedCode=([^&\'"]+)', webpage,
'ooyala embed code', default=None)
if embed_code:
return self.url_result('ooyala:%s' % embed_code, 'Ooyala')
youtube_id = self._search_regex(
r'data-youtube-id="([^"]+)"', webpage, 'youtube id', default=None)
if youtube_id:
return self.url_result(youtube_id, 'Youtube')
except ExtractorError:
raise ExtractorError('The page doesn\'t contain a video', expected=True)
return self._extract_preplay_video(urlh.geturl(), webpage)
class ViceShowIE(InfoExtractor):

View File

@ -1,23 +1,10 @@
# coding: utf-8
from __future__ import unicode_literals
import time
import hashlib
import json
from .adobepass import AdobePassIE
from ..compat import compat_HTTPError
from ..utils import (
int_or_none,
parse_age_limit,
str_or_none,
parse_duration,
ExtractorError,
extract_attributes,
)
from .vice import ViceBaseIE
class VicelandIE(AdobePassIE):
class VicelandIE(ViceBaseIE):
_VALID_URL = r'https?://(?:www\.)?viceland\.com/[^/]+/video/[^/]+/(?P<id>[a-f0-9]+)'
_TEST = {
'url': 'https://www.viceland.com/en_us/video/cyberwar-trailer/57608447973ee7705f6fbd4e',
@ -38,70 +25,9 @@ class VicelandIE(AdobePassIE):
},
'add_ie': ['UplynkPreplay'],
}
_PREPLAY_HOST = 'www.viceland'
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
watch_hub_data = extract_attributes(self._search_regex(
r'(?s)(<watch-hub\s*.+?</watch-hub>)', webpage, 'watch hub'))
video_id = watch_hub_data['vms-id']
title = watch_hub_data['video-title']
query = {}
if watch_hub_data.get('video-locked') == '1':
resource = self._get_mvpd_resource(
'VICELAND', title, video_id,
watch_hub_data.get('video-rating'))
query['tvetoken'] = self._extract_mvpd_auth(url, video_id, 'VICELAND', resource)
# signature generation algorithm is reverse engineered from signatureGenerator in
# webpack:///../shared/~/vice-player/dist/js/vice-player.js in
# https://www.viceland.com/assets/common/js/web.vendor.bundle.js
exp = int(time.time()) + 14400
query.update({
'exp': exp,
'sign': hashlib.sha512(('%s:GET:%d' % (video_id, exp)).encode()).hexdigest(),
})
try:
preplay = self._download_json('https://www.viceland.com/en_us/preplay/%s' % video_id, video_id, query=query)
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400:
error = json.loads(e.cause.read().decode())
raise ExtractorError('%s said: %s' % (self.IE_NAME, error['details']), expected=True)
raise
video_data = preplay['video']
base = video_data['base']
uplynk_preplay_url = preplay['preplayURL']
episode = video_data.get('episode', {})
channel = video_data.get('channel', {})
subtitles = {}
cc_url = preplay.get('ccURL')
if cc_url:
subtitles['en'] = [{
'url': cc_url,
}]
return {
'_type': 'url_transparent',
'url': uplynk_preplay_url,
'id': video_id,
'title': title,
'description': base.get('body'),
'thumbnail': watch_hub_data.get('cover-image') or watch_hub_data.get('thumbnail'),
'duration': parse_duration(video_data.get('video_duration') or watch_hub_data.get('video-duration')),
'timestamp': int_or_none(video_data.get('created_at')),
'age_limit': parse_age_limit(video_data.get('video_rating')),
'series': video_data.get('show_title') or watch_hub_data.get('show-title'),
'episode_number': int_or_none(episode.get('episode_number') or watch_hub_data.get('episode')),
'episode_id': str_or_none(episode.get('id') or video_data.get('episode_id')),
'season_number': int_or_none(watch_hub_data.get('season')),
'season_id': str_or_none(episode.get('season_id')),
'uploader': channel.get('base', {}).get('title') or watch_hub_data.get('channel-title'),
'uploader_id': str_or_none(channel.get('id')),
'subtitles': subtitles,
'ie_key': 'UplynkPreplay',
}
return self._extract_preplay_video(url, webpage)

View File

@ -3,7 +3,6 @@ from __future__ import unicode_literals
import collections
import re
import json
import sys
from .common import InfoExtractor
@ -369,8 +368,18 @@ class VKIE(VKBaseIE):
opts_url = 'http:' + opts_url
return self.url_result(opts_url)
data_json = self._search_regex(r'var\s+vars\s*=\s*({.+?});', info_page, 'vars')
data = json.loads(data_json)
# vars does not look to be served anymore since 24.10.2016
data = self._parse_json(
self._search_regex(
r'var\s+vars\s*=\s*({.+?});', info_page, 'vars', default='{}'),
video_id, fatal=False)
# <!json> is served instead
if not data:
data = self._parse_json(
self._search_regex(
r'<!json>\s*({.+?})\s*<!>', info_page, 'json'),
video_id)['player']['params'][0]
title = unescapeHTML(data['md_title'])

View File

@ -31,7 +31,8 @@ class VodlockerIE(InfoExtractor):
if any(p in webpage for p in (
'>THIS FILE WAS DELETED<',
'>File Not Found<',
'The file you were looking for could not be found, sorry for any inconvenience.<')):
'The file you were looking for could not be found, sorry for any inconvenience.<',
'>The file was removed')):
raise ExtractorError('Video %s does not exist' % video_id, expected=True)
fields = self._hidden_inputs(webpage)

View File

@ -0,0 +1,55 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
int_or_none,
float_or_none,
)
class VzaarIE(InfoExtractor):
_VALID_URL = r'https?://(?:(?:www|view)\.)?vzaar\.com/(?:videos/)?(?P<id>\d+)'
_TESTS = [{
'url': 'https://vzaar.com/videos/1152805',
'md5': 'bde5ddfeb104a6c56a93a06b04901dbf',
'info_dict': {
'id': '1152805',
'ext': 'mp4',
'title': 'sample video (public)',
},
}, {
'url': 'https://view.vzaar.com/27272/player',
'md5': '3b50012ac9bbce7f445550d54e0508f2',
'info_dict': {
'id': '27272',
'ext': 'mp3',
'title': 'MP3',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
video_data = self._download_json(
'http://view.vzaar.com/v2/%s/video' % video_id, video_id)
source_url = video_data['sourceUrl']
info = {
'id': video_id,
'title': video_data['videoTitle'],
'url': source_url,
'thumbnail': self._proto_relative_url(video_data.get('poster')),
'duration': float_or_none(video_data.get('videoDuration')),
}
if 'audio' in source_url:
info.update({
'vcodec': 'none',
'ext': 'mp3',
})
else:
info.update({
'width': int_or_none(video_data.get('width')),
'height': int_or_none(video_data.get('height')),
'ext': 'mp4',
})
return info

View File

@ -201,6 +201,32 @@ class YahooIE(InfoExtractor):
},
'skip': 'redirect to https://www.yahoo.com/music',
},
{
# yahoo://article/
'url': 'https://www.yahoo.com/movies/video/true-story-trailer-173000497.html',
'info_dict': {
'id': '071c4013-ce30-3a93-a5b2-e0413cd4a9d1',
'ext': 'mp4',
'title': "'True Story' Trailer",
'description': 'True Story',
},
'params': {
'skip_download': True,
},
},
{
# ytwnews://cavideo/
'url': 'https://tw.video.yahoo.com/movie-tw/單車天使-中文版預-092316541.html',
'info_dict': {
'id': 'ba133ff2-0793-3510-b636-59dfe9ff6cff',
'ext': 'mp4',
'title': '單車天使 - 中文版預',
'description': '中文版預',
},
'params': {
'skip_download': True,
},
},
]
def _real_extract(self, url):
@ -269,7 +295,8 @@ class YahooIE(InfoExtractor):
r'"first_videoid"\s*:\s*"([^"]+)"',
r'%s[^}]*"ccm_id"\s*:\s*"([^"]+)"' % re.escape(page_id),
r'<article[^>]data-uuid=["\']([^"\']+)',
r'yahoo://article/view\?.*\buuid=([^&"\']+)',
r'<meta[^<>]+yahoo://article/view\?.*\buuid=([^&"\']+)',
r'<meta[^<>]+["\']ytwnews://cavideo/(?:[^/]+/)+([\da-fA-F-]+)[&"\']',
]
video_id = self._search_regex(
CONTENT_ID_REGEXES, webpage, 'content ID')

View File

@ -1691,6 +1691,10 @@ def url_basename(url):
return path.strip('/').split('/')[-1]
def base_url(url):
return re.match(r'https?://[^?#&]+/', url).group()
class HEADRequest(compat_urllib_request.Request):
def get_method(self):
return 'HEAD'
@ -2345,11 +2349,18 @@ def _match_one(filter_part, dct):
m = operator_rex.search(filter_part)
if m:
op = COMPARISON_OPERATORS[m.group('op')]
if m.group('strval') is not None:
actual_value = dct.get(m.group('key'))
if (m.group('strval') is not None or
# If the original field is a string and matching comparisonvalue is
# a number we should respect the origin of the original field
# and process comparison value as a string (see
# https://github.com/rg3/youtube-dl/issues/11082).
actual_value is not None and m.group('intval') is not None and
isinstance(actual_value, compat_str)):
if m.group('op') not in ('=', '!='):
raise ValueError(
'Operator %s does not support string values!' % m.group('op'))
comparison_value = m.group('strval')
comparison_value = m.group('strval') or m.group('intval')
else:
try:
comparison_value = int(m.group('intval'))
@ -2361,7 +2372,6 @@ def _match_one(filter_part, dct):
raise ValueError(
'Invalid integer value %r in filter part %r' % (
m.group('intval'), filter_part))
actual_value = dct.get(m.group('key'))
if actual_value is None:
return m.group('none_inclusive')
return op(actual_value, comparison_value)

View File

@ -1,3 +1,3 @@
from __future__ import unicode_literals
__version__ = '2016.10.21.1'
__version__ = '2016.11.08.1'